Publications

@inproceedings{MarijaFG2025,

title = {SelfMAD: Enhancing Generalization and Robustness in Morphing Attack Detection via Self-Supervised Learning},

author = {Marija Ivanovska and Leon Todorov and Naser Damer and Deepak Kumar Jain and Peter Peer and

Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/04/FG2025__SelfMAD.pdf

http://arxiv.org/abs/2504.05504},

year  = {2025},

date = {2025-05-27},

booktitle = {IEEE International Conference on Automatic Face and Gesture Recognition 2025},

pages = {1-10},

abstract = {With the continuous advancement of generative models, face morphing attacks have become a significant challenge for existing face verification systems due to their potential use in identity fraud and other malicious activities. Contemporary Morphing Attack Detection (MAD) approaches frequently rely on supervised, discriminative models trained on examples of bona fide and morphed images. These models typically perform well with morphs generated with techniques seen during training, but often lead to suboptimal performance when subjected to novel unseen morphing techniques. While unsupervised models have been shown to perform better in terms of generalizability, they typically result in higher error rates, as they struggle to effectively capture features of subtle artifacts. To address these shortcomings, we present SelfMAD, a novel self-supervised approach that simulates general morphing attack artifacts, allowing classifiers to learn generic and robust decision boundaries without overfitting to the specific artifacts induced by particular face morphing methods. Through extensive experiments on widely used datasets, we demonstrate that SelfMAD significantly outperforms current state-of-the-art MADs, reducing the detection error by more than 64% in terms of EER when compared to the strongest unsupervised competitor, and by more than 66%, when compared to the best performing discriminative MAD model, tested in cross-morph settings. The source code for SelfMAD is available at https://github.com/LeonTodorov/SelfMAD.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{DarianFG2025,

title = {ID-Booth: Identity-consistent Face Generation with Diffusion Models},

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

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/04/ID_Booth__2025_.pdf},

year  = {2025},

date = {2025-05-27},

booktitle = {IEEE International Conference on Automatic Face and Gesture Recognition 2025},

pages = {1-10},

abstract = {Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition.  

Here, state-of-the-art generative models typically rely on conditioning and fine-tuning of powerful pretrained diffusion models to facilitate the synthesis of realistic images of a desired identity. Yet, these models often do not consider the identity of subjects during training, leading to poor consistency between generated and intended identities. In contrast, methods that employ identity-based training objectives tend to overfit on various aspects of the identity, and in turn, lower the diversity of images that can be generated. To address these issues, we present in this paper a novel generative diffusion-based framework, called ID-Booth. ID-Booth consists of a denoising network responsible for data generation, a variational auto-encoder for mapping images to and from a lower-dimensional latent space and a text encoder that allows for prompt-based control over the generation procedure. The framework utilizes a novel triplet identity training objective and enables identity-consistent image generation while retaining the synthesis capabilities of pretrained diffusion models. Experiments with a state-of-the-art latent diffusion model and diverse prompts reveal that our method facilitates better intra-identity consistency and inter-identity separability than competing methods, while achieving higher image diversity. In turn, the produced data allows for effective augmentation of small-scale datasets and training of better-performing recognition models in a privacy-preserving manner. The source code for the ID-Booth framework is publicly available at https://github.com/dariant/ID-Booth. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Anastasija_WACV25,

title = {Interpreting Face Recognition Templates using Natural Language Descriptions},

author = {Anastasija Manojlovska and Raghavendra Ramachandra and Georgios Spathoulas and Vitomir Struc and Klemen Grm},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/01/WACV_2025_RWS_workshop_clanek.pdf},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-01},

booktitle = {Proceedings of IEEE/CFV Winter Conference on Applications in Computer Vision - Workshops (WACV-W) 2025},

pages = {1-10},

address = {Tucson, USA},

abstract = {Explainable artificial intelligence (XAI) aims to ensure an AI system's decisions are transparent and understandable by humans, which is particularly important in potentially sensitive application scenarios in surveillance, security and law enforcement. In these and related areas, understanding  the internal mechanisms governing the decision-making process of AI-based systems can increase trust and consequently user acceptance. While various methods have been developed to provide insights into the behavior of AI-based models, solutions capable of explaining different aspects of the models using Natural Language are still limited in the literature. In this paper, we therefore propose a novel approach for interpreting the information content encoded in face templates, produced by state-of-the-art (SOTA) face recognition models. Specifically, we utilize the Text Encoder from the Contrastive Language-Image Pretraining (CLIP) model and generate natural language descriptions of various face attributes present in the face templates. We implement two versions of our approach, with the off-the-shelf CLIP text-encoder and a fine-tuned version using the VGGFace2 and MAADFace datasets.~Our experimental results indicate that the fine-tuned text encoder under the contrastive training paradigm increases the attribute-based explainability of face recognition templates, while both models provide valuable human-understandable insights into modern face recognition models.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Elahe_WACV2025,

title = {Extracting Local Information from Global Representations for Interpretable Deepfake Detection},

author = {Elahe Soltandoost and Richard Plesh and Stephanie Schuckers and Peter Peer and Vitomir Struc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/01/ElahePaperF.pdf},

year  = {2025},

date = {2025-03-01},

booktitle = {Proceedings of IEEE/CFV Winter Conference on Applications in Computer Vision - Workshops (WACV-W) 2025},

pages = {1-11},

address = {Tucson, USA},

abstract = {The detection of deepfakes has become increasingly challenging due to the sophistication of manipulation techniques that produce highly convincing fake videos. Traditional detection methods often lack transparency and provide limited insight into their decision-making processes. To address these challenges, we propose in this paper a Locally-Explainable Self-Blended (LESB) DeepFake detector that in addition to the final fake-vs-real classification decision also provides information, on which local facial region (i.e., eyes, mouth or nose) contributed the most to the decision process.~At the heart of the detector is a novel Local Feature Discovery (LFD) technique that can be applied to the embedding space of pretrained DeepFake detectors and allows identifying embedding space directions that encode variations in the appearance of local facial features. We demonstrate the merits of the proposed LFD technique and LESB detector in comprehensive experiments on four popular datasets, i.e.,  Celeb-DF, DeepFake Detection Challenge, Face Forensics in the Wild and FaceForensics++, and show that the proposed detector is not only competitive in comparison to strong baselines, but also exhibits enhanced transparency in the decision-making process by providing insights on the contribution of local face parts in the final detection decision. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{FadiWACV2025_Foundation,

title = {MADation: Face Morphing Attack Detection with Foundation Models},

author = {Eduarda Caldeira and Guray Ozgur and Tahar Chettaoui and Marija Ivanovska and Peter Peer and Fadi Boutros and Vitomir Struc and Naser Damer},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2025/01/MADation__Face_Morphing_Attack_Detection_with_Foundation_Models.pdf},

year  = {2025},

date = {2025-03-01},

booktitle = {Proceedings of IEEE/CFV Winter Conference on Applications in Computer Vision - Workshops (WACV-W) 2025},

pages = {1-11},

address = {Tucson, USA},

abstract = {Despite the considerable performance improvements of face recognition algorithms in recent years, the same scientific advances responsible for this progress can also be used to create efficient ways to attack them, posing a threat to their secure deployment. Morphing attack detection (MAD) systems aim to detect a specific type of threat, morphing attacks, at an early stage, preventing them from being considered for verification in critical processes. Foundation models (FM) learn from extensive amounts of unlabelled data, achieving remarkable zero-shot generalization to unseen domains. Although this generalization capacity might be weak when dealing with domain-specific downstream tasks such as MAD, FMs can easily adapt to these settings while retaining the built-in knowledge acquired during pre-training. In this work, we recognize the potential of FMs to perform well in the MAD task when properly adapted to its specificities. To this end, we adapt FM CLIP architectures with LoRA weights while simultaneously training a classification header. The proposed framework, MADation surpasses our alternative FM and transformer-based frameworks and constitutes the first adaption of FMs to the MAD task. MADation presents competitive results with current MAD solutions in the literature and even surpasses them in several evaluation scenarios. To encourage reproducibility and facilitate further research in MAD, we publicly release the implementation of MADation at https://github.com/gurayozgur/MADation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MRAC2024,

title = {W-TDL: Window-Based Temporal Deepfake Localization},

author = {Luka Dragar and Peter Rot and Peter Peer and Vitomir Štruc and Borut Batagelj},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/09/ACM_1M_DeepFakes.pdf},

year  = {2024},

date = {2024-11-01},

booktitle = {Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing (MRAC ’24), Proceedings of the 32nd ACM International Conference on Multimedia (MM’24)},

publisher = {ACM},

abstract = {The quality of synthetic data has advanced to such a degree of realism that distinguishing it from genuine data samples is increasingly challenging. Deepfake content, including images, videos, and audio, is often used maliciously, necessitating effective detection methods. While numerous competitions have propelled the development of deepfake detectors, a significant gap remains in accurately pinpointing the temporal boundaries of manipulations. Addressing this, we propose an approach for temporal deepfake localization (TDL) utilizing a window-based method for audio (W-TDL) and a complementary visual frame-based model. Our contributions include an effective method for detecting and localizing fake video and audio segments and addressing unbalanced training labels in spoofed audio datasets. Our approach leverages the EVA visual transformer for frame-level analysis and a modified TDL method for audio, achieving competitive results in the 1M-DeepFakes Detection Challenge. Comprehensive experiments on the AV-Deepfake1M dataset demonstrate the effectiveness of our method, providing an effective solution to detect and localize deepfake manipulations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{FadiECCV2024,

title = {AdaDistill: Adaptive Knowledge Distillation for Deep Face Recognition},

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

url = {https://arxiv.org/pdf/2407.01332},

year  = {2024},

date = {2024-09-30},

booktitle = {Proceedings of the European Conference on Computer Vision (ECCV 2024)},

