Seungryul Baek

Seungryul Baek ( 백승렬 )

Associate Professor
UNIST Vision and Learning (UVL) Lab
Artificial Intelligent Graduate School (AIGS) & Department of Computer Science and Engineering
College of Information and Biotechnology
Ulsan National Institute of Science and Technology (UNIST)
50 UNIST-gil, Ulju, Ulsan, South Korea, 44919

Email: srbaek@unist.ac.kr (official), sryul.baek@gmail.com (personal)
Links: [CV], [YouTube], [Google scholar]

Publications

MD Khalequzzaman Chowdhury Sayem, Mubarrat Tajoar Chowdhury, Yihalem Yimolal Tiruneh, Muneeb A. Khan, Muhammad Salman Ali, Binod Bhattarai, Seungryul Baek, "HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Denver, CO, USA, 2026 (accepted).

Thea Chum, Muneeb A. Khan, Joonsik Bang, Yun Ahn, Chang-Uk Kim, Seungryul Baek, "Crane Spreader Rotation Estimation for Vision-Based Automated Container Handling", IEEE Access 2026.

Sanskar Amgain, Prashant Shrestha, Bidur Khanal, Alina Devkota, Yash Raj Shrestha, Seungryul Baek, Prashnna K Gyawali, Binod Bhattarai, "Local K-Similarity Constraint for Medical Federated Learning with Label Noise", in Proc. of International Symposium on Biomedical Imaging (ISBI), London, UK, 2026.

Yoojin Jang, Junsu Kim, Ha Yeon Kim, Eun-Ki Lee, Eun-Sol Kim, Seungryul Baek, Jaejun Yoo, "B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing", in Proc. of British Machine Vision Conference (BMVC), Sheffield, UK, 2025.

Taehoon Kim, Jongwook Choi, Yonghyun Jeong, Haeun Noh, Jaejun Yoo, Seungryul Baek, Jongwon Choi, "Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection", in Proc. of IEEE Int. Conf. on Computer Vision (ICCV), Honolulu, HI, USA, 2025 (Highlight presentation, 2.9% Accept ratio).

Junsu Kim, Yunhoe Ku, Seungryul Beak, "Can Synthetic Images Conquer Forgetting? Beyond Unexplored Doubts in Few-Shot Class-Incremental Learning", in Proc. of the IEEE Int. Conf. on Computer Vision (ICCV) workshop on Continual Learning Vision (CLVision), Honolulu, HI, USA, 2025.

Jeongwan On, Kyeonghwan Gwak, Gunyoung Kang, Junuk Cha, Soohyun Hwang, Hyein Hwang, Seungryul Baek, "BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2025.

Uyoung Jeong, Jonathan Freer, Seungryul Baek, Hyung Jin Chang, Kwang In Kim, "PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2025.

Elkhan Ismayilzada, Khalequzzaman Sayem, Yihalem Yimolal Tiruneh, Mubarrat Tajoar Chowdhury, Muhammadjon Boboev, Seungryul Baek, "QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objects", in Proc. of Annual AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, PA, USA, 2025.

Junuk Cha, Mengwei Ren, Krishna Kumar Singh, He Zhang, Yannick Hold-Geoffroy, Seunghyun Yoon, HyunJoon Jung, Jae Shin Yoon*, Seungryul Baek*, "Text2Relight: Creative Portrait Relighting with Text Guidance", in Proc. of Annual AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, PA, USA, 2025.

Zicong Fan, Takehiko Ohkawa, Linlin Yang, Nie Lin, Zhishan Zhou, Shihao Zhou, Jiajun Liang, Zhong Gao, Xuanyang Zhang, Xue Zhang, Fei Li, Liu Zheng, Feng Lu, Karim Abou Zeid, Bastian Leibe, Jeongwan On, Seungryul Baek, Aditya Prakash, Saurabh Gupta, Kun He, Yoichi Sato, Otmar Hilliges, Hyung Jin Chang, Angela Yao, "Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects", in Proc. of European Conference on Computer Vision (ECCV), Milano, Italy, 2024.

