CVPR 2026 Open Access Repository

Second Workshop on Skilled Activity Understanding, Assessment & Feedback Generation

Efficient and Intrinsically Interpretable Spatiotemporal Transformer with Gated Fusion for Group Activity Recognition: Narthana Sivalingam,

Santhirarajah Sivasthigan,

Roshan Godaliyadda,

Vijitha Herath,

Parakrama Ekanayake; [pdf]
[bibtex]
@InProceedings{Sivalingam_2026_CVPR, author = {Sivalingam, Narthana and Sivasthigan, Santhirarajah and Godaliyadda, Roshan and Herath, Vijitha and Ekanayake, Parakrama}, title = {Efficient and Intrinsically Interpretable Spatiotemporal Transformer with Gated Fusion for Group Activity Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8912-8920} }
Distance-Aware Attention for Surgical Task Classification with Video Transformers: Jessica Tierney,

Soumee Guha,

Zheyuan Zhang,

Payton Miller,

Noosha Deravi,

Yichuan Yan,

Dimitrios Stefanidis,

Scott Acton,

Fiona Kolbinger; [pdf]
[bibtex]
@InProceedings{Tierney_2026_CVPR, author = {Tierney, Jessica and Guha, Soumee and Zhang, Zheyuan and Miller, Payton and Deravi, Noosha and Yan, Yichuan and Stefanidis, Dimitrios and Acton, Scott and Kolbinger, Fiona}, title = {Distance-Aware Attention for Surgical Task Classification with Video Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8941-8950} }
Behavior-Based Skill Assessment for Open Surgery from Multi-View and Egocentric Videos: Qiaomu Miao,

Jonathan Price,

Apostolos Tassiopoulos,

Dimitris Samaras; [pdf] [supp]
[bibtex]
@InProceedings{Miao_2026_CVPR, author = {Miao, Qiaomu and Price, Jonathan and Tassiopoulos, Apostolos and Samaras, Dimitris}, title = {Behavior-Based Skill Assessment for Open Surgery from Multi-View and Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8854-8864} }
Combining Boundary Supervision and Segment-Level Regularization for Fine-Grained Action Segmentation: Hinako Mitsuoka,

Kazuhiro Hotta; [pdf] [arXiv]
[bibtex]
@InProceedings{Mitsuoka_2026_CVPR, author = {Mitsuoka, Hinako and Hotta, Kazuhiro}, title = {Combining Boundary Supervision and Segment-Level Regularization for Fine-Grained Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8865-8873} }
DiagHOI: A Diagnostic Benchmark for Human-Object Interaction Detection: Lemeng Wang,

Qinqian Lei,

Vidhi Bakshi,

Daniel Yi,

Yifan Liu,

Jiacheng Hou,

Asher Seng Hao,

Zheda Mai,

Wei-Lun Chao,

Robby T. Tan,

Bo Wang; [pdf]
[bibtex]
@InProceedings{Wang_2026_CVPR, author = {Wang, Lemeng and Lei, Qinqian and Bakshi, Vidhi and Yi, Daniel and Liu, Yifan and Hou, Jiacheng and Hao, Asher Seng and Mai, Zheda and Chao, Wei-Lun and Tan, Robby T. and Wang, Bo}, title = {DiagHOI: A Diagnostic Benchmark for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8951-8960} }
Learning Coach's Tactics: Skill-aware Readiness Modeling for Interactive Badminton Training: Tzu-Yu Sung,

Wang-Lin Tsai,

Cheng-Kuan Lin,

Yu-Chee Tseng; [pdf]
[bibtex]
@InProceedings{Sung_2026_CVPR, author = {Sung, Tzu-Yu and Tsai, Wang-Lin and Lin, Cheng-Kuan and Tseng, Yu-Chee}, title = {Learning Coach's Tactics: Skill-aware Readiness Modeling for Interactive Badminton Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8921-8930} }
Can Vision Language Models Judge Action Quality? An Empirical Evaluation: Miguel Monte e Freitas,

Rui Henriques,

Ricardo Rei,

Pedro Henrique Martins; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{e_Freitas_2026_CVPR, author = {e Freitas, Miguel Monte and Henriques, Rui and Rei, Ricardo and Martins, Pedro Henrique}, title = {Can Vision Language Models Judge Action Quality? An Empirical Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8874-8883} }
EgoIndAssembly: Diagnosing Fine-Grained Temporal Hand Reasoning in Vision-Language Models for Skilled Assembly: Tatsuya Sasaki; [pdf]
[bibtex]
@InProceedings{Sasaki_2026_CVPR, author = {Sasaki, Tatsuya}, title = {EgoIndAssembly: Diagnosing Fine-Grained Temporal Hand Reasoning in Vision-Language Models for Skilled Assembly}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8894-8902} }
Sports Form Anomaly Detection Using Skeleton-PatchCore: Seiya Shirai,

Kazuhiro Hotta; [pdf]
[bibtex]
@InProceedings{Shirai_2026_CVPR, author = {Shirai, Seiya and Hotta, Kazuhiro}, title = {Sports Form Anomaly Detection Using Skeleton-PatchCore}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8903-8911} }
DUAL-Pose: Efficient Dual-Branch Graph Networks for Skeleton-Based Yoga Pose Recognition: Rashi Niyas P,

Hitika Tiwari,

Tushar Shinde; [pdf]
[bibtex]
@InProceedings{P_2026_CVPR, author = {P, Rashi Niyas and Tiwari, Hitika and Shinde, Tushar}, title = {DUAL-Pose: Efficient Dual-Branch Graph Networks for Skeleton-Based Yoga Pose Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8884-8893} }
Structured Relational Reasoning for Group Activity Assessment: Thinesh Thiyakesan Ponbagavathi,

Chengzheng Yang,

Alina Roitberg; [pdf]
[bibtex]
@InProceedings{Ponbagavathi_2026_CVPR, author = {Ponbagavathi, Thinesh Thiyakesan and Yang, Chengzheng and Roitberg, Alina}, title = {Structured Relational Reasoning for Group Activity Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8931-8940} }