pages = {1-20},

abstract = {Knowledge distillation (KD) aims at improving the performance of a compact student model by distilling the knowledge from a high-performing teacher model. In this paper, we present an adaptive KD approach, namely AdaDistill, for deep face recognition. The proposed AdaDistill embeds the KD concept into the softmax loss by training the student using a margin penalty softmax loss with distilled class centers from the teacher. Being aware of the relatively low capacity of the compact student model, we propose to distill less complex knowledge at an early stage of training and more complex one at a later stage of training. This relative adjustment of the distilled knowledge is controlled by the progression of the learning capability of the student over the training iterations without the need to tune any hyper-parameters. Extensive experiments and ablation studies show that AdaDistill can enhance the discriminative learning capability of the student and demonstrate superiority over various state-of-the-art competitors on several challenging benchmarks, such as IJB-B, IJB-C, and ICCV2021-MFR},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{EK_Ocvirk2024,

title = {Primerjava metod za zaznavanje napadov ponovnega zajema},

author = {Krištof Ocvirk and Marko Brodarič and Peter Peer and Vitomir Struc and Borut Batagelj},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/10/ocvirkprimerjava_metod.pdf},

year  = {2024},

date = {2024-09-26},

urldate = {2024-09-26},

booktitle = {Proceedings of ERK},

pages = {1-4},

address = {Portorož, Slovenia},

abstract = {The increasing prevalence of digital identity verification has amplified the demand for robust personal document authentication systems. To obscure traces of forgery, forgers often photograph the documents after reprinting or directly capture them from a screen display. This paper is a work report for the First Competition on Presentation Attack Detection on ID Cards, held at the International Joint Conference on Biometrics 2024 (IJCB PAD-ID Card 2024). The competition aims to explore the efficacy of deep neural networks in detecting recapture attacks. The Document Liveness Challenge Dataset (DLC-2021) was utilized to train models. Several models were adapted for this task, including ViT, Xception, TRes-Net, and EVA. Among these, the Xception model achieved the best performance, showing a significantly low error rate in both attack presentation classification error and bona fide presentation classification error.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Anastasija_ERK24,

title = {Interpretacija mehanizmov obraznih biometričnih modelov s kontrastnim multimodalnim učenjem},

author = {Anastasija Manojlovska and Vitomir Štruc and Klemen Grm},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/10/ERK2024_Copy.pdf},

year  = {2024},

date = {2024-09-26},

booktitle = {Proceedings of ERK 2024},

pages = {1-4},

address = {Portorož, Slovenia},

abstract = {Razložljiva umetna inteligenca (XAI) povečuje transparentnost sistemov umetne inteligence. Ta študija uporablja model CLIP (Contrastive Language-Image Pretraining) podjetja OpenAI za prepoznavanje obraznih atributov v podatkovni zbirki VGGFace2 z uporabo anotacij atributov iz podatkovne zbirke MAADFace. Z poravnavo slik in opisov v naravnem jeziku prepoznamo atribute, kot so starost, spol in pričeska, ter ustvarimo razlage v naravnem jeziku. Raziskujemo tudi integracijo predhodno naučenih modelov za prepoznavanje obrazov in dodajanje razvrščevalnih plasti za izboljšanje razvrščanja atributov. Prednaučeni model CLIP, se je izkazal najboljši pri prepoznavanju atributov Moški in Črn, saj je dosegel vrednosti AUC 0,9891 oz. 0,9829.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ERK_2024_Deepfakes,

title = {Towards Improving Backbones for Deepfake Detection},

author = {Marko Brodarič and Peter Peer and Vitomir Struc},

year  = {2024},

date = {2024-09-25},

booktitle = {Proceedings of ERK 2024},

pages = {1-4},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ERK_PAD24,

title = {Detection of Presentation Attacks with 3D Masks Using Deep Learning},

author = {Lovro Sikošek and Marko Brodarič and Peter Peer and Vitomir Struc and Borut Batagelj},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/10/sikosekdetekcija_prezentacijskih.pdf},

year  = {2024},

date = {2024-09-25},

booktitle = {Proceedings of ERK 2024},

pages = {1-4},

address = {Portorož, Slovenia},

abstract = {This paper describes a cutting edge approach to Presentation Attack Detection (PAD) of 3D mask attacks using deep learning. We utilize a ResNeXt convolutional neural network, pre-trained on the ImageNet dataset and fine-tuned on the 3D Mask Attack Database (3DMAD). We also evaluate the model on a smaller, more general validation set containing different types of presentation attacks captured with various types of sensors. Experimental data shows that our model achieves high accuracy in distinguishing between genuine faces and mask attacks within the 3DMAD database. However, evaluation on a more general testing set reveals challenges in generalizing to new types of attacks and datasets, suggesting the need for further research to enhance model robustness.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SWAP_ERK_24,

title = {Prepoznava zamenjave obraza na slikah osebnih dokumentov},

author = {Leon Alessio and Marko Brodarič and Peter Peer and Vitomir Struc and Borut Batagelj},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/10/alessioprepoznava_zamenjave.pdf},

year  = {2024},

date = {2024-09-25},

booktitle = {Proceedings of ERK 2024},

pages = {1-4},

address = {Portorož, Slovenia},

abstract = {In recent years, a need for remote user authentication has emerged. Many authentication techniques are based on verifying an image of identity documents (ID). This approach mitigates the need for physical presence from both parties, making the authentication process quicker and more effective. However, it also presents challenges, such as data security and the risk of identity fraud. Attackers use many techniques to fool authentication algorithms. This paper focuses on detecting face substitution, a common and straightforward fraud technique where the perpetrator replaces the face image on the ID. Due to its simplicity, almost anyone can utilize this technique extensively. Unlike digitally altered images, these modifications are manually detectable but pose challenges for computer algorithms. To face the challenge of detecting such an attack, we extended a dataset containing original images of identity cards of 9 countries with altered images, where the original face was substituted with another face from the dataset. We developed a method to detect such tampering by identifying unusual straight lines that indicate an overlay on the ID. We then evaluated the method on our dataset. While the method showed limited success, it underscores the complexity of this problem and provides a benchmark for future research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Krizaj,

title = {Discovering Interpretable Feature Directions in the Embedding Space of Face Recognition Models},

author = {Richard Plesh and Janez Križaj and Keivan Bahmani and Mahesh Banavar and Vitomir Struc and Stephanie Schuckers},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/08/107.pdf

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/08/107-supp.pdf},

year  = {2024},

date = {2024-09-15},

booktitle = {International Joint Conference on Biometrics (IJCB 2024)},

pages = {1-10},

abstract = {Modern face recognition (FR) models, particularly their convolutional neural network based implementations, often raise concerns regarding privacy and ethics due to their “black-box” nature. To enhance the explainability of FR models and the interpretability of their embedding space, we introduce in this paper three novel techniques for discovering semantically meaningful feature directions (or axes). The first technique uses a dedicated facial-region blending procedure together with principal component analysis to discover embedding space direction that correspond to spatially isolated semantic face areas, providing a new perspective on facial feature interpretation. The other two proposed techniques exploit attribute labels to discern feature directions that correspond to intra-identity variations, such as pose, illumination angle, and expression, but do so either through a cluster analysis or a dedicated regression procedure. To validate the capabilities of the developed techniques, we utilize a powerful template decoder that inverts the image embedding back into the pixel space. Using the decoder, we visualize linear movements along the discovered directions, enabling a clearer understanding of the internal representations within face recognition models. The source code will be made publicly available.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{CVPR_synth2024,

title = {Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data},

author = {Ivan DeAndres-Tame and Ruben Tolosana and Pietro Melzi and Ruben Vera-Rodriguez and Minchul Kim and Christian Rathgeb and Xiaoming Liu and Aythami Morales and Julian Fierrez and Javier Ortega-Garcia and Zhizhou Zhong and Yuge Huang and Yuxi Mi and Shouhong Ding and Shuigeng Zhou and Shuai He and Lingzhi Fu and Heng Cong and Rongyu Zhang and Zhihong Xiao and Evgeny Smirnov and Anton Pimenov and Aleksei Grigorev and Denis Timoshenko and Kaleb Mesfin Asfaw and Cheng Yaw Low and Hao Liu and Chuyi Wang and Qing Zuo and Zhixiang He and Hatef Otroshi Shahreza and Anjith George and Alexander Unnervik and Parsa Rahimi and Sébastien Marcel and Pedro C Neto and Marco Huber and Jan Niklas Kolf and Naser Damer and Fadi Boutros and Jaime S Cardoso and Ana F Sequeira and Andrea Atzori and Gianni Fenu and Mirko Marras and Vitomir Štruc and Jiang Yu and Zhangjie Li and Jichun Li and Weisong Zhao and Zhen Lei and Xiangyu Zhu and Xiao-Yu Zhang and Bernardo Biesseck and Pedro Vidal and Luiz Coelho and Roger Granada and David Menotti},

url = {https://openaccess.thecvf.com/content/CVPR2024W/FRCSyn/papers/Deandres-Tame_Second_Edition_FRCSyn_Challenge_at_CVPR_2024_Face_Recognition_Challenge_CVPRW_2024_paper.pdf},

year  = {2024},

date = {2024-06-17},

urldate = {2024-06-17},

booktitle = {Proceedings of CVPR Workshops (CVPRW 2024)},

pages = {1-11},

abstract = {Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intraclass variability, time and errors produced in manual labeling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations, including data privacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging situations such as aging, pose variations, and occlusions. Unlike the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new subtasks that allow participants to explore novel face generative methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Rot_FG2024,

title = {ASPECD: Adaptable Soft-Biometric Privacy-Enhancement Using Centroid Decoding for Face Verification},

author = {Peter Rot and Philipp Terhorst and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/03/PeterRot_FG2024.pdf},

year  = {2024},

date = {2024-05-28},

booktitle = {Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition (FG)},

pages = {1-9},

abstract = {State-of-the-art face recognition models commonly extract information-rich biometric templates from the input images that are then used for comparison purposes and identity inference. While these templates encode identity information in a highly discriminative manner, they typically also capture other potentially sensitive facial attributes, such as age, gender or ethnicity. To address this issue, Soft-Biometric Privacy-Enhancing Techniques (SB-PETs) were proposed in the literature that aim to suppress such attribute information, and, in turn, alleviate the privacy risks associated with the extracted biometric templates. While various SB-PETs were presented so far, existing   approaches do not provide dedicated mechanisms to determine which soft-biometrics to exclude and which to retain. In this paper, we address this gap and introduce ASPECD, a modular framework designed to selectively suppress binary and categorical soft-biometrics based on users' privacy preferences. ASPECD consists of multiple sequentially connected components, each dedicated for privacy-enhancement of an individual soft-biometric attribute.  The proposed framework suppresses attribute information using a Moment-based Disentanglement process coupled with a centroid decoding procedure, ensuring that the privacy-enhanced templates are directly comparable to the templates in the original embedding space, regardless of the soft-biometric modality being suppressed. 