Junsu Kim, Hoseong Cho, Jihyeon Kim, Yihalem Yimolal Tiruneh, Seungryul Baek, "SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2024 (Highlight presentation, 324/11,532≈2.8% Accept ratio).

Junuk Cha, Jihyeon Kim, Jae Shin Yoon*, Seungryul Baek*, "Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2024.

Jongwook Choi, Taehoon Kim, Yonghyun Jeong, Seungryul Baek, Jongwon Choi, "Exploiting Style Latent Flows for Generalizing Video Deepfake Detection", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2024.

Junsu Kim, Yunhoe Ku, Jihyeon Kim, Junuk Cha, Seungryul Baek, "VLM-PL: Advanced Pseudo Labeling approach Class Incremental Object Detection with Vision-Language Model", CVPR Workshop on Continual Learning Vision (CLVision), Seattle, WA, USA, 2024.

Junsu Kim, Sumin Hong, Chanwoo Kim, Jihyeon Kim, Yihalem Yimolal Tiruneh, Jeongwan On, Jihyun Song, Sunhwa Choi, Seungryul Baek, "Class-wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy", in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, South Korea, 2024.

YunSeong Cho, Chanwoo Kim, Hoseong Cho, Yunhoe Ku, Eunseo Kim, Muhammadjon Boboev, Joonseok Lee, Seungryul Baek, "RMFER: Semi-supervised Contrastive Learning for Facial Expression Recognition with Reaction Mashup Video", in Proc. of IEEE Winter Conf. on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2024 (Oral presentation, 53/2,042≈2.6% Accept ratio).

Junuk Cha, Hansol Lee, Jaewon Kim, Nhat Nguyen Bao Truong, Jae Shin Yoon*, Seungryul Baek*, "3D Reconstruction of Interacting Multi-Person in Clothing from a Single Image", in Proc. of IEEE Winter Conf. on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2024.

Nodirkhuja Khujaev, Tsoy Roman, Seungryul Baek, "AstroYOLO: Learning Astronomy Multi-Tasks in a Single Unified Real-Time Framework", in NeurIPS 2023 Workshop on Machine Learning and Physical Sciences, New Orleans, LA, USA, 2023.

Uyoung Jeong, Seungryul Baek, Hyung Jin Chang, Kwang In Kim, "BoIR: Box-Supervised Instance Representation for Multi Person Pose Estimation", in Proc. of British Machine Vision Conference (BMVC), Aberdeen, UK, 2023.

Hoseong Cho, Chanwoo Kim, Jihyeon Kim, Seongyeong Lee, Elkhan Ismayilzada, Seungryul Baek, "Transformer-based Unified Recognition of Two Hands Manipulating Objects", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023.

Seongyeong Lee, Hansoo Park, Jihyeon Kim, Dong Uk Kim, Muhammadjon Boboev, Seungryul Baek, "Image-free Domain Generalization via CLIP for 3D Hand Pose Estimation", in Proc. of IEEE Winter Conf. on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2023.

Junuk Cha, Muhammad Saqlain, GeonU Kim, Mingyu Shin, Seungryul Baek, "Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement", in Proc. of European Conf. on Computer Vision (ECCV), Tel Aviv, Israel, 2022.

Junuk Cha, Muhammad Saqlain, Donguk Kim, Seungeun Lee, Seongyeong Lee, Seungryul Baek, "Learning 3D Skeletal Representation From Transformer for Action Recognition", in IEEE Access 2022 (IF:3.367).

Muhammad Saqlain, Donguk Kim, Junuk Cha, Changhwa Lee, Seongyeong Lee, Seungryul Baek, "3DMesh-GAR: 3D human body mesh-based method for group activity recognition", in Sensors 2022 (IF:3.576).

Dong Uk Kim, Kwang In Kim, Seungryul Baek, ''End-to-End Detection and Pose Estimation of Two Interacting Hands'', in Proc. of IEEE Int. Conf. on Computer Vision (ICCV), Virtual, 2021.

