Publications

@article{PR_FICE_2024,

title = {FICE: Text-conditioned fashion-image editing with guided GAN inversion},

author = {Martin Pernus and Clinton Fookes and Vitomir Struc and Simon Dobrisek},

url = {https://www.sciencedirect.com/science/article/pii/S0031320324007738

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/09/FICE_main_paper.pdf

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/09/FICE_supplementary.pdf},

doi = {https://doi.org/10.1016/j.patcog.2024.111022},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-01},

journal = {Pattern Recognition},

volume = {158},

number = {111022},

pages = {1-18},

abstract = {Fashion-image editing is a challenging computer-vision task where the goal is to incorporate selected apparel into a given input image. Most existing techniques, known as Virtual Try-On methods, deal with this task by first selecting an example image of the desired apparel and then transferring the clothing onto the target person. Conversely, in this paper, we consider editing fashion images with text descriptions. Such an approach has several advantages over example-based virtual try-on techniques: (i) it does not require an image of the target fashion item, and (ii) it allows the expression of a wide variety of visual concepts through the use of natural language. Existing image-editing methods that work with language inputs are heavily constrained by their requirement for training sets with rich attribute annotations or they are only able to handle simple text descriptions. We address these constraints by proposing a novel text-conditioned editing model called FICE (Fashion Image CLIP Editing) that is capable of handling a wide variety of diverse text descriptions to guide the editing procedure. Specifically, with FICE, we extend the common GAN-inversion process by including semantic, pose-related, and image-level constraints when generating images. We leverage the capabilities of the CLIP model to enforce the text-provided semantics, due to its impressive image–text association capabilities. We furthermore propose a latent-code regularization technique that provides the means to better control the fidelity of the synthesized images. We validate the FICE through rigorous experiments on a combination of VITON images and Fashion-Gen text descriptions and in comparison with several state-of-the-art, text-conditioned, image-editing approaches. Experimental results demonstrate that the FICE generates very realistic fashion images and leads to better editing than existing, competing approaches. The source code is publicly available from: 

https://github.com/MartinPernus/FICE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Vitek2024_Gaze,

title = {GazeNet: A lightweight multitask sclera feature extractor},

author = {Matej Vitek and Vitomir Štruc and Peter Peer},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/11/1-s2.0-S1110016824014273-main.pdf

https://www.sciencedirect.com/science/article/pii/S1110016824014273},

doi = {https://doi.org/10.1016/j.aej.2024.11.011},

year  = {2025},

date = {2025-01-05},

journal = {Alexandria Engineering Journal},

volume = {112},

pages = {661-671},

abstract = {The sclera is a recently emergent biometric modality with many desirable characteristics. However, most literature solutions for sclera-based recognition rely on sequences of complex deep networks with significant computational overhead. In this paper, we propose a lightweight multitask-based sclera feature extractor. The proposed GazeNet network has a computational complexity below 1 GFLOP, making it appropriate for less capable devices like smartphones and head-mounted displays. Our experiments show that GazeNet (which is based on the SqueezeNet architecture) outperforms both the base SqueezeNet model as well as the more computationally intensive ScleraNET model from the literature. Thus, we demonstrate that our proposed gaze-direction multitask learning procedure, along with careful lightweight architecture selection, leads to computationally efficient networks with high recognition performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{KBS_2024,

title = {Transfer-Learning Enabled Micro-Expression Recognition Using Dense Connections and Mixed Attention},

author = {Chenquan Gan and Junhao Xiao and Qingyi Zhu and Deepak Kumar Jain and Vitomir Struc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/11/Transfer_Learning_Enabled_compressed.pdf},

doi = {https://doi.org/10.1016/j.knosys.2024.112640},

year  = {2024},

date = {2024-12-01},

urldate = {2025-02-01},

journal = {Knowledge Based Systems},

volume = {305},

number = {112640},

issue = {December 2024},

abstract = {Micro-expression recognition (MER) is a challenging computer vision problem, where the limited amount of available training data and insufficient intensity of the facial expressions are among the main issues adversely affecting the performance of existing recognition models. To address these challenges, this paper explores a transfer–learning enabled MER model using a densely connected feature extraction module with mixed attention. Unlike previous works that utilize transfer learning to facilitate MER and extract local facial expression information, our model relies on pretraining with three diverse macro-expression datasets and, as a result, can: (i) overcome the problem of insufficient sample size and limited training data availability, (ii) leverage (related) domain-specific information from multiple datasets with diverse characteristics, and (iii) improve the model adaptability to complex scenes. Furthermore, to enhance the intensity of the micro expressions and improve the discriminability of the extracted features, the Euler video magnification (EVM) method is adopted in the preprocessing stage and then used jointly with a densely connected feature extraction module and a mixed attention mechanism to derive expressive feature representations for the classification procedure. The proposed feature extraction mechanism not only guarantees the integrity of the extracted features but also efficiently captures local texture cues by aggregating the most salient information from the generated feature maps, which is key for the MER task. The experimental results on multiple datasets demonstrate the robustness and effectiveness of our model compared to the state-of-the-art.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Darian2024,

title = {Generating bimodal privacy-preserving data for face recognition},

author = {Darian Tomašević and Fadi Boutros and Naser Damer and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/05/PapersDarian.pdf},

doi = {https://doi.org/10.1016/j.engappai.2024.108495},

year  = {2024},

date = {2024-05-01},

journal = {Engineering Applications of Artificial Intelligence},

volume = {133},

issue = {E},

pages = {1-25},

abstract = {The performance of state-of-the-art face recognition systems depends crucially on the availability of large-scale training datasets. However, increasing privacy concerns nowadays accompany the collection and distribution of biometric data, which has already resulted in the retraction of valuable face recognition datasets. The use of synthetic data represents a potential solution, however, the generation of privacy-preserving facial images useful for training recognition models is still an open problem. Generative methods also remain bound to the visible spectrum, despite the benefits that multispectral data can provide. To address these issues, we present a novel identity-conditioned generative framework capable of producing large-scale recognition datasets of visible and near-infrared privacy-preserving face images. The framework relies on a novel identity-conditioned dual-branch style-based generative adversarial network to enable the synthesis of aligned high-quality samples of identities determined by features of a pretrained recognition model. In addition, the framework incorporates a novel filter to prevent samples of privacy-breaching identities from reaching the generated datasets and improve both identity separability and intra-identity diversity. Extensive experiments on six publicly available datasets reveal that our framework achieves competitive synthesis capabilities while preserving the privacy of real-world subjects. The synthesized datasets also facilitate training more powerful recognition models than datasets generated by competing methods or even small-scale real-world datasets. Employing both visible and near-infrared data for training also results in higher recognition accuracy on real-world visible spectrum benchmarks. Therefore, training with multispectral data could potentially improve existing recognition systems that utilize only the visible spectrum, without the need for additional sensors.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{BabnikTBIOM2024,

title = {eDifFIQA: Towards Efficient Face Image Quality Assessment based on Denoising Diffusion Probabilistic Models},

author = {Žiga Babnik and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/03/TBIOM___DifFIQAv2.pdf

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10468647&tag=1},

doi = {10.1109/TBIOM.2024.3376236},

issn = {2637-6407},

year  = {2024},

date = {2024-03-07},

urldate = {2024-03-07},

journal = {IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM)},

pages = {1-16},

abstract = {State-of-the-art Face Recognition (FR) models perform well in constrained scenarios, but frequently fail in difficult real-world scenarios, when no quality guarantees can be made for face samples. For this reason, Face Image Quality Assessment (FIQA) techniques are often used by FR systems, to provide quality estimates of captured face samples. The quality estimate provided by FIQA techniques can be used by the FR system to reject samples of low-quality, in turn improving the performance of the system and reducing the number of critical false-match errors. However, despite steady improvements, ensuring a good trade-off between the performance and computational complexity of FIQA methods across diverse face samples remains challenging. In this paper, we present DifFIQA, a powerful unsupervised approach for quality assessment based on the popular denoising diffusion probabilistic models (DDPMs) and the extended (eDifFIQA) approach. The main idea of the base DifFIQA approach is to utilize the forward and backward processes of DDPMs to perturb facial images and quantify the impact of these perturbations on the corresponding image embeddings for quality prediction. Because of the iterative nature of DDPMs the base DifFIQA approach is extremely computationally expensive. Using eDifFIQA we are able to improve on both the performance and computational complexity of the base DifFIQA approach, by employing label optimized knowledge distillation. In this process, quality information inferred by DifFIQA is distilled into a quality-regression model. During the distillation process, we use an additional source of quality information hidden in the relative position of the embedding to further improve the predictive capabilities of the underlying regression model. By choosing different feature extraction backbone models as the basis for the quality-regression eDifFIQA model, we are able to control the trade-off between the predictive capabilities and computational complexity of the final model. We evaluate three eDifFIQA variants of varying sizes in comprehensive experiments on 7 diverse datasets containing static-images and a separate video-based dataset, with 4 target CNN-based FR models and 2 target Transformer-based FR models and against 10 state-of-the-art FIQA techniques, as well as against the initial DifFIQA baseline and a simple regression-based predictor DifFIQA(R), distilled from DifFIQA without any additional optimization. The results show that the proposed label optimized knowledge distillation improves on the performance and computationally complexity of the base DifFIQA approach, and is able to achieve state-of-the-art performance in several distinct experimental scenarios. Furthermore, we also show that the distilled model can be used directly for face recognition and leads to highly competitive results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PR_Fairness2024,