To validate the performance of ASPECD, we conduct experiments on a large-scale face dataset and with five state-of-the-art face recognition models, demonstrating the effectiveness of the proposed approach in suppressing single and multiple soft-biometric attributes. Our approach achieves a competitive privacy-utility trade-off compared to the state-of-the-art methods in scenarios that involve enhancing privacy w.r.t. gender and ethnicity attributes. Source code will be made publicly available.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Ajda_Dicti,

title = {DiCTI: Diffusion-based Clothing Designer via Text-guided Input},

author = {Ajda Lampe and Julija Stopar and Deepak Kumar Jain and Shinichiro Omachi and Peter Peer and Vitomir Struc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/06/Dicti_FG2024_compressed.pdf},

year  = {2024},

date = {2024-05-27},

booktitle = {Proceedings of the18th International Conference on Automatic Face and Gesture Recognition (FG 2024)},

pages = {1-9},

abstract = {Recent developments in deep generative models have opened up a wide range of opportunities for image synthesis, leading to significant changes in various creative fields, including the fashion industry. While numerous methods have been proposed to benefit buyers, particularly in virtual try-on applications, there has been relatively less focus on facilitating fast prototyping for designers and customers seeking to order new designs. To address this gap, we introduce DiCTI (Diffusion-based Clothing Designer via Text-guided Input), a straightforward yet highly effective approach that allows designers to quickly visualize fashion-related ideas using text inputs only. 

Given an image of a person and a description of the desired garments as input, DiCTI automatically generates multiple high-resolution, photorealistic images that capture the expressed semantics.  

By leveraging a powerful diffusion-based inpainting model conditioned on text inputs, DiCTI is able to synthesize convincing, high-quality images with varied clothing designs that viably follow the provided text descriptions, while being able to process very diverse and challenging inputs, captured in completely unconstrained settings. We evaluate DiCTI in comprehensive experiments on two different datasets (VITON-HD and Fashionpedia) and in comparison to the state-of-the-art (SoTa). The results of our experiments show that DiCTI convincingly outperforms the SoTA competitor in generating higher quality images with more elaborate garments and superior text prompt adherence, both according to standard quantitative evaluation measures and human ratings, generated as part of a user study. The source code of DiCTI will be made publicly available.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Babnik_IWBF2024,

title = {AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation},

author = {Žiga Babnik and Fadi Boutros and Naser Damer and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/03/iwbf2024_fiq.pdf},

year  = {2024},

date = {2024-04-10},

urldate = {2024-04-10},

booktitle = {Proceedings of the International Workshop on Biometrics and Forensics (IWBF)},

pages = {1-6},

abstract = {Face Image Quality Assessment (FIQA) techniques have seen steady improvements over recent years, but their performance still deteriorates if the input face samples are not properly aligned. This alignment sensitivity comes from the fact that most FIQA techniques are trained or designed using a specific face alignment procedure. If the alignment technique changes, the performance of most existing FIQA techniques quickly becomes suboptimal. To address this problem, we present in this paper a novel knowledge distillation approach, termed AI-KD that can extend on any existing FIQA technique, improving its robustness to alignment variations and, in turn, performance with different alignment procedures. To validate the proposed distillation approach, we conduct comprehensive experiments on 6 face datasets with 4 recent face recognition models and in comparison to 7 state-of-the-art FIQA techniques. Our results show that AI-KD consistently improves performance of the initial FIQA techniques not only with misaligned samples, but also with properly aligned facial images. Furthermore, it leads to a new state-of-the-art, when used with a competitive initial FIQA approach. The code for AI-KD is made publicly available from: https://github.com/LSIbabnikz/AI-KD.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{RotICASSP24,

title = {Enhancing Gender Privacy with Photo-realistic Fusion of Disentangled Spatial Segments},

author = {Peter Rot and Janez Križaj and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/08/ICASSP_2024___Gender_privacy.pdf},

year  = {2024},

date = {2024-04-02},

urldate = {2024-04-02},

booktitle = {Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

pages = {1-5},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MarkoCVWW,

title = {Cross-Dataset Deepfake Detection: Evaluating the Generalization Capabilities of Modern DeepFake Detectors},

author = {Marko Brodarič and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2024/01/MarkoCVWW24_compressed.pdf},

year  = {2024},

date = {2024-01-31},

booktitle = {Proceedings of the 27th Computer Vision Winter Workshop (CVWW)},

pages = {1-10},

abstract = {Due to the recent advances in generative deep learning, numerous techniques have been proposed in the literature that allow for the creation of so-called deepfakes, i.e., forged facial images commonly used for malicious purposes. These developments have triggered a need for effective deepfake detectors, capable of identifying forged and manipulated imagery as robustly as possible. While a considerable number of detection techniques has been proposed over the years, generalization across a wide spectrum of deepfake-generation techniques still remains an open problem. In this paper, we study a representative set of deepfake generation methods and analyze their performance in a cross-dataset setting with the goal of better understanding the reasons behind the observed generalization performance. To this end, we conduct a comprehensive analysis on the FaceForensics++ dataset and adopt Gradient-weighted Class Activation Mappings (Grad-CAM) to provide insights into the behavior of the evaluated detectors. Since a new class of deepfake generation techniques based on diffusion models recently appeared in the literature, we introduce a new subset of the FaceForensics++ dataset with diffusion-based deepfake and include it in our analysis. The results of our experiments show that most detectors overfit to the specific image artifacts induced by a given deepfake-generation model and mostly focus on local image areas where such artifacts can be expected. Conversely, good generalization appears to be correlated with class activations that cover a broad spatial area and hence capture different image artifacts that appear in various part of the facial region.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MarijaWACV24,

title = {On the Vulnerability of Deepfake Detectors to Attacks Generated by Denoising Diffusion Models},

author = {Marija Ivanovska and Vitomir Štruc},

url = {https://openaccess.thecvf.com/content/WACV2024W/MAP-A/papers/Ivanovska_On_the_Vulnerability_of_Deepfake_Detectors_to_Attacks_Generated_by_WACVW_2024_paper.pdf},

year  = {2024},

date = {2024-01-08},

urldate = {2024-01-08},

booktitle = {Proceedings of WACV Workshops},

pages = {1051-1060},

abstract = {The detection of malicious deepfakes is a constantly evolving problem that requires continuous monitoring of detectors to ensure they can detect image manipulations generated by the latest emerging models. In this paper, we investigate the vulnerability of single–image deepfake detectors to black–box attacks created by the newest generation of generative methods, namely Denoising Diffusion Models (DDMs). Our experiments are run on FaceForensics++, a widely used deepfake benchmark consisting of manipulated images generated with various techniques for face identity swapping and face reenactment. Attacks are crafted through guided reconstruction of existing deepfakes with a proposed DDM approach for face restoration. Our findings indicate that employing just a single denoising diffusion step in the reconstruction process of a deepfake can significantly reduce the likelihood of detection, all without introducing any perceptible image modifications. While training detectors using attack examples demonstrated some effectiveness, it was observed that discriminators trained on fully diffusion–based deepfakes exhibited limited generalizability when presented with our attacks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{NicolasCCV,

title = {SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes},

author = {Nicolas Larue and Ngoc-Son Vu and Vitomir Štruc and Peter Peer and Vassilis Christophides},

url = {https://openaccess.thecvf.com/content/ICCV2023/papers/Larue_SeeABLE_Soft_Discrepancies_and_Bounded_Contrastive_Learning_for_Exposing_Deepfakes_ICCV_2023_paper.pdf

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/01/SeeABLE_compressed.pdf

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/01/SeeABLE_supplementary_compressed.pdf},

year  = {2023},

date = {2023-10-01},

urldate = {2023-10-01},

booktitle = {Proceedings of the International Conference on Computer Vision (ICCV)},

pages = {21011 - 21021},

organization = {IEEE},

abstract = {Modern deepfake detectors have achieved encouraging results, when training and test images are drawn from the same data collection. However, when these detectors are applied to images produced with unknown deepfake-generation techniques, considerable performance degradations are commonly observed. In this paper, we propose a novel deepfake detector, called SeeABLE, that formalizes the detection problem as a (one-class) out-of-distribution detection task and generalizes better to unseen deepfakes. Specifically, SeeABLE first generates local image perturbations (referred to as soft-discrepancies) and then pushes the perturbed faces towards predefined prototypes using a novel regression-based bounded contrastive loss. To strengthen the generalization performance of SeeABLE to unknown deepfake types, we generate a rich set of soft discrepancies and train the detector: (i) to localize, which part of the face was modified, and (ii) to identify the alteration type. To demonstrate the capabilities of SeeABLE, we perform rigorous experiments on several widely-used deepfake datasets and show that our model convincingly outperforms competing state-of-the-art detectors, while exhibiting highly encouraging generalization capabilities. The source code for SeeABLE is available from: https://github.com/anonymous-author-sub/seeable.