Junuk Cha, Muhammad Saqlain, Changhwa Lee, Seongyeong Lee, Seungeun Lee, Donguk Kim, Won-Hee Park, Seungryul Baek, "Towards Single 2D Image-level Self-supervision for 3D Human Pose and Shape Estimation", in Journal of Applied Sciences 2021 (IF:2.679).

Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek, Shreyas Hampali, Mahdi Rad, Zhaohui Zhang, Shipeng Xie, Neo Chen, Boshen Zhang, Fu Xiong, Yang Xiao, Zhiguo Cao, Junsong Yuan, Pengfei Ren, Weiting Huang, haifeng sun, Marek Hrúz, Jakub Kanis, Zdeněk Krňoul, Qingfu Wan, Shile Li, Dongheui Lee, Linlin Yang, Angela Yao, Yun-Hui Liu, Adrian Spurr, Pavlo Molchanov, Umar Iqbal, Philippe Weinzaepfel, Romain Brégier, Grégory Rogez, Vincent Lepetit, Tae-Kyun Kim, ''Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction'', in Proc. of European Conf. on Computer Vision (ECCV), Edinburgh, UK, 2020.

Seungryul Baek, Kwang In Kim, Tae-Kyun Kim, "Weakly-supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020 (Oral presentation, 335/5,865≈5.7% Accept ratio).

Binod Bhattarai, Seungryul Baek, Rumeysa Bodur, Tae-Kyun Kim, "Sampling Strategies for GAN Synthetic Data", in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020.

Seungryul Baek, Kwang In Kim, Tae-Kyun Kim, "Pushing the envelope for RGB-based dense 3D hand pose estimation via neural rendering", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019.

Seungryul Baek, Kwang In Kim, Tae-Kyun Kim, "Augmented skeleton space transfer for depth-based hand pose estimation", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 2018 (Oral presentation, 70/3,300≈2.1% Accept ratio).

Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek, Tae-Kyun Kim, "First-person hand action benchmark with RGB-D videos and 3D hand pose annotations", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 2018.

Seungryul Baek, Zhiyuan Shi, Masato Kawade, Tae-Kyun Kim, "Kinematic-layout-aware random forests for depth-based action recognition", in Proc. of British Machine Vision Conference (BMVC), London, UK, 2017 (Oral presentation, 36/635≈5.6% Accept ratio).

Seungryul Baek, Kwang In Kim, Tae-Kyun Kim, "Real-time online action detection forests using spatio-temporal contexts", in Proc. of IEEE Winter Conf. on Applications of Computer Vision (WACV), Santa Rosa, CA, USA, 2017.

Seungryul Baek, Taegyu Lim, Yong Seok Heo, Sungbum Park, Hantak Kwak and Woosung Shim, "Superpixel coherency and uncertainty models for semantic segmentation", in Proc. of IEEE Int. Conf. on Computer Vision (ICCV) workshop on PGMs, Sydney, Australia, 2013.

Seungryul Baek, Chang D. Yoo, Sungrack Yun, "Learning a discriminative visual codebook using homonym scheme", in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, 2011.

Honors and Awards

Best Poster Award at IPIU 2025.

2nd Prize at UNIST AI Challenger Program (AICP) 2024.

1st Place at 8th HANDS workshop challenge - ARCTIC held in ECCV 2024.

Best Paper Award Finalist at WACV 2024.

Special Prize at UNIST AI Challenger Program (AICP) 2023.

Best Paper Award (Encouragement) at Autumn Annual Conference of IEIE 2023.

3rd Place at 7th HANDS workshop challenge - ARCTIC held in ICCV 2023.

Achievement Award at AI Association 2022.

1st Place at HBHA challenge (Egocentric 3D hand pose estimation) held in ECCV 2022.

2nd Place at HBHA challenge (Hand and object pose based action recognition) held in ECCV 2022.

Best Paper Award (Encouragement) at IPIU 2022.

Best Paper Award Nominee at CVPR 2020.

Silver Prize at KIPS (Korea Information Processing Society) 2020 Fall Conference Paper Awards.

Europe Finalist at Qualcomm Innovation Fellowship 2018.

Silver Prize at Samsung Best Paper Awards 2013.