title = {Fairness in Face Presentation Attack Detection},

author = {Meiling Fang and Wufei Yang and Arjan Kuijper and Vitomir S̆truc and Naser Damer},

url = {https://www.sciencedirect.com/science/article/pii/S0031320323007008?dgcid=coauthor},

year  = {2024},

date = {2024-03-01},

urldate = {2024-03-01},

journal = {Pattern Recognition},

volume = {147 },

issue = {110002},

pages = {1-14},

abstract = {Face recognition (FR) algorithms have been proven to exhibit discriminatory behaviors against certain demographic and non-demographic groups, raising ethical and legal concerns regarding their deployment in real-world scenarios. Despite the growing number of fairness studies in FR, the fairness of face presentation attack detection (PAD) has been overlooked, mainly due to the lack of appropriately annotated data. To avoid and mitigate the potential negative impact of such behavior, it is essential to assess the fairness in face PAD and develop fair PAD models. To enable fairness analysis in face PAD, we present a Combined Attribute Annotated PAD Dataset (CAAD-PAD), offering seven human-annotated attribute labels. Then, we comprehensively analyze the fairness of PAD and its relation to the nature of the training data and the Operational Decision Threshold Assignment (ODTA) through a set of face PAD solutions. Additionally, we propose a novel metric, the Accuracy Balanced Fairness (ABF), that jointly represents both the PAD fairness and the absolute PAD performance. The experimental results pointed out that female and faces with occluding features (e.g. eyeglasses, beard, etc.) are relatively less protected than male and non-occlusion groups by all PAD solutions. To alleviate this observed unfairness, we propose a plug-and-play data augmentation method, FairSWAP, to disrupt the identity/semantic information and encourage models to mine the attack clues. The extensive experimental results indicate that FairSWAP leads to better-performing and fairer face PADs in 10 out of 12 investigated cases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ESWA2024,

title = {Y-GAN: Learning Dual Data Representations for Anomaly Detection in Images},

author = {Marija Ivanovska and Vitomir Štruc},

url = {https://www.sciencedirect.com/science/article/pii/S0957417424002756

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/02/YGAN_Marija.pdf},

doi = {https://doi.org/10.1016/j.eswa.2024.123410},

year  = {2024},

date = {2024-03-01},

urldate = {2024-03-01},

journal = {Expert Systems with Applications (ESWA)},

volume = {248},

number = {123410},

pages = {1-7},

abstract = {We propose a novel reconstruction-based model for anomaly detection in image data, called 'Y-GAN'. The model consists of a Y-shaped auto-encoder and represents images in two separate latent spaces. The first captures meaningful image semantics, which are key for representing (normal) training data, whereas the second encodes low-level residual image characteristics. To ensure the dual representations encode mutually exclusive information, a disentanglement procedure is designed around a latent (proxy) classifier. Additionally, a novel representation-consistency mechanism is proposed to prevent information leakage between the latent spaces. The model is trained in a one-class learning setting using only normal training data. Due to the separation of semantically-relevant and residual information, Y-GAN is able to derive informative data representations that allow for efficacious anomaly detection across a diverse set of anomaly detection tasks. The model is evaluated in comprehensive experiments with several recent anomaly detection models using four popular image datasets, i.e., MNIST, FMNIST, CIFAR10, and PlantVillage. Experimental results show that Y-GAN outperforms all tested models by a considerable margin and yields state-of-the-art results. The source code for the model is made publicly available at https://github.com/MIvanovska/Y-GAN. },

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{InformSciences2024,

title = {A graph neural network with context filtering and feature correction for conversational emotion recognition},

author = {Chenquan Gan and Jiahao Zheng and Qingyi Zhu and Deepak Kumar Jain and Vitomir {v{S}}truc, },

url = {https://www.sciencedirect.com/science/article/pii/S002002552301602X?via%3Dihub

https://lmi.fe.uni-lj.si/wp-content/uploads/2023/12/InformationSciences.pdf},

doi = {https://doi.org/10.1016/j.ins.2023.120017},

year  = {2024},

date = {2024-02-01},

journal = {Information Sciences},

volume = {658},

number = {120017},

pages = {1-21},

abstract = {Conversational emotion recognition represents an important machine-learning problem with a wide variety of deployment possibilities. The key challenge in this area is how to properly capture the key conversational aspects that facilitate reliable emotion recognition, including utterance semantics, temporal order, informative contextual cues, speaker interactions as well as other relevant factors. In this paper, we present a novel Graph Neural Network approach for conversational emotion recognition at the utterance level. Our method addresses the outlined challenges and represents conversations in the form of graph structures that naturally encode temporal order, speaker dependencies, and even long-distance context. To efficiently capture the semantic content of the conversations, we leverage the zero-shot feature-extraction capabilities of pre-trained large-scale language models and then integrate two key contributions into the graph neural network to ensure competitive recognition results. The first is a novel context filter that establishes meaningful utterance dependencies for the graph construction procedure and removes low-relevance and uninformative utterances from being used as a source of contextual information for the recognition task. The second contribution is a feature-correction procedure that adjusts the information content in the generated feature representations through a gating mechanism to improve their discriminative power and reduce emotion-prediction errors. We conduct extensive experiments on four commonly used conversational datasets, i.e., IEMOCAP, MELD, Dailydialog, and EmoryNLP, to demonstrate the capabilities of the developed graph neural network with context filtering and error-correction capabilities. The results of the experiments point to highly promising performance, especially when compared to state-of-the-art competitors from the literature.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{KrizajEAAI2024,

title = {Deep Face Decoder: Towards understanding the embedding space of convolutional networks through visual reconstruction of deep face templates},

author = {Janez Križaj and Richard O. Plesh and Mahesh Banavar and Stephanie Schuckers and Vitomir Štruc},

url = {https://www.sciencedirect.com/science/article/abs/pii/S095219762400099X

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/02/DFD_Overleaf.pdf},

doi = {https://doi.org/10.1016/j.engappai.2024.107941},

year  = {2024},

date = {2024-01-30},

urldate = {2024-01-30},

journal = {Engineering Applications of Artificial Intelligence},

volume = {132},

issue = {107941},

pages = {1-20},

abstract = {Advances in deep learning and convolutional neural networks (ConvNets) have driven remarkable face recognition (FR) progress recently. However, the black-box nature of modern ConvNet-based face recognition models makes it challenging to interpret their decision-making process, to understand the reasoning behind specific success and failure cases, or to predict their responses to unseen data characteristics. It is, therefore, critical to design mechanisms that explain the inner workings of contemporary FR models and offer insight into their behavior. To address this challenge, we present in this paper a novel textit{template-inversion approach} capable of reconstructing high-fidelity face images from the embeddings (templates, feature-space representations) produced by modern FR techniques. Our approach is based on a novel Deep Face Decoder (DFD) trained in a regression setting to visualize the information encoded in the embedding space with the goal of fostering explainability. We utilize the developed DFD model in comprehensive experiments on multiple unconstrained face datasets, namely Visual Geometry Group Face dataset 2 (VGGFace2), Labeled Faces in the Wild (LFW), and Celebrity Faces Attributes Dataset High Quality (CelebA-HQ). Our analysis focuses on the embedding spaces of two distinct face recognition models with backbones based on the Visual Geometry Group 16-layer model (VGG-16) and the 50-layer Residual Network (ResNet-50). The results reveal how information is encoded in the two considered models and how perturbations in image appearance due to rotations, translations, scaling, occlusion, or adversarial attacks, are propagated into the embedding space. Our study offers researchers a deeper comprehension of the underlying mechanisms of ConvNet-based FR models, ultimately promoting advancements in model design and explainability. },

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{MaskFaceGAN,

title = {MaskFaceGAN: High Resolution Face Editing With Masked GAN Latent Code Optimization},

author = {Martin Pernuš and Vitomir Štruc and Simon Dobrišek},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10299582

https://lmi.fe.uni-lj.si/wp-content/uploads/2023/02/MaskFaceGAN_compressed.pdf

https://arxiv.org/pdf/2103.11135.pdf},

doi = {10.1109/TIP.2023.3326675},

issn = {1941-0042},

year  = {2023},

date = {2023-10-27},

urldate = {2023-01-02},

journal = {IEEE Transactions on Image Processing},

abstract = {Face editing represents a popular research topic within the computer vision and image processing communities. While significant progress has been made recently in this area, existing solutions: ( i ) are still largely focused on low-resolution images, ( ii ) often generate editing results with visual artefacts, or ( iii ) lack fine-grained control over the editing procedure and alter multiple (entangled) attributes simultaneously, when trying to generate the desired facial semantics. In this paper, we aim to address these issues through a novel editing approach, called MaskFaceGAN that focuses on local attribute editing. The proposed approach is based on an optimization procedure that directly optimizes the latent code of a pre-trained (state-of-the-art) Generative Adversarial Network (i.e., StyleGAN2) with respect to several constraints that ensure: ( i ) preservation of relevant image content, ( ii ) generation of the targeted facial attributes, and ( iii ) spatially–selective treatment of local image regions. The constraints are enforced with the help of an (differentiable) attribute classifier and face parser that provide the necessary reference information for the optimization procedure. MaskFaceGAN is evaluated in extensive experiments on the FRGC, SiblingsDB-HQf, and XM2VTS datasets and in comparison with several state-of-the-art techniques from the literature. Our experimental results show that the proposed approach is able to edit face images with respect to several local facial attributes with unprecedented image quality and at high-resolutions (1024×1024), while exhibiting considerably less problems with attribute entanglement than competing solutions. The source code is publicly available from: https://github.com/MartinPernus/MaskFaceGAN.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PrivacProberRot,