},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Diffiqa_2023,

title = {DifFIQA: Face Image Quality Assessment Using Denoising Diffusion Probabilistic Models},

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

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/121.pdf

https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/121-supp.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics },

pages = {1-10},

publisher = {IEEE},

address = {Ljubljana, Slovenia},

abstract = {Modern face recognition (FR) models excel in constrained

scenarios, but often suffer from decreased performance

when deployed in unconstrained (real-world) environments

due to uncertainties surrounding the quality

of the captured facial data. Face image quality assessment

(FIQA) techniques aim to mitigate these performance

degradations by providing FR models with sample-quality

predictions that can be used to reject low-quality samples

and reduce false match errors. However, despite steady improvements,

ensuring reliable quality estimates across facial

images with diverse characteristics remains challenging.

In this paper, we present a powerful new FIQA approach,

named DifFIQA, which relies on denoising diffusion

probabilistic models (DDPM) and ensures highly competitive

results. The main idea behind the 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 the diffusion-based perturbations are

computationally expensive, we also distill the knowledge

encoded in DifFIQA into a regression-based quality predictor,

called DifFIQA(R), that balances performance and

execution time. We evaluate both models in comprehensive

experiments on 7 diverse datasets, with 4 target FR models

and against 10 state-of-the-art FIQA techniques with

highly encouraging results. The source code is available

from: https://github.com/LSIbabnikz/DifFIQA.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Deepfake_comp2023,

title = {DFGC-VRA: DeepFake Game Competition on Visual Realism Assessment},

author = {Bo Peng and Xianyun Sun and Caiyong Wang and Wei Wang and Jing Dong and Zhenan Sun and Rongyu Zhang and Heng Cong and Lingzhi Fu and Hao Wang and Yusheng Zhang and HanYuan Zhang and Xin Zhang and Boyuan Liu and Hefei Ling and Luka Dragar and Borut Batagelj and Peter Peer and Vitomir Struc and Xinghui Zhou and Kunlin Liu and Weitao Feng and Weiming Zhang and Haitao Wang and Wenxiu Diao},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/CameraReady-225.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics (IJCB 2023)},

pages = {1-9},

address = {Ljubljana, Slovenia},

abstract = {This paper presents the summary report on the DeepFake

Game Competition on Visual Realism Assessment (DFGCVRA).

Deep-learning based face-swap videos, also known

as deepfakes, are becoming more and more realistic and

deceiving. The malicious usage of these face-swap videos

has caused wide concerns. There is a ongoing deepfake

game between its creators and detectors, with the human in

the loop. The research community has been focusing on

the automatic detection of these fake videos, but the assessment

of their visual realism, as perceived by human

eyes, is still an unexplored dimension. Visual realism assessment,

or VRA, is essential for assessing the potential

impact that may be brought by a specific face-swap video,

and it is also useful as a quality metric to compare different

face-swap methods. This is the third edition of DFGC

competitions, which focuses on the new visual realism assessment

topic, different from previous ones that compete

creators versus detectors. With this competition, we conduct

a comprehensive study of the SOTA performance on

the new task. We also release our MindSpore codes to fur-

*Jing Dong (jdong@nlpr.ia.ac.cn) is the corresponding author.

ther facilitate research in this field (https://github.

com/bomb2peng/DFGC-VRA-benckmark).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{EFAR2023_2023,

title = {EFaR 2023: Efficient Face Recognition Competition},

author = {Jan Niklas Kolf and Fadi Boutros and Jurek Elliesen and Markus Theuerkauf and Naser Damer and Mohamad Y Alansari and Oussama Abdul Hay and Sara Yousif Alansari and Sajid Javed and Naoufel Werghi and Klemen Grm and Vitomir Struc and Fernando Alonso-Fernandez and Kevin Hernandez-Diaz and Josef Bigun and Anjith George and Christophe Ecabert and Hatef Otroshi Shahreza and Ketan Kotwal and Sébastien Marcel and Iurii Medvedev and Jin Bo and Diogo Nunes and Ahmad Hassanpour and Pankaj Khatiwada and Aafan Ahmad Toor and Bian Yang},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/CameraReady-231.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics (IJCB 2023)},

pages = {1-12},

address = {Ljubljana, Slovenia},

abstract = {This paper presents the summary of the Efficient Face

Recognition Competition (EFaR) held at the 2023 International

Joint Conference on Biometrics (IJCB 2023). The

competition received 17 submissions from 6 different teams.

To drive further development of efficient face recognition

models, the submitted solutions are ranked based on a

weighted score of the achieved verification accuracies on a

diverse set of benchmarks, as well as the deployability given

by the number of floating-point operations and model size.

The evaluation of submissions is extended to bias, crossquality,

and large-scale recognition benchmarks. Overall,

the paper gives an overview of the achieved performance

values of the submitted solutions as well as a diverse set of

baselines. The submitted solutions use small, efficient network

architectures to reduce the computational cost, some

solutions apply model quantization. An outlook on possible

techniques that are underrepresented in current solutions is

given as well.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SSBRC2023,

title = {Sclera Segmentation and Joint Recognition Benchmarking Competition: SSRBC 2023},

author = {Abhijit Das and Saurabh K Atreya and Aritra Mukherjee and Matej Vitek and Haiqing Li and Caiyong Wang and Zhao Guangzhe and Fadi Boutros and Patrick Siebke and Jan Niklas Kolf and Naser Damer and Ye Sun and Lu Hexin and Fab Aobo and You Sheng and Sabari Nathan and Suganya Ramamoorthy and Rampriya R S and Geetanjali G and Prinaka Sihag and Aditya Nigam and Peter Peer and Umapada Pal and Vitomir Struc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/CameraReady-233.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics (IJCB 2023)},

pages = {1-10},

address = {Ljubljana, Slovenia},

abstract = {This paper presents the summary of the Sclera Segmentation

and Joint Recognition Benchmarking Competition (SSRBC

2023) held in conjunction with IEEE International

Joint Conference on Biometrics (IJCB 2023). Different from

the previous editions of the competition, SSRBC 2023 not

only explored the performance of the latest and most advanced

sclera segmentation models, but also studied the impact

of segmentation quality on recognition performance.

Five groups took part in SSRBC 2023 and submitted a total

of six segmentation models and one recognition technique

for scoring. The submitted solutions included a wide

variety of conceptually diverse deep-learning models and

were rigorously tested on three publicly available datasets,

i.e., MASD, SBVPI and MOBIUS. Most of the segmentation

models achieved encouraging segmentation and recognition

performance. Most importantly, we observed that better

segmentation results always translate into better verification

performance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{UERC2023,

title = {The Unconstrained Ear Recognition Challenge 2023: Maximizing Performance and Minimizing Bias},

author = {Ziga Emersic and Tetsushi Ohki and Muku Akasaka and Takahiko Arakawa and Soshi Maeda and Masora Okano and Yuya Sato and Anjith George and Sébastien Marcel and Iyyakutti Iyappan Ganapathi and Syed Sadaf Ali and Sajid Javed and Naoufel Werghi and Selin Gök Işık and Erdi Sarıtaş and Hazim Kemal Ekenel and Valter Hudovernik and Jan Niklas Kolf and Fadi Boutros and Naser Damer and Geetanjali Sharma and Aman Kamboj and Aditya Nigam and Deepak Kumar Jain and Guillermo Cámara and Peter Peer and Vitomir Struc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/09/CameraReady-234.pdf},

year  = {2023},

date = {2023-09-01},

booktitle = {IEEE International Joint Conference on Biometrics (IJCB 2023)},

pages = {1-10},

address = {Ljubljana, Slovenia},

abstract = {The paper provides a summary of the 2023 Unconstrained

Ear Recognition Challenge (UERC), a benchmarking

effort focused on ear recognition from images acquired

in uncontrolled environments. The objective of the challenge

was to evaluate the effectiveness of current ear recognition

techniques on a challenging ear dataset while analyzing

the techniques from two distinct aspects, i.e., verification

performance and bias with respect to specific demographic

factors, i.e., gender and ethnicity. Seven research

groups participated in the challenge and submitted

a seven distinct recognition approaches that ranged from

descriptor-based methods and deep-learning models to ensemble

techniques that relied on multiple data representations

to maximize performance and minimize bias. A comprehensive

investigation into the performance of the submitted

models is presented, as well as an in-depth analysis of

bias and associated performance differentials due to differences

in gender and ethnicity. The results of the challenge

suggest that a wide variety of models (e.g., transformers,

convolutional neural networks, ensemble models) is capable

of achieving competitive recognition results, but also

that all of the models still exhibit considerable performance

differentials with respect to both gender and ethnicity. To

promote further development of unbiased and effective ear

recognition models, the starter kit of UERC 2023 together

with the baseline model, and training and test data is made

available from: http://ears.fri.uni-lj.si/.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MarijaTomato2023,

title = {TomatoDIFF: On–plant Tomato Segmentation with Denoising Diffusion Models},

author = {Marija Ivanovska and Vitomir Štruc and Janez Perš },

url = {https://arxiv.org/pdf/2307.01064.pdf

https://ieeexplore.ieee.org/document/10215774},

doi = {10.23919/MVA57639.2023.10215774},

year  = {2023},

date = {2023-07-23},

urldate = {2023-07-23},

booktitle = {18th International Conference on Machine Vision and Applications (MVA 2023)},

