Workshop on AI-driven Skilled Activity Understanding, Assessment & Feedback Generation


EHWGesture - A dataset for multimodal understanding of clinical gestures
Gianluca Amprimo,
Alberto Ancilotto,
Alessandro Savino,
Fabio Quazzolo,
Claudia Ferraris,
Gabriella Olmo,
Elisabetta Farella,
Stefano Di Carlo
[pdf] [supp]
[bibtex]
@InProceedings{Amprimo_2025_ICCV, author = {Amprimo, Gianluca and Ancilotto, Alberto and Savino, Alessandro and Quazzolo, Fabio and Ferraris, Claudia and Olmo, Gabriella and Farella, Elisabetta and Di Carlo, Stefano}, title = {EHWGesture - A dataset for multimodal understanding of clinical gestures}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2701-2710} }

Learning Robust Aligned Representations Across Multiple Visual Modalities in Human Action Recognition
David Lerch,
Bastian Rothenburger,
Zeyun Zhong,
Manuel Martin,
Frederik Diederichs,
Rainer Stiefelhagen
[pdf]
[bibtex]
@InProceedings{Lerch_2025_ICCV, author = {Lerch, David and Rothenburger, Bastian and Zhong, Zeyun and Martin, Manuel and Diederichs, Frederik and Stiefelhagen, Rainer}, title = {Learning Robust Aligned Representations Across Multiple Visual Modalities in Human Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2679-2689} }

EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
Ivan Rodin,
Tz-Ying Wu,
Kyle Min,
Sharath Nittur Sridhar,
Antonino Furnari,
Subarna Tripathi,
Giovanni Maria Farinella
[pdf]
[bibtex]
@InProceedings{Rodin_2025_ICCV, author = {Rodin, Ivan and Wu, Tz-Ying and Min, Kyle and Sridhar, Sharath Nittur and Furnari, Antonino and Tripathi, Subarna and Farinella, Giovanni Maria}, title = {EASG-Bench: Video Q\&A Benchmark with Egocentric Action Scene Graphs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2711-2716} }

EgoOops: A Dataset for Mistake Action Detection from Egocentric Videos referring to Procedural Texts
Yuto Haneji,
Taichi Nishimura,
Hirotaka Kameko,
Keisuke Shirai,
Tomoya Yoshida,
Keiya Kajimura,
Koki Yamamoto,
Taiyu Cui,
Tomohiro Nishimoto,
Shinsuke Mori
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Haneji_2025_ICCV, author = {Haneji, Yuto and Nishimura, Taichi and Kameko, Hirotaka and Shirai, Keisuke and Yoshida, Tomoya and Kajimura, Keiya and Yamamoto, Koki and Cui, Taiyu and Nishimoto, Tomohiro and Mori, Shinsuke}, title = {EgoOops: A Dataset for Mistake Action Detection from Egocentric Videos referring to Procedural Texts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2690-2700} }

CricTAL: Introducing Temporal Activity Localisation using pose estimation to identify key phases in cricket batting for downstream Action Quality Assessment
Tevin Moodley,
Dustin van der Haar
[pdf]
[bibtex]
@InProceedings{Moodley_2025_ICCV, author = {Moodley, Tevin and van der Haar, Dustin}, title = {CricTAL: Introducing Temporal Activity Localisation using pose estimation to identify key phases in cricket batting for downstream Action Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2717-2725} }

InstaPose: Scene-Aware Pose Recommendation via Vision Transformers and Diversity-Optimized Reranking
Yu Ji,
I-Han Hsiao
[pdf]
[bibtex]
@InProceedings{Ji_2025_ICCV, author = {Ji, Yu and Hsiao, I-Han}, title = {InstaPose: Scene-Aware Pose Recommendation via Vision Transformers and Diversity-Optimized Reranking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2726-2732} }

Assessing the Quality of Soccer Shots from Single-Camera Video with Vision-Language Models and Motion Features
Filip Noworolnik,
Joanna Jaworek-Korjakowska
[pdf]
[bibtex]
@InProceedings{Noworolnik_2025_ICCV, author = {Noworolnik, Filip and Jaworek-Korjakowska, Joanna}, title = {Assessing the Quality of Soccer Shots from Single-Camera Video with Vision-Language Models and Motion Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2733-2740} }