title = {PrivacyProber: Assessment and Detection of Soft–Biometric Privacy–Enhancing Techniques},

author = {Peter Rot and Klemen Grm and Peter Peer and Vitomir Štruc},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10264192},

doi = {10.1109/TDSC.2023.3319500},

isbn = {1545-5971},

year  = {2023},

date = {2023-09-23},

journal = {IEEE Transactions on Dependable and Secure Computing},

pages = {1-18},

abstract = {Soft–biometric privacy–enhancing techniques represent machine learning methods that aim to: (i) mitigate privacy concerns associated with face recognition technology by suppressing selected soft–biometric attributes in facial images (e.g., gender, age, ethnicity) and (ii) make unsolicited extraction of sensitive personal information infeasible. Because such techniques are increasingly used in real–world applications, it is imperative to understand to what extent the privacy enhancement can be inverted and how much attribute information can be recovered from privacy–enhanced images. While these aspects are critical, they have not been investigated in the literature so far. In this paper, we, therefore, study the robustness of several state–of–the–art soft–biometric privacy–enhancing techniques to attribute recovery attempts. We propose PrivacyProber, a high–level framework for restoring soft–biometric information from privacy–enhanced facial images, and apply it for attribute recovery in comprehensive experiments on three public face datasets, i.e., LFW, MUCT and Adience. Our experiments show that the proposed framework is able to restore a considerable amount of suppressed information, regardless of the privacy–enhancing technique used (e.g., adversarial perturbations, conditional synthesis, etc.), but also that there are significant differences between the considered privacy models. These results point to the need for novel mechanisms that can improve the robustness of existing privacy–enhancing techniques and secure them against potential adversaries trying to restore suppressed information. Additionally, we demonstrate that PrivacyProber can also be used to detect privacy–enhancement in facial images (under black–box assumptions) with high accuracy. Specifically, we show that a detection procedure can be developed around the proposed framework that is learning free and, therefore, generalizes well across different data characteristics and privacy–enhancing techniques.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{VitekSaud2023,

title = {IPAD: Iterative Pruning with Activation Deviation for Sclera Biometrics},

author = {Matej Vitek and Matic Bizjak and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/07/PublishedVersion.pdf},

doi = {https://doi.org/10.1016/j.jksuci.2023.101630},

year  = {2023},

date = {2023-07-10},

journal = {Journal of King Saud University - Computer and Information Sciences},

volume = {35},

number = {8},

pages = {1-21},

abstract = {The sclera has recently been gaining attention as a biometric modality due to its various desirable characteristics. A key step in any type of ocular biometric recognition, including sclera recognition, is the segmentation of the relevant part(s) of the eye. However, the high computational complexity of the (deep) segmentation models used in this task can limit their applicability on resource-constrained devices such as smartphones or head-mounted displays. As these devices are a common desired target for such biometric systems, lightweight solutions for ocular segmentation are critically needed. To address this issue, this paper introduces IPAD (Iterative Pruning with Activation Deviation), a novel method for developing lightweight convolutional networks, that is based on model pruning. IPAD uses a novel filter-activation-based criterion (ADC) to determine low-importance filters and employs an iterative model pruning procedure to derive the final lightweight model. To evaluate the proposed pruning procedure, we conduct extensive experiments with two diverse segmentation models, over four publicly available datasets (SBVPI, SLD, SMD and MOBIUS), in four distinct problem configurations and in comparison to state-of-the-art methods from the literature. The results of the experiments show that the proposed filter-importance criterion outperforms the standard L1 and L2 approaches from the literature. Furthermore, the results also suggest that: 1) the pruned models are able to retain (or even improve on) the performance of the unpruned originals, as long as they are not over-pruned, with RITnet and U-Net at 50% of their original FLOPs reaching up to 4% and 7% higher IoU values than their unpruned versions, respectively, 2) smaller models require more careful pruning, as the pruning process can hurt the model’s generalization capabilities, and 3) the novel criterion most convincingly outperforms the classic approaches when sufficient training data is available, implying that the abundance of data leads to more robust activation-based importance computation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{AccessMartin2023,

title = {ChildNet: Structural Kinship Face Synthesis Model With Appearance Control Mechanisms},

author = {Martin Pernuš and Mansi Bhatnagar and Badr Samad and Divyanshu Singh and Peter Peer and Vitomir Štruc and Simon Dobrišek},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10126110},

doi = {10.1109/ACCESS.2023.3276877},

issn = {2169-3536},

year  = {2023},

date = {2023-05-17},

journal = {IEEE Access},

pages = {1-22},

abstract = {Kinship face synthesis is an increasingly popular topic within the computer vision community, particularly the task of predicting the child appearance using parental images. Previous work has been limited in terms of model capacity and inadequate training data, which is comprised of low-resolution and tightly cropped images, leading to lower synthesis quality. In this paper, we propose ChildNet,  a method for kinship face synthesis that leverages the facial image generation capabilities of a state-of-the-art Generative Adversarial Network (GAN), and resolves the aforementioned problems. ChildNet is designed within the GAN latent space and is able to predict a child appearance that bears high resemblance to real parents’ children. To ensure fine-grained control, we propose an age and gender manipulation module that allows precise manipulation of the child synthesis result. ChildNet is capable of generating multiple child images per parent pair input, while providing a way to control the image generation variability. Additionally, we introduce a mechanism to control the dominant parent image. Finally, to facilitate the task of kinship face synthesis, we introduce a new kinship dataset, called Next of Kin. This dataset contains 3690 high-resolution face images with a diverse range of ethnicities and ages. We evaluate ChildNet in comprehensive experiments against three competing kinship face synthesis models, using two kinship datasets. The experiments demonstrate the superior performance of ChildNet in terms of identity similarity, while exhibiting high perceptual image quality. The source code for the model is publicly available at: https://github.com/MartinPernus/ChildNet.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{FadiIVCSynthetic,

title = {Synthetic data for face recognition: Current state and future prospects},

author = {Fadi Boutros and Vitomir Štruc and Julian Fierrez and Naser Damer},

url = {https://www.sciencedirect.com/science/article/pii/S0262885623000628},

doi = {https://doi.org/10.1016/j.imavis.2023.104688},

year  = {2023},

date = {2023-05-15},

urldate = {2023-05-15},

journal = {Image and Vision Computing},

number = {104688},

abstract = {Over the past years, deep learning capabilities and the availability of large-scale training datasets advanced rapidly, leading to breakthroughs in face recognition accuracy. However, these technologies are foreseen to face a major challenge in the next years due to the legal and ethical concerns about using authentic biometric data in AI model training and evaluation along with increasingly utilizing data-hungry state-of-the-art deep learning models. With the recent advances in deep generative models and their success in generating realistic and high-resolution synthetic image data, privacy-friendly synthetic data has been recently proposed as an alternative to privacy-sensitive authentic data to overcome the challenges of using authentic data in face recognition development. This work aims at providing a clear and structured picture of the use-cases taxonomy of synthetic face data in face recognition along with the recent emerging advances of face recognition models developed on the bases of synthetic data. We also discuss the challenges facing the use of synthetic data in face recognition development and several future prospects of synthetic data in the domain of face recognition.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Grabner_TSG,

title = {A global modeling framework for load forecasting in distribution networks},

author = {Miha Grabner and Yi Wang and Qingsong Wen and Boštjan Blažič and Vitomir Štruc},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10092804},

doi = {10.1109/TSG.2023.3264525},

issn = {1949-3061},

year  = {2023},

date = {2023-04-05},

journal = {IEEE Transactions on Smart Grid},

abstract = {With the increasing numbers of smart meter installations, scalable and efficient load forecasting techniques are critically needed to ensure sustainable situation awareness within the distribution networks. Distribution networks include a large amount of different loads at various aggregation levels, such as individual consumers, low-voltage feeders, and transformer stations. It is impractical to develop individual (or so-called local) forecasting models for each load separately. Additionally, such local models also (i) (largely) ignore the strong dependencies between different loads that might be present due to their spatial proximity and the characteristics of the distribution network, (ii) require historical data for each load to be able to make forecasts, and (iii) are incapable of adjusting to changes in the load behavior without retraining. To address these issues, we propose a global modeling framework for load forecasting in distribution networks that, unlike its local competitors, relies on a single global model to generate forecasts for a large number of loads. The global nature of the framework, significantly reduces the computational burden typically required when training multiple local forecasting models, efficiently exploits the cross-series information shared among different loads, and facilitates forecasts even when historical data for a load is missing or the behavior of a load evolves over time. To further improve on the performance of the proposed framework, an unsupervised localization mechanism and optimal ensemble construction strategy are also proposed to localize/personalize the global forecasting model to different load characteristics. Our experimental results show that the proposed framework outperforms naive benchmarks by more than 25% (in terms of Mean Absolute Error) on real-world dataset while exhibiting highly desirable characteristics when compared to the local models that are predominantly used in the literature. All source code and data are made publicly available to enable reproducibility: https://github.com/mihagrabner/GlobalModelingFramework},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{MedenDeID2023,