pages = {1-6},

abstract = {Artificial intelligence applications enable farmers to optimize crop growth and production while reducing costs and environmental impact. Computer vision-based algorithms in particular, are commonly used for fruit segmentation, enabling in-depth analysis of the harvest quality and accurate yield estimation. In this paper, we propose TomatoDIFF, a novel diffusion-based model for semantic segmentation of on-plant tomatoes. When evaluated against other competitive methods, our model demonstrates

state-of-the-art (SOTA) performance, even in challenging environments with highly occluded fruits. Additionally, we introduce Tomatopia, a new, large and challenging dataset of greenhouse tomatoes. The dataset comprises high-resolution RGB-D images and pixel-level annotations of the fruits. The source code of TomatoDIFF and Tomatopia are available at https://github. com/MIvanovska/TomatoDIFF},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{PleshCVPR2023,

title = {GlassesGAN: Eyewear Personalization using Synthetic Appearance Discovery and Targeted Subspace Modeling},

author = {Richard Plesh and Peter Peer and Vitomir Štruc},

url = {https://arxiv.org/pdf/2210.14145.pdf

https://openaccess.thecvf.com/content/CVPR2023/html/Plesh_GlassesGAN_Eyewear_Personalization_Using_Synthetic_Appearance_Discovery_and_Targeted_Subspace_CVPR_2023_paper.html},

year  = {2023},

date = {2023-06-18},

urldate = {2023-06-18},

booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR) },

abstract = {We present GlassesGAN, a novel image editing framework for custom design of glasses, that sets a new standard in terms of image quality, edit realism, and continuous multi-style edit capability. To facilitate the editing process with GlassesGAN, we propose a Targeted Subspace Modelling (TSM) procedure that, based on a novel mechanism for (synthetic) appearance discovery in the latent space of a pre-trained GAN generator, constructs an eyeglasses-specific (latent) subspace that the editing framework can utilize. Additionally, we also introduce an appearance-constrained subspace initialization (SI) technique that centers the latent representation of the given input image in the well-defined part of the constructed subspace to improve the reliability of the learned edits. We test GlassesGAN on two (diverse) high-resolution datasets (CelebA-HQ and SiblingsDB-HQf) and compare it to three state-of-the-art competitors, i.e., InterfaceGAN, GANSpace, and MaskGAN. The reported results show that GlassesGAN convincingly outperforms all competing techniques, while offering additional functionality (e.g.,  fine-grained multi-style editing) not available with any of the competitors.  The source code will be made freely available.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{IWBF2023_Marija,

title = {Face Morphing Attack Detection with Denoising Diffusion Probabilistic Models},

author = {Marija Ivanovska and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/03/IWBF2023_Morphing.pdf},

year  = {2023},

date = {2023-02-28},

booktitle = {Proceedings of the International Workshop on Biometrics and Forensics (IWBF)},

pages = {1-6},

abstract = {Morphed face images have recently become a growing concern for existing face verification systems, as they are relatively easy to generate and can be used to impersonate someone's identity for various malicious purposes. Efficient Morphing Attack Detection (MAD) that generalizes well across different morphing techniques is, therefore, of paramount importance. Existing MAD techniques predominantly rely on discriminative models that learn from examples of bona fide and morphed images and, as a result, often exhibit sub-optimal generalization performance when confronted with unknown types of morphing attacks. To address this problem, we propose a novel, diffusion--based MAD method in this paper that learns only from the characteristics of bona fide images. Various forms of morphing attacks are then detected by our model as out-of-distribution samples. We perform rigorous experiments over four different datasets (CASIA-WebFace, FRLL-Morphs, FERET-Morphs and FRGC-Morphs) and compare the proposed solution to both discriminatively-trained and once-class MAD models. The experimental results show that our MAD model achieves highly competitive results on all considered datasets.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{iwbf2023babnik,

title = {Optimization-Based Improvement of Face Image Quality Assessment Techniques},

author = {Žiga Babnik and Naser Damer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2023/03/IWBF_23___paper-1.pdf},

year  = {2023},

date = {2023-02-28},

booktitle = {Proceedings of the International Workshop on Biometrics and Forensics (IWBF)},

abstract = {Contemporary face recognition~(FR) models achieve near-ideal recognition performance in constrained settings, yet do not fully translate the performance to unconstrained (real-world) scenarios. To help improve the performance and stability of FR systems in such unconstrained settings, face image quality assessment (FIQA) techniques try to infer sample-quality information from the input face images that can aid with the recognition process. While existing FIQA techniques are able to efficiently capture the differences between high and low quality images, they typically cannot fully distinguish between images of similar quality, leading to lower performance in many scenarios. To address this issue, we present in this paper a supervised quality-label optimization approach, aimed at improving the performance of existing FIQA techniques. The developed optimization procedure infuses additional information (computed with a selected FR model) into the initial quality scores generated with a given FIQA technique to produce better estimates of the ``actual'' image quality. We evaluate the proposed approach in comprehensive experiments with six  state-of-the-art FIQA approaches (CR-FIQA, FaceQAN, SER-FIQ, PCNet, MagFace, SER-FIQ) on five commonly used benchmarks (LFW, CFP-FP, CPLFW, CALFW, XQLFW) using three targeted FR models (ArcFace, ElasticFace, CurricularFace) with highly encouraging results. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{WACVW2023,

title = {Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition},

author = {Klemen Grm and Berk Ozata and Vitomir Struc and Hazim K. Ekenel},

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

https://arxiv.org/abs/2211.15225

https://openaccess.thecvf.com/content/WACV2023W/RWS/papers/Grm_Meet-in-the-Middle_Multi-Scale_Upsampling_and_Matching_for_Cross-Resolution_Face_Recognition_WACVW_2023_paper.pdf



},

year  = {2023},

date = {2023-01-06},

booktitle = {WACV workshops},

pages = {120-129},

abstract = {In this paper, we aim to address the large domain gap between high-resolution face images, e.g., from professional portrait photography, and low-quality surveillance images, e.g., from security cameras. Establishing an identity match between disparate sources like this is a classical surveillance face identification scenario, which continues to be a challenging problem for modern face recognition techniques. To that end, we propose a method that combines face super-resolution, resolution matching, and multi-scale template accumulation to reliably recognize faces from long-range surveillance footage, including from low quality sources. The proposed approach does not require training or fine-tuning on the target dataset of real surveillance images. Extensive experiments show that our proposed method is able to outperform even existing methods fine-tuned to the SCFace dataset.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{TomasevicIJCBBiOcular,

title = {BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images},

author = {Darian Tomašević and Peter Peer and Vitomir Štruc },

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/12/BiModal_StyleGAN.pdf

https://arxiv.org/pdf/2205.01536.pdf},

year  = {2022},

date = {2022-10-20},

urldate = {2022-10-20},

booktitle = {IEEE/IAPR International Joint Conference on Biometrics (IJCB 2022) },

pages = {1-10},

abstract = {Current state-of-the-art segmentation techniques for ocular images are critically dependent on large-scale annotated datasets, which are labor-intensive to gather and often raise privacy concerns. In this paper, we present a novel framework, called BiOcularGAN, capable of generating synthetic large-scale datasets of photorealistic (visible light and near-infrared) ocular images, together with corresponding segmentation labels to address these issues. At its core, the framework relies on a novel Dual-Branch StyleGAN2 (DB-StyleGAN2) model that facilitates bimodal image generation, and a Semantic Mask Generator (SMG) component that produces semantic annotations by exploiting latent features of the DB-StyleGAN2 model. We evaluate BiOcularGAN through extensive experiments across five diverse ocular datasets and analyze the effects of bimodal data generation on image quality and the produced annotations. Our experimental results show that BiOcularGAN is able to produce high-quality matching bimodal images and annotations (with minimal manual intervention) that can be used to train highly competitive (deep) segmentation models (in a privacy aware-manner) that perform well across multiple real-world datasets. The source code for the BiOcularGAN framework is publicly available at: https://github.com/dariant/BiOcularGAN.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{IvanovskaSYNMAD,

title = {SYN-MAD 2022: Competition on Face Morphing Attack Detection based on Privacy-aware Synthetic Training Data},

author = {Marco Huber and Fadi Boutros and Anh Thi Luu and Kiran Raja and Raghavendra Ramachandra and Naser Damer and Pedro C. Neto and Tiago Goncalves and Ana F. Sequeira and Jaime S. Cardoso and João Tremoco and Miguel Lourenco and Sergio Serra and Eduardo Cermeno and Marija Ivanovska and Borut Batagelj and Andrej Kronovšek and Peter Peer and Vitomir Štruc},

url = {https://ieeexplore.ieee.org/iel7/10007927/10007928/10007950.pdf?casa_token=k7CV1Vs4DUsAAAAA:xMvzvPAyLBoPv1PqtJQTmZQ9S3TJOlExgcxOeuZPNEuVFKVuIfofx30CgN-jnhVB8_5o_Ne3nJLB},

doi = {10.1109/IJCB54206.2022.10007950},

isbn = {978-1-6654-6394-2},

year  = {2022},

date = {2022-09-01},

urldate = {2022-09-01},

booktitle = {IEEE International Joint Conference on Biometrics (IJCB)},

pages = {1-10},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MarijaMorphing,

title = {Face Morphing Attack Detection Using Privacy-Aware Training Data},

author = {Marija Ivanovska and Andrej Kronovšek and Peter Peer and Vitomir Štruc and Borut Batagelj },

