Objave

@inproceedings{UERC2026,

title = {The Unconstrained Ear Recognition Challenge 2026: Size Matters - Ear Biometrics on Edge},

author = {D. Sušanj and J. Jin and M. Tokumasu and T. Ohki and A. Kamboj and A. Rai and S. Aggarwal and S. Ahluwalia and M. Chipade and A. Sharma and D. Pinčić and M. Banov and K. Lenac and K. Shigematsu and K. Inoue and A. Shin and H. Shirono and A. Hazra and T. Batabyal and S. Pal and D. Freire-Obregón and G. Gupta and A. Gupta and D. Arun and P. Flynn and J. L. Godoy and D. D. A. Ruiz and J. N. Khiarak and F. N. Khiarak and T.A. Saeed and L.D.M.S.S. Teja and D.P. Chowdhury and

K. Griparić and R. Lajić and D. Tomašević and B. Meden and H.K. Ekenel and G. Cámara-Chávez and V. Štruc and P. Peer and Ž. Emeršič},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2026/09/UERC26.pdf},

year  = {2026},

date = {2026-09-04},

urldate = {2026-09-04},

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

pages = {1--10},

abstract = {The 2026 Unconstrained Ear Recognition Challenge (UERC 2026), a benchmarking competition focused on lightweight and efficient ear recognition from images captured in uncontrolled environments. Building on the previous editions of the UERC series, the 2026 challenge introduced a novel evaluation paradigm that jointly assesses recognition accuracy and computational efficiency, with the goal of promoting the development of compact ear recognition models suitable for deployment on resource-constrained and edge platforms. The competition was organized into two tracks: Track 1: Lightweight Model Design, which focused on balancing recognition performance with model efficiency through a composite evaluation criterion combining verification accuracy, parameter count, and model size, and Track 2: Edge Deployment which assessed recognition accuracy together with end-to-end inference time on a standardized Raspberry Pi 4 platform. A total of 11 research groups participated in Track 1 and 8 groups competed in Track 2, submitting solutions spanning a wide range of architectures including lightweight convolutional networks, vision transformers, ensemble-distillation pipelines, and ONNX-accelerated models.

The results demonstrate that carefully designed compact architectures, such as knowledge-distilled MobileNetV4 and INT8-quantized TinyViT networks, can achieve competitive verification performance while drastically reducing parameter counts and inference time.

The competition's starter kit, baseline code, and dataset are publicly available at http://uerc.fri.uni-lj.si/.},

keywords = {competition, competition IJCB, ear, ear biometrics, ear recognition},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SSBC2026,

title = {Label-Efficient Sclera Segmentation with Foundation Models: SSBC 2026},

author = {M. Vitek and D.D. Premani and A. Das and U.N. Modi and M.S. Raval and H.H. Bhatt and P. Baumstimler and Z.A. Daniels and A.H. Sheth and M. Gondalia and K.J. Shah and C. Zhang and C. Wang and A. Shin and K. Shigematsu and H. Shirono and K. Inoue and G. Gupta and A. Gupta and G. Sharma and T. Gupta and A. Nigam and R. Ramachandra and J. Nourmohammadi Khiarak and T. Akbari Saeed and F. Nourmohammadi Khiarak and A. Kumar and U. Pal and P. Peer and V. Štruc},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2026/09/IJCB_SSBC_2026.pdf},

year  = {2026},

date = {2026-09-01},

urldate = {2026-09-01},

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

pages = {1--13},

abstract = {This paper presents a summary of the 2026 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the adaptation of foundation models for the task of sclera segmentation and the implementation of label-efficient training paradigms.~The goal of the competition was to evaluate whether massive, generalized architectures can surpass domain-specific segmentation networks, and to assess the capacity of label-efficient strategies to overcome severe data scarcity. The competition featured two tracks, i.e.: (1) the Foundation Model Adaptation track, which provided fully annotated training data to adapt pre-trained (foundation) backbones, and (2) the Label-Efficient Learning track, which restricted access to ground truth annotations but supplied a massive collection of unlabelled imagery for training arbitrary sclera segmentation models, not just foundation model. The submitted approaches employed a variety of architectural designs, including parameter-efficient adaptations, vision-language guidance, and semi-supervised multi-architecture ensembles. To score the competition entries, experiments were conducted across three sequestered evaluation datasets containing real-world and synthetic images collected under diverse conditions. Results show that label-efficient methodologies can achieve remarkable accuracy, with the top Track 2 model performing comparably to the fully supervised Track 1 winner. Moreover, comparisons with SSBC 2025 results suggest that properly (domain) adapted foundation backbones significantly outperform previous approaches under the same training/evaluation protocol and thus represent a new state-of-the-art in sclera segmentation.},

keywords = {biometrics, competition IJCB, sclera, sclera segmentation, SSBC},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{IJCBFaceCom2026,

title = {IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data},

author = {Tahar Chettaoui and Guray Ozgur and Eduarda Caldeira and Arturas Nakvosas and Hatef Otroshi Shahreza and Sebastien Marcel and Rishabh Shukla and Aditya Takkar and Rushil Khullar and Lalak Yadav and Gourav Gupta and Anant Gupta and Shiqi Yu and Vitomir Štruc and Naser Damer and Fadi Boutros},

url = {https://lmi.fe.uni-lj.si/wp-content/uploads/2026/09/IJBC_FaceComp.pdf},

year  = {2026},

date = {2026-09-01},

urldate = {2026-09-01},

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

pages = {1--12},

keywords = {biometrics, competition IJCB, face recognition, foundation models},

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 = {competition IJCB, deepfake detection, deepfakes, face, realism assessment},

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 = {biometrics, competition IJCB, computer vision, deep learning, sclera, sclera segmentation},

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 = {biometrics, competition IJCB, ocular, sclera, segmentation, SSBC},

pubstate = {published},

tppubtype = {inproceedings}

}