title = {Face deidentification with controllable privacy protection},

author = {Blaž Meden and Manfred Gonzalez-Hernandez and Peter Peer and Vitomir Štruc},

url = {https://reader.elsevier.com/reader/sd/pii/S0262885623000525?token=BC1E21411C50118E666720B002A89C9EB3DB4CFEEB5EB18D7BD7B0613085030A96621C8364583BFE7BAE025BE3646096&originRegion=eu-west-1&originCreation=20230516115322},

doi = {https://doi.org/10.1016/j.imavis.2023.104678},

year  = {2023},

date = {2023-04-01},

journal = {Image and Vision Computing},

volume = {134},

number = {104678},

pages = {1-19},

abstract = {Privacy protection has become a crucial concern in today’s digital age. Particularly sensitive here are facial images, which typically not only reveal a person’s identity, but also other sensitive personal information. To address this problem, various face deidentification techniques have been presented in the literature. These techniques try to remove or obscure personal information from facial images while still preserving their usefulness for further analysis. While a considerable amount of work has been proposed on face deidentification, most state-of-theart solutions still suffer from various drawbacks, and (a) deidentify only a narrow facial area, leaving potentially important contextual information unprotected, (b) modify facial images to such degrees, that image naturalness and facial diversity is suffering in the deidentify images, (c) offer no flexibility in the level of privacy protection ensured, leading to suboptimal deployment in various applications, and (d) often offer an unsatisfactory tradeoff between the ability to obscure identity information, quality and naturalness of the deidentified images, and sufficient utility preservation. In this paper, we address these shortcomings with a novel controllable face deidentification technique that balances image quality, identity protection, and data utility for further analysis. The proposed approach utilizes a powerful generative model (StyleGAN2), multiple auxiliary classification models, and carefully designed constraints to guide the deidentification process. The approach is validated across four diverse datasets (CelebA-HQ, RaFD, XM2VTS, AffectNet) and in comparison to 7 state-of-the-art competitors. The results of the experiments demonstrate that the proposed solution leads to: (a) a considerable level of identity protection, (b) valuable preservation of data utility, (c) sufficient diversity among the deidentified faces, and (d) encouraging overall performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{TIFS_Sclera2022,

title = {Exploring Bias in Sclera Segmentation Models: A Group Evaluation Approach},

author = {Matej Vitek and Abhijit Das and Diego Rafael Lucio and Luiz Antonio Zanlorensi Jr. and David Menotti and Jalil Nourmohammadi Khiarak and Mohsen Akbari Shahpar and Meysam Asgari-Chenaghlu and Farhang Jaryani and Juan E. Tapia and Andres Valenzuela and Caiyong Wang and Yunlong Wang and Zhaofeng He and Zhenan Sun and Fadi Boutros and Naser Damer and Jonas Henry Grebe and Arjan Kuijper and Kiran Raja and Gourav Gupta and Georgios Zampoukis and Lazaros Tsochatzidis and Ioannis Pratikakis and S. V. Aruna Kumar and B. S. Harish and Umapada Pal and Peter Peer and Vitomir Štruc},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9926136},

doi = {10.1109/TIFS.2022.3216468},

issn = {1556-6013},

year  = {2023},

date = {2023-01-18},

urldate = {2022-10-18},

journal = {IEEE Transactions on Information Forensics and Security},

volume = {18},

pages = {190-205},

abstract = {Bias and fairness of biometric algorithms have been key topics of research in recent years, mainly due to the societal, legal and ethical implications of potentially unfair decisions made by automated decision-making models. A considerable amount of work has been done on this topic across different biometric modalities, aiming at better understanding the main sources of algorithmic bias or devising mitigation measures. In this work, we contribute to these efforts and present the first study investigating bias and fairness of sclera segmentation models. Although sclera segmentation techniques represent a key component of sclera-based biometric systems with a considerable impact on the overall recognition performance, the presence of different types of biases in sclera segmentation methods is still underexplored. To address this limitation, we describe the results of a group evaluation effort (involving seven research groups), organized to explore the performance of recent sclera segmentation models within a common experimental framework and study performance differences (and bias), originating from various demographic as well as environmental factors. Using five diverse datasets, we analyze seven independently developed sclera segmentation models in different experimental configurations. The results of our experiments suggest that there are significant differences in the overall segmentation performance across the seven models and that among the considered factors, ethnicity appears to be the biggest cause of bias. Additionally, we observe that training with representative and balanced data does not necessarily lead to less biased results. Finally, we find that in general there appears to be a negative correlation between the amount of bias observed (due to eye color, ethnicity and acquisition device) and the overall segmentation performance, suggesting that advances in the field of semantic segmentation may also help with mitigating bias.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{IVC2023,

title = {A Survey on Computer Vision based Human Analysis in the COVID-19 Era},

author = {Fevziye Irem Eyiokur and Alperen Kantarci and Mustafa Ekrem Erakin and Naser Damer and Ferda Ofli and Muhammad Imran and Janez Križaj and Albert Ali Salah and Alexander Waibel and Vitomir Štruc and Hazim K. Ekenel },

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/01/FG4COVID19_PAPER_compressed.pdf

https://authors.elsevier.com/a/1gKOyxnVK7RBS},

doi = {https://doi.org/10.1016/j.imavis.2022.104610},

year  = {2023},

date = {2023-01-01},

journal = {Image and Vision Computing},

volume = {130},

number = {104610},

pages = {1-19},

abstract = {The emergence of COVID-19 has had a global and profound impact, not only on society as a whole, but also on the lives of individuals. Various prevention measures were introduced around the world to limit the transmission of the disease, including 

face masks, mandates for social distancing and regular disinfection in public spaces, and the use of screening applications. These developments also triggered the need for novel and improved computer vision techniques capable of (i) providing support to the prevention measures through an automated analysis of visual data, on the one hand, and (ii) facilitating normal operation of existing vision-based services, such as biometric authentication schemes, on the other. Especially important here, are computer vision techniques that focus on the analysis of people and faces in visual data and have been affected the most by the partial occlusions introduced by the mandates for facial masks. 

Such computer vision based human analysis techniques include face and face-mask detection approaches, face recognition techniques, crowd counting solutions, age and expression estimation procedures, models for detecting face-hand interactions and many others, and have seen considerable attention over recent years. The goal of this survey is to provide an introduction to the problems induced by COVID-19 into such research and to present a comprehensive review of the work done in the computer vision based human analysis field. Particular attention is paid to the impact of facial masks on the performance of various methods and recent solutions to mitigate this problem. Additionally, a detailed review of existing datasets useful for the development and evaluation of methods for COVID-19 related applications is also provided. Finally, to help advance the field further, a discussion on the main open challenges and future research direction is given at the end of the survey. This work is intended to have a broad appeal and be useful not only for computer vision researchers but also the general public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{UhljiIETZiga,

title = {Efficient ear alignment using a two-stack hourglass network},

author = {Anja Hrovatič and Peter Peer and Vitomir Štruc and Žiga Emeršič},

url = {https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/bme2.12109},

doi = {10.1049/bme2.12109},

issn = {2047-4938},

year  = {2023},

date = {2023-01-01},

journal = {IET Biometrics },

pages = {1-14},

abstract = {Ear images have been shown to be a reliable modality for biometric recognition with desirable characteristics, such as high universality, distinctiveness, measurability and permanence. While a considerable amount of research has been directed towards ear recognition techniques, the problem of ear alignment is still under-explored in the open literature. Nonetheless, accurate alignment of ear images, especially in unconstrained acquisition scenarios, where the ear appearance is expected to vary widely due to pose and view point variations, is critical for the performance of all downstream tasks, including ear recognition. Here, the authors address this problem and present a framework for ear alignment that relies on a two-step procedure: (i) automatic landmark detection and (ii) fiducial point alignment. For the first (landmark detection) step, the authors implement and train a Two-Stack Hourglass model (2-SHGNet) capable of accurately predicting 55 landmarks on diverse ear images captured in uncontrolled conditions. For the second (alignment) step, the authors use the Random Sample Consensus (RANSAC) algorithm to align the estimated landmark/fiducial points with a pre-defined ear shape (i.e. a collection of average ear landmark positions). The authors evaluate the proposed framework in comprehensive experiments on the AWEx and ITWE datasets and show that the 2-SHGNet model leads to more accurate landmark predictions than competing state-of-the-art models from the literature. Furthermore, the authors also demonstrate that the alignment step significantly improves recognition accuracy with ear images from unconstrained environments compared to unaligned imagery.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{TextEmotionESWA,

title = {DHF-Net: A hierarchical feature interactive fusion network for dialogue emotion recognition},

author = {Chenquan Gan and Yucheng Yang and Qingyi Zhub and Deepak Kumar Jain and Vitomir Struc},

url = {https://www.sciencedirect.com/science/article/pii/S0957417422016025?via%3Dihub},

doi = {https://doi.org/10.1016/j.eswa.2022.118525},

year  = {2022},

date = {2022-12-30},

urldate = {2022-08-01},

journal = {Expert Systems with Applications},

volume = {210},

abstract = {To balance the trade-off between contextual information and fine-grained information in identifying specific emotions during a dialogue and combine the interaction of hierarchical feature related information, this paper proposes a hierarchical feature interactive fusion network (named DHF-Net), which not only can retain the integrity of the context sequence information but also can extract more fine-grained information. To obtain a deep semantic information, DHF-Net processes the task of recognizing dialogue emotion and dialogue act/intent separately, and then learns the cross-impact of two tasks through collaborative attention. Also, a bidirectional gate recurrent unit (Bi-GRU) connected hybrid convolutional neural network (CNN) group method is designed, by which the sequence information is smoothly sent to the multi-level local information layers for feature exaction. Experimental results show that, on two open session datasets, the performance of DHF-Net is improved by 1.8% and 1.2%, respectively.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{TomasevicSensors,