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/08/2022_ERK__Face_Morphing_Attack_Detecton_Using_Privacy_Aware_Training_Data.pdf},

year  = {2022},

date = {2022-08-01},

urldate = {2022-08-01},

booktitle = {Proceedings of ERK 2022},

pages = {1-4},

abstract = {Images of morphed faces pose a serious threat to face recognition--based security systems, as they can be used to illegally verify the identity of multiple people with a single morphed image. Modern detection algorithms learn to identify such morphing attacks using authentic images of real individuals. This approach raises various privacy concerns and limits the amount of publicly available training data. In this paper, we explore the efficacy of detection algorithms that are trained only on faces of non--existing people and their respective morphs. To this end, two dedicated algorithms are trained with synthetic data and then evaluated on three real-world datasets, i.e.: FRLL-Morphs, FERET-Morphs and FRGC-Morphs. Our results show that synthetic facial images can be successfully employed for the training process of the detection algorithms and generalize well to real-world scenarios.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SirceljSuperQuadrics,

title = {Hierarchical Superquadric Decomposition with Implicit Space Separation},

author = {Jaka Šircelj and Peter Peer and Franc Solina and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/08/sq_erk.pdf},

year  = {2022},

date = {2022-08-01},

urldate = {2022-08-01},

booktitle = {Proceedings of ERK 2022},

pages = {1-4},

abstract = {We introduce a new method to reconstruct 3D objects using a set of volumetric primitives, i.e., superquadrics. The method hierarchically decomposes a target 3D object into pairs of superquadrics recovering finer and finer details. While such hierarchical methods have been studied before, we introduce a new way of splitting the object space using only properties of the predicted superquadrics. The method is trained and evaluated on the ShapeNet dataset. The results of our experiments suggest that reasonable reconstructions can be obtained with the proposed approach for a diverse set of objects with complex geometry.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Grm2022Erk,

title = {Optimization-based Image Filter Design for Self-supervised Super-resolution Training},

author = {Klemen Grm and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/08/erk22_filtri.pdf},

year  = {2022},

date = {2022-08-01},

booktitle = {Proceedings of ERK 2022},

abstract = {Single-image super-resolution can be posed as a self - supervised machine learning task, where the training inputs and targets are derived from an unlabelled dataset of high-resolution images. For super-resolution training, the derivation takes the form of a degradation function that yields low-resolution images given high-resolution ones. Typically, the degradation function is selected manually based on heuristics, such as the desired magnification ratio of the super-resolution method being trained. In this paper, we instead propose principled, optimization-based methods for picking the image filter of the degradation function based on its desired properties in the frequency domain. We develop implicit and explicit methods for filter optimization and demonstrate the resulting filters are better at rejecting aliasing and matching the frequency domain characteristics of real-life low-resolution images than commonly used heuristic picks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{BabnikErk2022,

title = {Iterativna optimizacija ocen kakovosti slikovnih podatkov v sistemih za razpoznavanje obrazov},

author = {Žiga Babnik and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/08/ERK_2022.pdf},

year  = {2022},

date = {2022-08-01},

booktitle = {Proceedings of ERK 2022},

pages = {1-4},

abstract = {While recent face recognition (FR) systems achieve excellent results in many deployment scenarios, their performance in challenging real-world settings is still under question. For this reason, face image quality assessment (FIQA) techniques aim to support FR systems, by providing them with sample quality information that can be used to reject poor quality data unsuitable for recognition purposes. Several groups of FIQA methods relying on different concepts have been proposed in the literature, all of which can be used for generating quality scores of facial images that can serve as pseudo ground-truth (quality) labels and be exploited for training (regression-based) quality estimation models. Several FIQA approaches show that a significant amount of sample-quality information can be extracted from mated similarity-score distributions generated with some face matcher. Based on this insight, we propose in this paper a quality label optimization approach, which incorporates sample-quality information from mated-pair similarities into quality predictions of existing off-the-shelf FIQA techniques. We evaluate the proposed approach using three state-of-the-art FIQA methods over three diverse datasets. The results of our experiments show that the proposed optimization procedure heavily depends on the number of executed optimization iterations. At ten iterations, the approach seems to perform the best, consistently outperforming the base quality scores of the three FIQA methods, chosen for the experiments.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ICPR2022,

title = {FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration},

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

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/06/ICPR_2022___paper-17.pdf},

year  = {2022},

date = {2022-05-17},

urldate = {2022-05-17},

booktitle = {IAPR International Conference on Pattern Recognition (ICPR)},

abstract = {Recent state-of-the-art face recognition (FR) approaches have achieved impressive performance, yet unconstrained face recognition still represents an open problem. Face image quality assessment (FIQA) approaches aim to estimate the quality of the input samples that can help provide information on the confidence of the recognition decision and eventually lead to improved results in challenging scenarios. While much progress has been made in face image quality assessment in recent years, computing reliable quality scores for diverse facial images and FR models remains challenging. In this paper, we propose a novel approach to face image quality assessment, called FaceQAN, that is based on adversarial examples and relies on the analysis of adversarial noise which can be calculated with any FR model learned by using some form of gradient descent. As such, the proposed approach is the first to link image quality to adversarial attacks. Comprehensive (cross-model as well as model-specific) experiments are conducted with four benchmark datasets, i.e., LFW, CFP–FP, XQLFW and IJB–C, four FR models, i.e., CosFace, ArcFace, CurricularFace and ElasticFace and in comparison to seven state-of-the-art FIQA methods to demonstrate the performance of FaceQAN. Experimental results show that FaceQAN achieves competitive results, while exhibiting several desirable characteristics. The source code for FaceQAN will be made publicly available.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{EUSIPCO_2022,

title = {Assessing Bias in Face Image Quality Assessment},

author = {Žiga Babnik and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/06/EUSIPCO_2022___paper.pdf},

year  = {2022},

date = {2022-05-16},

urldate = {2022-05-16},

booktitle = {EUSIPCO 2022},

abstract = {Face image quality assessment (FIQA) attempts to improve face recognition (FR) performance  by providing additional information about sample quality. 

Because FIQA methods attempt to estimate the utility of a sample for face recognition, it is reasonable to assume that these methods are heavily influenced by the underlying face recognition system. Although modern face recognition systems are known to perform well, several studies have found that such systems often exhibit problems with demographic bias. It is therefore likely that such problems are also present with FIQA techniques. To investigate the demographic biases associated with FIQA approaches, this paper presents a comprehensive study involving a variety of quality assessment methods (general-purpose image quality assessment, supervised face quality assessment, and unsupervised face quality assessment methods) and three diverse state-of-the-art FR models. 

Our analysis on the Balanced Faces in the Wild (BFW) dataset shows that all techniques considered are affected more by variations in race than sex. While the general-purpose image quality assessment methods appear to be less biased with respect to the two demographic factors considered, the supervised and unsupervised face image quality assessment methods both show strong bias with a tendency to favor white individuals (of either sex). In addition, we found that methods that are less racially biased perform worse overall. This suggests that the observed bias in FIQA methods is to a significant extent related to the underlying face recognition system.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{KinEars,

title = {Kinship Verification from Ear Images: An Explorative Study with Deep Learning Models},

author = {Grega Dvoršak and Ankita Dwivedi and Vitomir Štruc and Peter Peer and Žiga Emeršič},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/03/Gregovi_Uhlji_Template-2.pdf},

year  = {2022},

date = {2022-04-21},

urldate = {2022-04-21},

booktitle = {International Workshop on Biometrics and Forensics (IWBF)},

pages = {1--6},

abstract = {The analysis of kin relations from visual data represents a challenging research problem with important real-world applications. However, research in this area has mostly been limited to the analysis of facial images, despite the potential of other physical (human) characteristics for this task. In this paper, we therefore study the problem of kinship verification from ear images and investigate whether salient appearance characteristics, useful for this task, can be extracted from ear data. To facilitate the study, we introduce a novel dataset, called KinEar, that contains data from 19 families with each family member having from 15 to 31 ear images. Using the KinEar data, we conduct experiments using a Siamese training setup and  5 recent deep learning backbones. The results of our experiments suggests that ear images  represent a viable alternative to other modalities for kinship verification, as 4 out of 5 considered  models reach a performance of over 60% in terms of the Area Under the Receiver Operating Characteristics (ROC-AUC). },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Rosus2022,

title = {Segmentacija telesa z uporabo večciljnega učenja},

author = {Julijan Jug and Ajda Lampe and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/03/Rosus2020.pdf},

year  = {2022},

date = {2022-03-17},

booktitle = {Proceedings of Rosus 2022},

abstract = {Segmentacija je pomemben del številnih problemov računalniškega vida, ki vključujejo človeške podobe, in je ena ključnih komponent, ki vpliva na uspešnost vseh nadaljnjih nalog. Več predhodnih del je ta problem obravnavalo z uporabo večciljnega modela, ki izkorišča korelacije med različnimi nalogami za izboljšanje uspešnosti segmentacije. Na podlagi uspešnosti takšnih rešitev v tem prispevku predstavljamo nov večciljni model za segmentacijo/razčlenjevanje ljudi, ki vključuje tri naloge, tj. (i) napoved skeletnih točk, (ii) napoved globinske predstavitve poze in (iii) segmentacijo človeškega telesa. Glavna ideja predlaganega modela Segmentacija-Skelet-Globinska predstavitev (ali na kratko iz angleščine SPD) je naučiti se boljšega modela segmentacije z izmenjavo znanja med različnimi, a med seboj povezanimi nalogami. SPD temelji na skupni hrbtenici globoke nevronske mreže, ki se razcepi na tri glave modela, specifične za nalogo, in se uči z uporabo cilja optimizacije za več nalog. Učinkovitost modela je analizirana s strogimi eksperimenti na nizih podatkov LIP in ATR ter v primerjavi z nedavnim (najsodobnejšim) večciljnim modelom segmentacije telesa. Predstavljene so tudi študije ablacije. Naši eksperimentalni rezultati kažejo, da je predlagani večciljni (segmentacijski) model zelo konkurenčen in da uvedba dodatnih nalog prispeva k večji skupni uspešnosti segmentacije.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{JulijanJugBody,

title = {Body Segmentation Using Multi-task Learning},

author = {Julijan Jug and Ajda Lampe and Vitomir Štruc and Peter Peer},

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

doi = {10.1109/ICAIIC54071.2022.9722662},

isbn = {978-1-6654-5818-4},

year  = {2022},

date = {2022-01-20},

urldate = {2022-01-20},

booktitle = {International Conference on Artificial Intelligence in Information and Communication (ICAIIC)},

publisher = {IEEE},

abstract = {Body segmentation is an important step in many computer vision problems involving human images and one of the key components that affects the performance of all downstream tasks.  Several prior works have approached this problem using a multi-task model that exploits correlations between different tasks to improve segmentation performance.  Based on the success of such solutions, we present in this paper a novel multi-task model for human segmentation/parsing that involves three tasks, i.e., (i) keypoint-based skeleton estimation, (ii) dense pose prediction, and (iii) human-body segmentation. The main idea behind the proposed Segmentation--Pose--DensePose model (or SPD for short) is to learn a  better segmentation model by sharing knowledge across different, yet related tasks. SPD is based on a shared deep neural network backbone that branches off into three task-specific model heads and is learned using a multi-task optimization objective. The performance of the  model is analysed through rigorous experiments on the  LIP and ATR datasets and in comparison to a recent (state-of-the-art) multi-task body-segmentation model. Comprehensive ablation studies are also presented. Our experimental results show that the proposed multi-task (segmentation) model is highly competitive and that the introduction of additional tasks contributes towards a higher overall segmentation performance. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{WACV2022_Fele,

title = {C-VTON: Context-Driven Image-Based Virtual Try-On Network},

author = {Benjamin Fele and Ajda Lampe and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2022/12/WACV2022_Benjamin_compressed-1.pdf},

year  = {2022},

date = {2022-01-04},

urldate = {2022-01-04},

booktitle = {IEEE/CVF Winter Applications in Computer Vision (WACV)},

pages = {1--10},

abstract = {Image-based virtual try-on techniques have shown great promise for enhancing the user-experience and improving customer satisfaction on fashion-oriented e-commerce platforms. However, existing techniques are currently still limited in the quality of the try-on results they are able to produce from input images of diverse characteristics. In this work, we propose a Context-Driven Virtual Try-On Network (C-VTON) that addresses these limitations and  convincingly transfers selected clothing items to the target subjects even under challenging pose configurations and in the presence of self-occlusions. At the core of the C-VTON pipeline are: (i) a geometric matching procedure that efficiently aligns the target clothing with the pose of the person in the input images, and (ii) a powerful image generator that utilizes various types of contextual information when synthesizing the final try-on result. C-VTON is evaluated in rigorous experiments on the VITON and MPV datasets and in comparison to state-of-the-art techniques from the literature. Experimental results show that the proposed approach is able to produce photo-realistic and visually convincing results and significantly improves on the existing state-of-the-art.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ERK_Marija_2021,

title = {A Comparative Study on Discriminative and One--Class Learning Models for Deepfake Detection},

author = {Marija Ivanovska and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2021/10/ERK_2021__A_Comparative_Study_of_Discriminative_and_One__Class_Learning_Models_for_Deepfake_Detection.pdf},

year  = {2021},

date = {2021-09-20},

booktitle = {Proceedings of ERK 2021},

pages = {1--4},

abstract = {Deepfakes or manipulated face images, where a donor's face is swapped with the face of a target person, have gained enormous popularity among the general public recently. With the advancements in  artificial intelligence and generative modeling  

such images can nowadays be easily generated and used to spread misinformation and harm individuals, businesses or society. As the tools for generating deepfakes are rapidly improving, it is critical for deepfake detection models to be able to recognize advanced, sophisticated data manipulations, including those that have not been seen during  training. In this paper, we explore the use of one--class learning models as an alternative to discriminative methods for the detection of deepfakes. We conduct a  comparative study with three popular deepfake datasets and investigate the performance of selected (discriminative and one-class) detection models in matched- and cross-dataset experiments. Our results show that disciminative models significantly outperform one-class models when training and testing data come from the same dataset, but degrade considerably when the characteristics of the testing data deviate from the training setting. In such cases, one-class models tend to generalize much better.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Grm-SuperResolution_ERK2021,

title = {Frequency Band Encoding for Face Super-Resolution},

author = {Klemen Grm and Štruc Vitomir},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2021/10/SRAE_ERK21.pdf},

year  = {2021},

date = {2021-09-10},

booktitle = {Proceedings of ERK 2021},

pages = {1-4},

abstract = {In this paper, we present a novel method for face super-resolution based on an encoder-decoder architecture. Unlike previous approaches, which focused primarily on directly reconstructing the high-resolution face appearance from low-resolution images, our method relies on a multi-stage approach where we learn a face representation in different frequency bands, followed by decoding the representation into a high-resolution image. Using quantitative experiments, we are able to demonstrate that this approach results in better face image reconstruction, as well as aiding in downstream semantic tasks such as face recognition and face verification.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MFR_IJCB2021,

title = {MFR 2021: Masked Face Recognition Competition},

author = {Fadi Boutros and Naser Damer and Jan Niklas Kolf and Kiran Raja and Florian Kirchbuchner and Raghavendra Ramachandra and Arjan Kuijper and Pengcheng Fang and Chao Zhang and Fei Wang and David Montero and Naiara Aginako and Basilio Sierra and Marcos Nieto and Mustafa Ekrem Erakin and Ugur Demir and Hazım Kemal Ekenel and Asaki Kataoka and Kohei Ichikawa and Shizuma Kubo and Jie Zhang and Mingjie He and Dan Han and Shiguang Shan and Klemen Grm and Vitomir Štruc and Sachith Seneviratne and Nuran Kasthuriarachchi and Sanka Rasnayaka and Pedro C. Neto and Ana F. Sequeira and Joao Ribeiro Pinto and Mohsen Saffari and Jaime S. Cardoso},

url = {https://ieeexplore.ieee.org/iel7/9484326/9484328/09484337.pdf?casa_token=OOL4s274P0YAAAAA:XE7ga2rP_wNom2Zeva75ZwNwN-HKz6kF1HZtkpzrdTdz36eaGcLffWkzOgIe3xU2PqaU30qTLws},

doi = {10.1109/IJCB52358.2021.9484337},

year  = {2021},

date = {2021-08-01},

booktitle = {Proceedings of the IEEE International Joint Conference on Biometrics (IJCB 2021)},

abstract = {This paper presents a summary of the Masked Face Recognition Competitions (MFR) held within the 2021 International Joint Conference on Biometrics (IJCB 2021). The competition attracted a total of 10 participating teams with valid submissions. The affiliations of these teams are diverse and associated with academia and industry in nine different countries. These teams successfully submitted 18 valid solutions. The competition is designed to motivate solutions aiming at enhancing the face recognition accuracy of masked faces. Moreover, the competition considered the deployability of the proposed solutions by taking the compactness of the face recognition models into account. A private dataset representing a collaborative, multisession, real masked, capture scenario is used to evaluate the submitted solutions. In comparison to one of the topperforming academic face recognition solutions, 10 out of the 18 submitted solutions did score higher masked face verification accuracy.

},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{NIR_IJCB2021,

title = {NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization},

author = {Caiyong Wang and Yunlong Wang and Kunbo Zhang and Jawad Muhammad and Tianhao Lu and Qi Zhang and Qichuan Tian and Zhaofeng He and Zhenan Sun and Yiwen Zhang and Tianbao Liu and Wei Yang and Dongliang Wu and Yingfeng Liu and Ruiye Zhou and Huihai Wu and Hao Zhang and Junbao Wang and Jiayi Wang and Wantong Xiong and Xueyu Shi and Shao Zeng and Peihua Li and Haodong Sun and Jing Wang and Jiale Zhang and Qi Wang and Huijie Wu and Xinhui Zhang and Haiqing Li and Yu Chen and Liang Chen and Menghan Zhang and Ye Sun and Zhiyong Zhou and Fadi Boutros and Naser Damer and Arjan Kuijper and Juan Tapia and Andres Valenzuela and Christoph Busch and Gourav Gupta and Kiran Raja and Xi Wu and Xiaojie Li and Jingfu Yang and Hongyan Jing and Xin Wang and Bin Kong and Youbing Yin and Qi Song and Siwei Lyu and Shu Hu and Leon Premk and Matej Vitek and Vitomir Štruc and Peter Peer and Jalil Nourmohammadi Khiarak and Farhang Jaryani and Samaneh Salehi Nasab and Seyed Naeim Moafinejad and Yasin Amini and Morteza Noshad},

url = {https://ieeexplore.ieee.org/iel7/9484326/9484328/09484336.pdf?casa_token=FOKx4ltO-hYAAAAA:dCkNHfumDzPGkAipRdbppNWpzAiUYUrJL6OrAjNmimTxUA0Vmx311-3-J3ej7YQc_zONxEO-XKo},

doi = {10.1109/IJCB52358.2021.9484336},

year  = {2021},

date = {2021-08-01},

booktitle = {Proceedings of the IEEE International Joint Conference on Biometrics (IJCB 2021)},

abstract = {For iris recognition in non-cooperative environments, iris segmentation has been regarded as the first most important challenge still open to the biometric community, affecting all downstream tasks from normalization to recognition. In recent years, deep learning technologies have gained significant popularity among various computer vision tasks and also been introduced in iris biometrics, especially iris segmentation. To investigate recent developments and attract more interest of researchers in the iris segmentation method, we organized the 2021 NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization (NIR-ISL 2021) at the 2021 International Joint Conference on Biometrics (IJCB 2021). The challenge was used as a public platform to assess the performance of iris segmentation and localization methods on Asian and African NIR iris images captured in non-cooperative environments. The three best-performing entries achieved solid and satisfactory iris segmentation and localization results in most cases, and their code and models have been made publicly available for reproducibility research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{BortolatoFG2020,

title = {Learning privacy-enhancing face representations through feature disentanglement},

author = {Blaž Bortolato and Marija Ivanovska and Peter Rot and Janez Križaj and Philipp Terhorst and Naser Damer and Peter Peer and Vitomir Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/07/FG2020___Learning_privacy_enhancing_face_representations_through_feature_disentanglement-1.pdf