title = {Reconstructing Superquadrics from Intensity and Color Images},

author = {Darian Tomašecić and Peter Peer and Franc Solina and Aleš Jaklič and Vitomir Štruc},

url = {https://www.mdpi.com/1424-8220/22/14/5332/pdf?version=1658380987},

doi = {https://doi.org/10.3390/s22145332},

year  = {2022},

date = {2022-07-16},

journal = {Sensors},

volume = {22},

number = {5332},

issue = {4},

abstract = {The task of reconstructing 3D scenes based on visual data represents a longstanding problem in computer vision. Common reconstruction approaches rely on the use of multiple volumetric primitives to describe complex objects. Superquadrics (a class of volumetric primitives) have shown great promise due to their ability to describe various shapes with only a few parameters. Recent research has shown that deep learning methods can be used to accurately reconstruct random superquadrics from both 3D point cloud data and simple depth images. In this paper, we extended these reconstruction methods to intensity and color images. Specifically, we used a dedicated convolutional neural network (CNN) model to reconstruct a single superquadric from the given input image. We analyzed the results in a qualitative and quantitative manner, by visualizing reconstructed superquadrics as well as observing error and accuracy distributions of predictions. We showed that a CNN model designed around a simple ResNet backbone can be used to accurately reconstruct superquadrics from images containing one object, but only if one of the spatial parameters is fixed or if it can be determined from other image characteristics, e.g., shadows. Furthermore, we experimented with images of increasing complexity, for example, by adding textures, and observed that the results degraded only slightly. In addition, we show that our model outperforms the current state-of-the-art method on the studied task. Our final result is a highly accurate superquadric reconstruction model, which can also reconstruct superquadrics from real images of simple objects, without additional training.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{TBIOM_2022,

title = {An Attack on Feature Level-based Facial Soft-biometric Privacy Enhancement},

author = {Daile Osorio-Roig and Christian Rathgeb and Pawel Drozdowski and Philipp Terhörst and Vitomir Štruc and Christoph Busch},

url = {https://arxiv.org/pdf/2111.12405.pdf},

year  = {2022},

date = {2022-05-02},

urldate = {2022-05-02},

journal = {IEEE Transactions on Biometrics, Identity and Behavior (TBIOM)},

volume = {4},

issue = {2},

pages = {263-275},

abstract = {In the recent past, different researchers have proposed novel privacy-enhancing face recognition systems designed to conceal soft-biometric information at feature level. These works have reported impressive results, but usually do not consider specific attacks in their analysis of privacy protection. In most cases, the privacy protection capabilities of these schemes are tested through simple machine learning-based classifiers and visualisations of dimensionality reduction tools. In this work, we introduce an attack on feature level-based facial soft–biometric privacy-enhancement techniques. The attack is based on two observations: (1) to achieve high recognition accuracy, certain similarities between facial representations have to be retained in their privacy-enhanced versions; (2) highly similar facial representations usually originate from face images with similar soft-biometric attributes. Based on these observations, the proposed attack compares a privacy-enhanced face representation against a set of privacy-enhanced face representations with known soft-biometric attributes. Subsequently, the best obtained similarity scores are analysed to infer the unknown soft-biometric attributes of the attacked privacy-enhanced face representation. That is, the attack only requires a relatively small database of arbitrary face images and the privacy-enhancing face recognition algorithm as a black-box. In the experiments, the attack is applied to two representative approaches which have previously been reported to reliably conceal the gender in privacy-enhanced face representations. It is shown that the presented attack is able to circumvent the privacy enhancement to a considerable degree and is able to correctly classify gender with an accuracy of up to approximately 90% for both of the analysed privacy-enhancing face recognition systems. Future works on privacy-enhancing face recognition are encouraged to include the proposed attack in evaluations on privacy protection.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{KrizajSensors2022,

title = {Making the most of single sensor information : a novel fusion approach for 3D face recognition using region covariance descriptors and Gaussian mixture models},

author = {Janez Križaj and Simon Dobrišek and Vitomir Štruc},

url = {https://www.mdpi.com/1424-8220/22/6/2388},

doi = {10.3390/s22062388},

year  = {2022},

date = {2022-03-01},

journal = {Sensors},

number = {2388},

issue = {6},

pages = {1-26},

abstract = {Most commercially successful face recognition systems combine information from multiple sensors (2D and 3D, visible light and infrared, etc.) to achieve reliable recognition in various environments. When only a single sensor is available, the robustness as well as efficacy of the recognition process suffer. In this paper, we focus on face recognition using images captured by a single 3D sensor and propose a method based on the use of region covariance matrixes and Gaussian mixture models (GMMs). All steps of the proposed framework are automated, and no metadata, such as pre-annotated eye, nose, or mouth positions is required, while only a very simple clustering-based face detection is performed. The framework computes a set of region covariance descriptors from local regions of different face image representations and then uses the unscented transform to derive low-dimensional feature vectors, which are finally modeled by GMMs. In the last step, a support vector machine classification scheme is used to make a decision about the identity of the input 3D facial image. The proposed framework has several desirable characteristics, such as an inherent mechanism for data fusion/integration (through the region covariance matrixes), the ability to explore facial images at different levels of locality, and the ability to integrate a domain-specific prior knowledge into the modeling procedure. Several normalization techniques are incorporated into the proposed framework to further improve performance. Extensive experiments are performed on three prominent databases (FRGC v2, CASIA, and UMB-DB) yielding competitive results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Stoimchev2022,

title = {Learning to Combine Local and Global Image Information for Contactless Palmprint Recognition},

author = {Marjan Stoimchev and Marija Ivanovska and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/03/sensors-22-00073_reduced.pdf},

doi = {https://doi.org/10.3390/s22010073},

year  = {2022},

date = {2022-01-01},

journal = {Sensors},

volume = {22},

number = {1},

pages = {1-26},

abstract = {In the past few years, there has been a leap from traditional palmprint recognition methodologies, which use handcrafted features, to deep-learning approaches that are able to automatically learn feature representations from the input data. However, the information that is extracted from such deep-learning models typically corresponds to the global image appearance, where only the most discriminative cues from the input image are considered. This characteristic is especially problematic when data is acquired in unconstrained settings, as in the case of contactless palmprint recognition systems, where visual artifacts caused by elastic deformations of the palmar surface are typically present in spatially local parts of the captured images. In this study we address the problem of elastic deformations by introducing a new approach to contactless palmprint recognition based on a novel CNN model, designed as a two-path architecture, where one path processes the input in a holistic manner, while the second path extracts local information from smaller image patches sampled from the input image. As elastic deformations can be assumed to most significantly affect the global appearance, while having a lesser impact on spatially local image areas, the local processing path addresses the issues related to elastic deformations thereby supplementing the information from the global processing path. The model is trained with a learning objective that combines the Additive Angular Margin (ArcFace) Loss and the well-known center loss. By using the proposed model design, the discriminative power of the learned image representation is significantly enhanced compared to standard holistic models, which, as we show in the experimental section, leads to state-of-the-art performance for contactless palmprint recognition. Our approach is tested on two publicly available contactless palmprint datasets—namely, IITD and CASIA—and is demonstrated to perform favorably against state-of-the-art methods from the literature. The source code for the proposed model is made publicly available.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ContexedNet_Emersic_2021,

title = {ContexedNet : Context-Aware Ear Detection in Unconstrained Settings},

author = {Žiga Emeršič and Diego Sušanj and Blaž Meden and Peter Peer and Vitomir Štruc},

editor = {ContexedNet : Context-Aware Ear Detection in Unconstrained Settings},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9583244},

issn = {2169-3536},

year  = {2021},

date = {2021-10-20},

urldate = {2021-10-20},

journal = {IEEE Access},

pages = {1--17},

abstract = {Ear detection represents one of the key components of contemporary ear recognition systems. While significant progress has been made in the area of ear detection over recent years, most of the improvements are direct results of advances in the field of visual object detection. Only a limited number of techniques presented in the literature are domain--specific and designed explicitly with ear detection in mind. In this paper, we aim to address this gap and present a novel detection approach that does not rely only on general ear (object) appearance, but also exploits contextual information, i.e., face--part locations, to ensure accurate and robust ear detection with images captured in a wide variety of imaging conditions. The proposed approach is based on a Context--aware Ear Detection Network (ContexedNet) and poses ear detection as a semantic image segmentation problem. ContexedNet consists of two processing paths: 1) a context--provider that extracts probability maps corresponding to the locations of facial parts from the input image, and 2) a dedicated ear segmentation model that integrates the computed probability maps into a context--aware segmentation-based ear detection procedure. ContexedNet is evaluated in rigorous experiments on the AWE and UBEAR datasets and shown to ensure competitive performance when evaluated against state--of--the--art ear detection models from the literature. Additionally, because the proposed contextualization is model agnostic, it can also be utilized with other ear detection techniques to improve performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{TIFS_PrivacySurveyb,

title = {Privacy-Enhancing Face Biometrics: A Comprehensive Survey},

author = {Blaz Meden, Peter Rot, Philipp Terhorst, Naser Damer, Arjan Kuijper, Walter J. Scheirer, Arun Ross, Peter Peer, Vitomir Struc},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9481149

https://lmi.fe.uni-lj.si/en/visual_privacy_of_faces__a_survey_preprint-compressed/},

doi = {10.1109/TIFS.2021.3096024},

year  = {2021},

date = {2021-07-12},

journal = {IEEE Transactions on Information Forensics and Security},

volume = {16},

pages = {4147-4183},

abstract = {Biometric recognition technology has made significant advances over the last decade and is now used across a number of services and applications. However, this widespread deployment has also resulted in privacy concerns and evolving societal expectations about the appropriate use of the technology. For example, the ability to automatically extract age, gender, race, and health cues from biometric data has heightened concerns about privacy leakage. Face recognition technology, in particular, has been in the spotlight, and is now seen by many as posing a considerable risk to personal privacy. In response to these and similar concerns, researchers have intensified efforts towards developing techniques and computational models capable of ensuring privacy to individuals, while still facilitating the utility of face recognition technology in several application scenarios.  These efforts have resulted in a multitude of privacy--enhancing techniques that aim at addressing privacy risks originating from biometric systems and providing technological solutions for legislative requirements set forth in privacy laws and regulations, such as GDPR. The goal of this overview paper is to provide a comprehensive introduction into privacy--related research in the area of biometrics and review existing work on textit{Biometric Privacy--Enhancing Techniques} (B--PETs) applied to face biometrics. To make this work useful for as wide of an audience as possible,  several key topics are covered as well, including evaluation strategies used with B--PETs, existing datasets, relevant standards, and regulations and critical open issues that will have to be addressed in the future. },

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{CrowdCountingPevec,

title = {Benchmarking Crowd-Counting Techniques across Image Characteristics},

author = {Klemen Pevec and Klemen Grm and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/10/Pevec.pdf

https://ev.fe.uni-lj.si/5-2021/Pevec.pdf},

year  = {2021},

date = {2021-05-01},

journal = {Elektorethniski Vestnik},

volume = {88},

issue = {5},

pages = {227-235},

abstract = {Crowd--counting is a longstanding computer vision used in estimating the crowd sizes for security purposes at public protests in streets, public gatherings, for collecting crowd statistics at airports, malls, concerts, conferences, and other similar venues, and for monitoring people and crowds during public health crises (such as the one caused by COVID-19). Recently, the performance of automated methods for crowd--counting from single images has improved particularly due to the introduction of deep learning techniques and large labelled training datasets. However, the robustness of these methods to varying imaging conditions, such as weather, image perspective, and large variations in the crowd size has not been studied in-depth in the open literature. To address this gap, a systematic study on the robustness of four recently developed crowd--counting methods is performed in this paper to evaluate their performance with respect to variable (real-life) imaging scenarios that include different event types, weather conditions, image sources and crowd sizes. It is shown that the performance of the tested techniques is degraded in unclear weather conditions (i.e., fog, rain, snow) and also on images taken from large distances by drones. On the opposite, clear weather conditions, crowd--counting methods can provide accurate and usable results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Batagelj2021,

title = {How to correctly detect face-masks for COVID-19 from visual information?},

author = {Borut Batagelj and Peter Peer and Vitomir Štruc and Simon Dobrišek},

url = {https://www.mdpi.com/2076-3417/11/5/2070/pdf},

doi = {10.3390/app11052070},

isbn = {2076-3417},

year  = {2021},

date = {2021-03-01},

urldate = {2021-03-01},

journal = {Applied sciences},

volume = {11},

number = {5},

pages = {1-24},

abstract = {The new Coronavirus disease (COVID-19) has seriously affected the world. By the end of November 2020, the global number of new coronavirus cases had already exceeded 60 million and the number of deaths 1,410,378 according to information from the World Health Organization (WHO). To limit the spread of the disease, mandatory face-mask rules are now becoming common in public settings around the world. Additionally, many public service providers require customers to wear face-masks in accordance with predefined rules (e.g., covering both mouth and nose) when using public services. These developments inspired research into automatic (computer-vision-based) techniques for face-mask detection that can help monitor public behavior and contribute towards constraining the COVID-19 pandemic. Although existing research in this area resulted in efficient techniques for face-mask detection, these usually operate under the assumption that modern face detectors provide perfect detection performance (even for masked faces) and that the main goal of the techniques is to detect the presence of face-masks only. In this study, we revisit these common assumptions and explore the following research questions: (i) How well do existing face detectors perform with masked-face images? (ii) Is it possible to detect a proper (regulation-compliant) placement of facial masks? and (iii) How useful are existing face-mask detection techniques for monitoring applications during the COVID-19 pandemic? To answer these and related questions we conduct a comprehensive experimental evaluation of several recent face detectors for their performance with masked-face images. Furthermore, we investigate the usefulness of multiple off-the-shelf deep-learning models for recognizing correct face-mask placement. Finally, we design a complete pipeline for recognizing whether face-masks are worn correctly or not and compare the performance of the pipeline with standard face-mask detection models from the literature. To facilitate the study, we compile a large dataset of facial images from the publicly available MAFA and Wider Face datasets and annotate it with compliant and non-compliant labels. The annotation dataset, called Face-Mask-Label Dataset (FMLD), is made publicly available to the research community.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Oblak2021,

title = {Learning to predict superquadric parameters from depth images with explicit and implicit supervision},

author = {Tim Oblak and Jaka Šircelj and Vitomir Struc and Peter Peer and Franc Solina and Aleš Jaklic

},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9274424},

doi = {10.1109/ACCESS.2020.3041584},

issn = {2169-3536},

year  = {2021},

date = {2021-01-01},

journal = {IEEE Access},

pages = {1-16},

abstract = {Reconstruction of 3D space from visual data has always been a significant challenge in

the field of computer vision. A popular approach to address this problem can be found in the form of

bottom-up reconstruction techniques which try to model complex 3D scenes through a constellation of

volumetric primitives. Such techniques are inspired by the current understanding of the human visual

system and are, therefore, strongly related to the way humans process visual information, as suggested

by recent visual neuroscience literature. While advances have been made in recent years in the area of

3D reconstruction, the problem remains challenging due to the many possible ways of representing 3D

data, the ambiguity of determining the shape and general position in 3D space and the difficulty to train

efficient models for the prediction of volumetric primitives. In this paper, we address these challenges and

present a novel solution for recovering volumetric primitives from depth images. Specifically, we focus on

the recovery of superquadrics, a special type of parametric models able to describe a wide array of 3D

shapes using only a few parameters. We present a new learning objective that relies on the superquadric

(inside-outside) function and develop two learning strategies for training convolutional neural networks

(CNN) capable of predicting superquadric parameters. The first uses explicit supervision and penalizes the

difference between the predicted and reference superquadric parameters. The second strategy uses implicit

supervision and penalizes differences between the input depth images and depth images rendered from

the predicted parameters. CNN predictors for superquadric parameters are trained with both strategies and

evaluated on a large dataset of synthetic and real-world depth images. Experimental results show that both

strategies compare favourably to the existing state-of-the-art and result in high quality 3D reconstructions

of the modelled scenes at a much shorter processing time.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/corr/abs-2103-11135,

title = {High Resolution Face Editing with Masked GAN Latent Code Optimization},

author = {Martin Pernus and Vitomir Struc and Simon Dobrisek},

url = {https://arxiv.org/abs/2103.11135},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {CoRR},

volume = {abs/2103.11135},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PEMIU_Access2020,

title = {PE-MIU: a training-free privacy-enhancing face recognition approach based on minimum information units},

author = {Philipp Terhorst and Kevin Riehl and Naser Damer and Peter Rot and Blaz Bortolato and Florian Kirchbuchner and Vitomir Struc and Arjan Kuijper},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9094207},

year  = {2020},

date = {2020-06-02},

journal = {IEEE Access},

volume = {2020},

abstract = {Research on soft-biometrics showed that privacy-sensitive information can be deduced from

biometric data. Utilizing biometric templates only, information about a persons gender, age, ethnicity,

sexual orientation, and health state can be deduced. For many applications, these templates are expected

to be used for recognition purposes only. Thus, extracting this information raises major privacy issues.

Previous work proposed two kinds of learning-based solutions for this problem. The first ones provide

strong privacy-enhancements, but limited to pre-defined attributes. The second ones achieve more comprehensive but weaker privacy-improvements. In this work, we propose a Privacy-Enhancing face recognition

approach based on Minimum Information Units (PE-MIU). PE-MIU, as we demonstrate in this work, is a

privacy-enhancement approach for face recognition templates that achieves strong privacy-improvements

and is not limited to pre-defined attributes. We exploit the structural differences between face recognition

and facial attribute estimation by creating templates in a mixed representation of minimal information

units. These representations contain pattern of privacy-sensitive attributes in a highly randomized form.

Therefore, the estimation of these attributes becomes hard for function creep attacks. During verification,

these units of a probe template are assigned to the units of a reference template by solving an optimal

best-matching problem. This allows our approach to maintain a high recognition ability. The experiments

are conducted on three publicly available datasets and with five state-of-the-art approaches. Moreover,

we conduct the experiments simulating an attacker that knows and adapts to the systems privacy mechanism.