},

year  = {2020},

date = {2020-11-04},

booktitle = {Proceedings of FG 2020},

publisher = {IEEE},

abstract = {Convolutional Neural Networks (CNNs) are today the de-facto standard for extracting compact and discriminative face representations (templates) from images in automatic face recognition systems. Due to the characteristics of CNN models, the generated representations typically encode a multitude of information ranging from identity to soft-biometric attributes, such as age, gender or ethnicity. However, since these representations were computed for the purpose of identity recognition only, the soft-biometric information contained in the templates represents a serious privacy risk. To mitigate this problem, we present in this paper a privacy-enhancing approach capable of suppressing potentially sensitive soft-biometric information in face representations without significantly compromising identity information. Specifically, we introduce a Privacy-Enhancing Face-Representation learning Network (PFRNet) that disentangles identity from attribute information in face representations and consequently allows to efficiently suppress soft-biometrics in face templates. We demonstrate the feasibility of PFRNet on the problem of gender suppression and show through rigorous experiments on the CelebA, Labeled Faces in the Wild (LFW) and Adience datasets that the proposed disentanglement-based approach is highly effective and improves significantly on the existing state-of-the-art.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SSBC2020,

title = {SSBC 2020: Sclera Segmentation Benchmarking Competition in the Mobile Environment},

author = {M. Vitek and A. Das and Y. Pourcenoux and A. Missler and C. Paumier and S. Das and I. De Ghosh and D. R. Lucio and L. A. Zanlorensi Jr. and D. Menotti and F. Boutros and N. Damer and J. H. Grebe and A. Kuijper and J. Hu and Y. He and C. Wang and H. Liu and Y. Wang and Z. Sun and D. Osorio-Roig and C. Rathgeb and C. Busch and J. Tapia and A.~Valenzuela and G. Zampoukis and L. Tsochatzidis and I. Pratikakis and S. Nathan and R. Suganya and V. Mehta and A. Dhall and K. Raja and G. Gupta and J. N. Khiarak and M. Akbari-Shahper and F. Jaryani and M. Asgari-Chenaghlu and R. Vyas and S. Dakshit and S. Dakshit and P. Peer and U. Pal and V. Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/11/IJCB_SSBC_2020.pdf},

year  = {2020},

date = {2020-09-28},

booktitle = {International Joint Conference on Biometrics (IJCB 2020)},

pages = {1--10},

abstract = {The paper presents a summary of the 2020 Sclera Segmentation Benchmarking Competition (SSBC), the 7th in the series of group benchmarking efforts centred around the problem of sclera segmentation. Different from previous editions, the goal of SSBC 2020 was to evaluate the performance of sclera-segmentation models on images captured with mobile devices. The competition was used as a platform to assess the sensitivity of existing models to i) differences in mobile devices used for image capture and ii) changes in the ambient acquisition conditions. 26 research groups registered for SSBC 2020, out of which 13 took part in the final round and submitted a total of 16 segmentation models for scoring. These included a wide variety of deep-learning solutions as well as one approach based on standard image processing techniques. Experiments were conducted with three recent datasets. Most of the segmentation models achieved relatively consistent  performance across images captured with different mobile devices (with slight differences across devices), but struggled most with  low-quality images captured in challenging ambient conditions, i.e., in an indoor environment and with poor lighting. },

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Biosig_naser_2020,

title = {Privacy Evaluation Protocols for the Evaluation of Soft-Biometric Privacy-Enhancing Technologies},

author = {Philipp Terhörst, Marco Huber, Naser Damer, Peter Rot, Florian Kirchbuchner, Vitomir Struc, Arjan Kuijper},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/11/Biosig_privacy.pdf},

issn = {1617-5468},

year  = {2020},

date = {2020-09-16},

booktitle = {Proceedings of the International Conference of the Biometrics Special Interest Group (BIOSIG) 2020},

pages = {1-5},

publisher = {IEEE},

abstract = {Biometric data includes privacy-sensitive information, such as soft-biometrics. Soft-biometric privacy enhancing technologies aim at limiting the possibility of deducing such information. Previous works proposed several solutions to this problem using several different evaluation processes, metrics, and attack scenarios. The absence of a standardized evaluation protocol makes a meaningful comparison of these solutions difficult. In this work, we propose privacy evaluation protocols (PEPs) for privacy-enhancing technologies (PETs) dealing with soft-biometric privacy. Our framework evaluates PETs in the most critical scenario of an attacker that knows and adapts to the systems privacy-mechanism. Moreover, our PEPs differentiate between PET of learning-based or training-free nature. To ensure that our protocol meets the highest standards in both cases, it is based on Kerckhoffs‘s principle of cryptography.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GrmEUSIPCO2020,

title = {Analysis of Race and Gender Bias in Deep Age Estimation Model},

author = {Andraž Puc and Vitomir Štruc and Klemen Grm},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2020/07/race_and_gender_bias_eusipco-2.pdf},

year  = {2020},

date = {2020-09-01},

booktitle = {Proceedings of EUSIPCO 2020},

abstract = {Due to advances in deep learning and convolutional neural networks (CNNs) there has been significant progress in the field of visual age estimation from face images over recent years. While today's models are able to achieve considerable age estimation accuracy, their behaviour, especially with respect to specific demographic groups is still not well understood. In this paper, we take a deeper look at CNN-based age estimation models and analyze their performance across different race and gender groups. We use two publicly available off-the-shelf age estimation models, i.e., FaceNet and WideResNet, for our study and analyze their performance on the UTKFace and APPA-REAL datasets. We partition face images into sub-groups based on race, gender and combinations of race and gender. We then compare age estimation results and find that there are noticeable differences in performance across demographics. Specifically, our results show that age estimation accuracy is consistently higher for men than for women, while race does not appear to have consistent effects on the tested models across different test datasets.

},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sircelj2020sqcnn,

title = {Segmentation and Recovery of Superquadric Models using Convolutional Neural Networks},

author = {Jaka Šircelj and Tim Oblak and Klemen Grm and Uroš Petković and Aleš Jaklič and Peter Peer and Vitomir Štruc and Franc Solina},

url = {https://lmi.fe.uni-lj.si/en/sircelj2020cvww/

https://arxiv.org/abs/2001.10504},

year  = {2020},

date = {2020-02-03},

booktitle = {25th Computer Vision Winter Workshop (CVWW 2020)},

abstract = {In this paper we address the problem of representing 3D visual data with parameterized volumetric shape primitives. Specifically, we present a (two-stage) approach built around convolutional neural networks (CNNs) capable of segmenting complex depth scenes into the simpler geometric structures that can be represented with superquadric models. In the first stage, our approach uses a Mask RCNN model to identify superquadric-like structures in depth scenes and then fits superquadric models to the segmented structures using a specially designed CNN regressor. Using our approach we are able to describe complex structures with a small number of interpretable parameters. We evaluated the proposed approach on synthetic as well as real-world depth data and show that our solution does not only result in competitive performance in comparison to the state-of-the-art, but is able to decompose scenes into a number of superquadric models at a fraction of the time required by competing approaches. We make all data and models used in the paper available from https://lmi.fe.uni-lj.si/en/research/resources/sq-seg.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{oblak2019recovery,

title = {Recovery of Superquadrics from Range Images using Deep Learning: A Preliminary Study},

author = {Tim Oblak and Klemen Grm and Aleš Jaklič and Peter Peer and Vitomir Štruc and Franc Solina},

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

year  = {2019},

date = {2019-06-01},

booktitle = {2019 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)},

journal = {arXiv preprint arXiv:1904.06585},

pages = {45-52},

publisher = {IEEE},

abstract = {It has been a longstanding goal in computer vision to describe the 3D physical space in terms of parameterized volumetric models that would allow autonomous machines to understand and interact with their surroundings. Such models are typically motivated by human visual perception and aim to represents all elements of the physical word ranging from individual objects to complex scenes using a small set of parameters. One of the de facto standards to approach this problem are superquadrics - volumetric models that define various 3D shape primitives and can be fitted to actual 3D data (either in the form of point clouds or range images). However, existing solutions to superquadric recovery involve costly iterative fitting procedures, which limit the applicability of such techniques in practice. To alleviate this problem, we explore in this paper the possibility to recover superquadrics from range images without time consuming iterative parameter estimation techniques by using contemporary deep-learning models, more specifically, convolutional neural networks (CNNs). We pose the superquadric recovery problem as a regression task and develop a CNN regressor that is able to estimate the parameters of a superquadric model from a given range image. We train the regressor on a large set of synthetic range images, each containing a single (unrotated) superquadric shape and evaluate the learned model in comparative experiments with the current state-of-the-art. Additionally, we also present a qualitative analysis involving a dataset of real-world objects. The results of our experiments show that the proposed regressor not only outperforms the existing state-of-the-art, but also ensures a 270x faster  execution time.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}