The experiments demonstrate that PE-MIU is able to suppress privacy-sensitive information to a significantly

higher degree than previous work in all investigated scenarios. At the same time, our solution is able to

achieve a verification performance close to that of the unmodified recognition system. Unlike previous

works, our approach offers a strong and comprehensive privacy-enhancement without the need of training},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{TIPKlemen_2020,

title = {Face hallucination using cascaded super-resolution and identity priors},

author = {Klemen Grm and Walter J. Scheirer and Vitomir Štruc},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8866753

https://lmi.fe.uni-lj.si/wp-content/uploads/2023/02/IEEET_face_hallucination_compressed.pdf},

doi = {10.1109/TIP.2019.2945835},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {IEEE Transactions on Image Processing},

abstract = {In this paper we address the problem of hallucinating high-resolution facial images from low-resolution inputs at high magnification factors. We approach this task with convolutional neural networks (CNNs) and propose a novel (deep) face hallucination model that incorporates identity priors into the learning procedure. The model consists of two main parts: i) a cascaded super-resolution network that upscales the lowresolution facial images, and ii) an ensemble of face recognition models that act as identity priors for the super-resolution network during training. Different from most competing super-resolution techniques that rely on a single model for upscaling (even with large magnification factors), our network uses a cascade of multiple SR models that progressively upscale the low-resolution images using steps of 2×. This characteristic allows us to apply supervision signals (target appearances) at different resolutions and incorporate identity constraints at multiple-scales. The proposed C-SRIP model (Cascaded Super Resolution with Identity Priors) is able to upscale (tiny) low-resolution images captured in unconstrained conditions and produce visually convincing results for diverse low-resolution inputs. We rigorously evaluate the proposed model on the Labeled Faces in the Wild (LFW), Helen and CelebA datasets and report superior performance compared to the existing state-of-the-art.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{vitek2020comprehensive,

title = {A comprehensive investigation into sclera biometrics: a novel dataset and performance study},

author = {Matej Vitek and Peter Rot and Vitomir Struc and Peter Peer},

url = {https://link.springer.com/epdf/10.1007/s00521-020-04782-1},

doi = {https://doi.org/10.1007/s00521-020-04782-1},

year  = {2020},

date = {2020-01-01},

journal = {Neural Computing and Applications},

pages = {1-15},

abstract = {The area of ocular biometrics is among the most popular branches of biometric recognition technology. This area has long been dominated by iris recognition research, while other ocular modalities such as the periocular region or the vasculature of the sclera have received significantly less attention in the literature. Consequently, ocular modalities beyond the iris are not well studied and their characteristics are today still not as well understood. While recent needs for more secure authentication schemes have considerably increased the interest in competing ocular modalities, progress in these areas is still held back by the lack of publicly available datasets that would allow for more targeted research into specific ocular characteristics next to the iris. In this paper, we aim to bridge this gap for the case of sclera biometrics and introduce a novel dataset designed for research into ocular biometrics and most importantly for research into the vasculature of the sclera. Our dataset, called Sclera Blood Vessels, Periocular and Iris (SBVPI), is, to the best of our knowledge, the first publicly available dataset designed specifically with research in sclera biometrics in mind. The dataset contains high-quality RGB ocular images, captured in the visible spectrum, belonging to 55 subjects. Unlike competing datasets, it comes with manual markups of various eye regions, such as the iris, pupil, canthus or eyelashes and a detailed pixel-wise annotation of the complete sclera vasculature for a subset of the images. Additionally, the datasets ship with gender and age labels. The unique characteristics of the dataset allow us to study aspects of sclera biometrics technology that have not been studied before in the literature (e.g. vasculature segmentation techniques) as well as issues that are of key importance for practical recognition systems. Thus, next to the SBVPI dataset we also present in this paper a comprehensive investigation into sclera biometrics and the main covariates that affect the performance of sclera segmentation and recognition techniques, such as gender, age, gaze direction or image resolution. Our experiments not only demonstrate the usefulness of the newly introduced dataset, but also contribute to a better understanding of sclera biometrics in general.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Krizaj3Docalization,

title = {Simultaneous multi-decent regression and feature learning for landmarking in depth image},

author = {Janez Krizaj and Peter Peer and Vitomir Struc and Simon Dobrisek},

url = {https://link.springer.com/content/pdf/10.1007%2Fs00521-019-04529-7.pdf},

doi = {https://doi.org/10.1007/s00521-019-04529-7},

isbn = {0941-0643},

year  = {2019},

date = {2019-10-01},

journal = {Neural Computing and Applications},

abstract = {Face alignment (or facial landmarking) is an important task in many face-related applications, ranging from registration, tracking, and animation to higher-level classification problems such as face, expression, or attribute recognition. While several solutions have been presented in the literature for this task so far, reliably locating salient facial features across a wide range of posses still remains challenging. To address this issue, we propose in this paper a novel method for automatic facial landmark localization in 3D face data designed specifically to address appearance variability caused by significant pose variations. Our method builds on recent cascaded regression-based methods to facial landmarking and uses a gating mechanism to incorporate multiple linear cascaded regression models each trained for a limited range of poses into a single powerful landmarking model capable of processing arbitrary-posed input data. We develop two distinct approaches around the proposed gating mechanism: (1) the first uses a gated multiple ridge descent mechanism in conjunction with established (hand-crafted) histogram of gradients features for face alignment and achieves state-of-the-art landmarking performance across a wide range of facial poses and (2) the second simultaneously learns multiple-descent directions as well as binary features that are optimal for the alignment tasks and in addition to competitive landmarking results also ensures extremely rapid processing. We evaluate both approaches in rigorous experiments on several popular datasets of 3D face images, i.e., the FRGCv2 and Bosphorus 3D face datasets and image collections F and G from the University of Notre Dame. The results of our evaluation show that both approaches compare favorably to the state-of-the-art, while exhibiting considerable robustness to pose variations.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kovavc2019frame,

title = {Frame-based classification for cross-speed gait recognition},

author = {Jure Kovač and Vitomir Štruc and Peter Peer},

url = {http://rdcu.be/BfJP},

doi = {https://doi.org/10.1007/s11042-017-5469-0},

issn = {1573-7721},

year  = {2019},

date = {2019-03-01},

journal = {Multimedia Tools and Applications},

volume = {78},

number = {5},

pages = {5621--5643},

publisher = {Springer},

abstract = {The use of human gait as the means of biometric identification has gained a lot of attention in the past few years, mostly due to its enormous potential. Such biometrics can be captured at public places from a distance without subjects collaboration, awareness and even consent. However, there are still numerous challenges caused by influence of covariate factors like changes of walking speed, view, clothing, footwear etc., that have negative impact on recognition performance. In this paper we tackle walking speed changes with a skeleton model-based gait recognition system focusing on improving algorithm robustness and improving the performance at higher walking speed changes. We achieve these by proposing frame based classification method, which overcomes the main shortcoming of distance based classification methods, which are very sensitive to gait cycle starting point detection. The proposed technique is starting point invariant with respect to gait cycle starts and as such ensures independence of classification from gait cycle start positions. Additionally, we propose wavelet transform based signal approximation, which enables the analysis of feature signals on different frequency space resolutions and diminishes the need for using feature transformation that require training. With the evaluation on OU-ISIR gait dataset we demonstrate state of the art performance of proposed methods.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{krivzaj2019sistem,

title = {Sistem nadgrajene resničnosti za verifikacijo predmetov v skladiščnih okoljih},

author = {Janez Križaj and Janez Perš and Simon Dobrišek and Vitomir Štruc},

url = {https://ev.fe.uni-lj.si/1-2-2019/Krizaj.pdf},

year  = {2019},

date = {2019-01-01},

journal = {Elektrotehniski Vestnik},

volume = {86},

number = {1/2},

pages = {1--6},

publisher = {Elektrotehniski Vestnik},

abstract = {The paper proposes an augmented reality system for visual object verification that helps warehouse workers perform their work. The system sequentially captures images of objects that the warehouse workers encounter during their work and verifies whether the objects are the ones that the workers are supposed to fetch from storage. The system uses Android-powered smart glasses to capture image data and display results to the user, whereas the computationally-intensive verification task is carried out in the cloud and is implemented using recent deep-learning techniques. By doing so, the system is able to process images in near real-time and achieves a high verification accuracy as shown by the experimental results},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{GrmIEEE2018,

title = {Deep face recognition for surveillance applications},

author = {Klemen Grm and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2019/08/UniversityOfLjubljana_IEEE_IS_Submission.pdf},

year  = {2018},

date = {2018-05-01},

journal = {IEEE Intelligent Systems},

volume = {33},

number = {3},

pages = {46--50},

abstract = {Automated person recognition from surveillance quality footage is an open research problem with many potential application areas. In this paper, we aim at addressing this problem by presenting a face recognition approach tailored towards surveillance applications. The presented approach is based on domain-adapted convolutional neural networks and ranked second in the International Challenge on Biometric Recognition in the Wild (ICB-RW) 2016. We evaluate the performance of the presented approach on part of the Quis-Campi dataset and compare it against several existing face recognition techniques and one (state-of-the-art) commercial system. We find that the domain-adapted convolutional network outperforms all other assessed techniques, but is still inferior to human performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{emervsivc2018evaluation,

title = {Evaluation and analysis of ear recognition models: performance, complexity and resource requirements},

author = {Žiga Emeršič and Blaž Meden and Peter Peer and Vitomir Štruc},

url = {https://rdcu.be/Os7a},

doi = {https://doi.org/10.1007/s00521-018-3530-1},

isbn = {0941-0643},

year  = {2018},

date = {2018-05-01},

journal = {Neural Computing and Applications},

pages = {1--16},

publisher = {Springer},

abstract = {Ear recognition technology has long been dominated by (local) descriptor-based techniques due to their formidable recognition performance and robustness to various sources of image variability. While deep-learning-based techniques have started to appear in this field only recently, they have already shown potential for further boosting the performance of ear recognition technology and dethroning descriptor-based methods as the current state of the art. However, while recognition performance is often the key factor when selecting recognition models for biometric technology, it is equally important that the behavior of the models is understood and their sensitivity to different covariates is known and well explored. Other factors, such as the train- and test-time complexity or resource requirements, are also paramount and need to be consider when designing recognition systems. To explore these issues, we present in this paper a comprehensive analysis of several descriptor- and deep-learning-based techniques for ear recognition. Our goal is to discover weak points of contemporary techniques, study the characteristics of the existing technology and identify open problems worth exploring in the future. We conduct our analysis through identification experiments on the challenging Annotated Web Ears (AWE) dataset and report our findings. The results of our analysis show that the presence of accessories and high degrees of head movement significantly impacts the identification performance of all types of recognition models, whereas mild degrees of the listed factors and other covariates such as gender and ethnicity impact the identification performance only to a limited extent. From a test-time-complexity point of view, the results suggest that lightweight deep models can be equally fast as descriptor-based methods given appropriate computing hardware, but require significantly more resources during training, where descriptor-based methods have a clear advantage. As an additional contribution, we also introduce a novel dataset of ear images, called AWE Extended (AWEx), which we collected from the web for the training of the deep models used in our experiments. AWEx contains 4104 images of 346 subjects and represents one of the largest and most challenging (publicly available) datasets of unconstrained ear images at the disposal of the research community.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{emervsivc2018convolutional,

title = {Convolutional encoder--decoder networks for pixel-wise ear detection and segmentation},

author = {Žiga Emeršič and Luka Gabriel and Vitomir Štruc and Peter Peer},

url = {https://arxiv.org/pdf/1702.00307.pdf},

year  = {2018},

date = {2018-03-01},

journal = {IET Biometrics},

volume = {7},

number = {3},

pages = {175--184},

publisher = {IET},

abstract = {Object detection and segmentation represents the basis for many tasks in computer and machine vision. In biometric recognition systems the detection of the region-of-interest (ROI) is one of the most crucial steps in the processing pipeline, significantly impacting the performance of the entire recognition system. Existing approaches to ear detection, are commonly susceptible to the presence of severe occlusions, ear accessories or variable illumination conditions and often deteriorate in their performance if applied on ear images captured in unconstrained settings. To address these shortcomings, we present a novel ear detection technique based on convolutional encoder-decoder networks (CEDs). We formulate the problem of ear detection as a two-class segmentation problem and design and train a CED-network architecture to distinguish between image-pixels belonging to the ear and the non-ear class. Unlike competing techniques, our approach does not simply return a bounding box around the detected ear, but provides detailed, pixel-wise information about the location of the ears in the image. Experiments on a dataset gathered from the web (a.k.a. in the wild) show that the proposed technique ensures good detection results in the presence of various covariate factors and significantly outperforms competing methods from the literature.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{meden2018k,

title = {k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification},

author = {Blaž Meden and Žiga Emeršič and Vitomir Štruc and Peter Peer},

url = {https://www.mdpi.com/1099-4300/20/1/60/pdf},

year  = {2018},

date = {2018-01-01},

journal = {Entropy},

volume = {20},

number = {1},

pages = {60},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {Image and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data after deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent Generative Neural Networks (GNNs) with the well-known k-Anonymitymechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for deidentification by seamlessly combining features of identities used to train the GNN model. Furthermore, it allows us to control the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comprehensive experiments on the XM2VTS and CK+ datasets. We evaluate the efficacy of the proposed approach through reidentification experiments with recent recognition models and compare our results with competing deidentification techniques from the literature. We also present facial expression recognition experiments to demonstrate the utility-preservation capabilities of k-Same-Net. Our experimental results suggest that k-Same-Net is a viable option for facial deidentification that exhibits several desirable characteristics when compared to existing solutions in this area.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.3389/fphys.2018.00198,

title = {Intestinal Metagenomes and Metabolomes in Healthy Young Males: Inactivity and Hypoxia Generated Negative Physiological Symptoms Precede Microbial Dysbiosis},

author = {Robert Šket and Tadej Debevec and Susanne Kublik and Michael Schloter and Anne Schoeller and Boštjan Murovec and Katarina Vogel Mikuš and Damjan Makuc and Klemen Pečnik and Janez Plavec and Igor B Mekjavić and Ola Eiken and Zala Prevoršek and Blaž Stres},

url = {https://www.frontiersin.org/article/10.3389/fphys.2018.00198},

doi = {10.3389/fphys.2018.00198},

issn = {1664-042X},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

journal = {Frontiers in Physiology},

volume = {9},

pages = {198},

abstract = {We explored the metagenomic, metabolomic and trace metal makeup of intestinal microbiota and environment in healthy male participants during the run-in (5 day) and the following three 21-day interventions: normoxic bedrest (NBR), hypoxic bedrest (HBR) and hypoxic ambulation (HAmb) which were carried out within a controlled laboratory environment (circadian rhythm, fluid and dietary intakes, microbial bioburden, oxygen level, exercise). The fraction of inspired O2 (FiO2) and partial pressure of inspired O2 (PiO2) were 0.209 and 133.1 ± 0.3 mmHg for the NBR and 0.141 ± 0.004 and 90.0 ± 0.4 mmHg (~4000 m simulated altitude) for HBR and HAmb interventions, respectively. Shotgun metagenomes were analyzed at various taxonomic and functional levels, 1H- and 13C -metabolomes were processed using standard quantitative and human expert approaches, whereas metals were assessed using X-ray fluorescence spectrometry. Inactivity and hypoxia resulted in a significant increase in the genus Bacteroides in HBR, in genes coding for proteins involved in iron acquisition and metabolism, cell wall, capsule, virulence, defense and mucin degradation, such as beta-galactosidase (EC3.2.1.23), α-L-fucosidase (EC3.2.1.51), Sialidase (EC3.2.1.18) and α-N-acetylglucosaminidase (EC3.2.1.50). In contrast, the microbial metabolomes, intestinal element and metal profiles, the diversity of bacterial, archaeal and fungal microbial communities were not significantly affected. The observed progressive decrease in defecation frequency and concomitant increase in the electrical conductivity (EC) preceded or took place in absence of significant changes at the taxonomic, functional gene, metabolome and intestinal metal profile levels. The fact that the genus Bacteroides and proteins involved in iron acquisition and metabolism, cell wall, capsule, virulence and mucin degradation were enriched at the end of HBR suggest that both constipation and EC decreased intestinal metal availability leading to modified expression of co-regulated genes in Bacteroides genomes. Bayesian network analysis was used to derive the first hierarchical model of initial inactivity mediated deconditioning steps over time. The PlanHab wash-out period corresponded to a profound life-style change (i.e. reintroduction of exercise) that resulted in stepwise amelioration of the negative physiological symptoms, indicating that exercise apparently prevented the crosstalk between the microbial physiology, mucin degradation and proinflammatory immune activities in the host.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{MUROVEC2018428,

title = {1H NMR metabolomics of microbial metabolites in the four MW agricultural biogas plant reactors: A case study of inhibition mirroring the acute rumen acidosis symptoms},

author = {Boštjan Murovec and Damjan Makuc and Sabina Kolbl Repinc and Zala Prevoršek and Domen Zavec and Robert Šket and Klemen Pečnik and Janez Plavec and Blaž Stres},

url = {http://www.sciencedirect.com/science/article/pii/S0301479718305991},

doi = {https://doi.org/10.1016/j.jenvman.2018.05.068},

issn = {0301-4797},

year  = {2018},

date = {2018-01-01},

journal = {Journal of Environmental Management},

volume = {222},

pages = {428 - 435},

abstract = {In this study, nuclear magnetic resonance (1H NMR) spectroscopic profiling was used to provide a more comprehensive view of microbial metabolites associated with poor reactor performance in a full-scale 4 MW mesophilic agricultural biogas plant under fully operational and also under inhibited conditions. Multivariate analyses were used to assess the significance of differences between reactors whereas artificial neural networks (ANN) were used to identify the key metabolites responsible for inhibition and their network of interaction. Based on the results of nm-MDS ordination the subsamples of each reactor were similar, but not identical, despite homogenization of the full-scale reactors before sampling. Hence, a certain extent of variability due to the size of the system under analysis was transferred into metabolome analysis. Multivariate analysis showed that fully active reactors were clustered separately from those containing inhibited reactor metabolites and were significantly different. Furthermore, the three distinct inhibited states were significantly different from each other. The inhibited metabolomes were enriched in acetate, caprylate, trimethylamine, thymine, pyruvate, alanine, xanthine and succinate. The differences in the metabolic fingerprint between inactive and fully active reactors observed in this study resembled closely the metabolites differentiating the (sub) acute rumen acidosis inflicted and healthy rumen metabolomes, creating thus favorable conditions for the growth and activity of pathogenic bacteria. The consistency of our data with those reported before for rumen ecosystems shows that 1H NMR based metabolomics is a reliable approach for the evaluation of metabolic events at full-scale biogas reactors.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}