Gueter Josmy Faure

Taipei City, Taiwan

I am a Software Engineer at Google and a PhD Student in Computer Science at National Taiwan University, advised by Prof. Winston Hsu. Previously, I was a Senior Computer Vision Engineer at HTC. Prior to that, I earned my Master’s Degree from National Tsing Hua University and my Bachelor’s from National Yang Ming Chiao Tung University, both in Computer Science.

My research focuses on teaching AI systems to see and understand human actions in videos.

My work is about building AI systems that understand human movements, poses and interactions.

news

May 19, 2026	FineBench accepted to the CVPR Workshop on Video Large Language Models (VidLLMs 2026)! 🎉
Aug 21, 2025	Our paper MovieCORE: Cognitive Reasoning in Movies is accepted for publication at EMNLP-2025 Main Conference as *Oral* 🚀.
Jun 26, 2025	Our paper HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics is accepted for publication at ICCV-2025 🚀.

latest posts

May 10, 2026	31
Apr 24, 2026	Turning 31
Mar 20, 2026	My Double Life: The last mile

selected publications

EMNLP

MovieCORE: COgnitive REasoning in Movies

Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Ying Cheng, Hung-Ting Su, Yung-Hao Tang, Shang-Hong Lai, and Winston H. Hsu

2025

Bib HTML

@misc{faure2025moviecorecognitivereasoningmovies,
  title = {MovieCORE: COgnitive REasoning in Movies},
  author = {Faure, Gueter Josmy and Chen, Min-Hung and Yeh, Jia-Fong and Cheng, Ying and Su, Hung-Ting and Tang, Yung-Hao and Lai, Shang-Hong and Hsu, Winston H.},
  year = {2025},
  eprint = {2508.19026},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  url = {https://arxiv.org/abs/2508.19026},
}

ICCV

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

Gueter Josmy Faure, Jia-Fong Yeh, Min-Hung Chen, Hung-Ting Su, Shang-Hong Lai, and Winston H. Hsu

2025

Bib HTML

@misc{faure2024hermestemporalcoherentlongformunderstanding,
  title = {HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics},
  author = {Faure, Gueter Josmy and Yeh, Jia-Fong and Chen, Min-Hung and Su, Hung-Ting and Lai, Shang-Hong and Hsu, Winston H.},
  year = {2025},
  eprint = {2408.17443},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://joslefaure.github.io/assets/html/hermes.html},
}

ECCVW

Bridging Episodes and Semantics: A Novel Framework for Long-Form Video Understanding

Gueter Josmy Faure, Jia-Fong Yeh, Min-Hung Chen, Hung-Ting Su, Winston H. Hsu, and Shang-Hong Lai

2024

Bib HTML

@misc{faure2024bridgingepisodessemanticsnovel,
  title = {Bridging Episodes and Semantics: A Novel Framework for Long-Form Video Understanding},
  author = {Faure, Gueter Josmy and Yeh, Jia-Fong and Chen, Min-Hung and Su, Hung-Ting and Hsu, Winston H. and Lai, Shang-Hong},
  year = {2024},
  eprint = {2408.17443},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://joslefaure.github.io/assets/html/hermes.html},
}

NeurIPS-W

MovieCORE: COgnitive REasoning in Movies

Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh, Ying Cheng, Hung-Ting Su, Shang-Hong Lai, and Winston H Hsu

In The First Workshop on System-2 Reasoning at Scale, NeurIPS-24 , 2024

Bib HTML

@inproceedings{faure2moviecore,
  title = {MovieCORE: COgnitive REasoning in Movies},
  author = {Faure, Gueter Josmy and Chen, Min-Hung and Yeh, Jia-Fong and Cheng, Ying and Su, Hung-Ting and Lai, Shang-Hong and Hsu, Winston H},
  booktitle = {The First Workshop on System-2 Reasoning at Scale, NeurIPS-24},
  year = {2024},
  url = {https://joslefaure.github.io/assets/html/moviecore.html},
}

WACV

Holistic interaction transformer network for action detection

Gueter Josmy Faure, Min-Hung Chen, and Shang-Hong Lai

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , 2023

Bib HTML

@inproceedings{faure2023holistic,
  title = {Holistic interaction transformer network for action detection},
  author = {Faure, Gueter Josmy and Chen, Min-Hung and Lai, Shang-Hong},
  booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  pages = {3340--3350},
  year = {2023},
  google_scholar_id = {iH-uZ7U-co4C},
}

ICCVW

Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection

Wei-Jhe Huang, Jheng-Hsien Yeh, Min-Hung Chen, Gueter Josmy Faure, and Shang-Hong Lai

In Proceedings of the IEEE/CVF International Conference on Computer Vision , 2023

Bib HTML

@inproceedings{huang2023interaction,
  title = {Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection},
  author = {Huang, Wei-Jhe and Yeh, Jheng-Hsien and Chen, Min-Hung and Faure, Gueter Josmy and Lai, Shang-Hong},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {284--293},
  year = {2023},
}

ACPR

Confidence-aware anomaly detection in human actions

Tsung-Hsuan Wu, Chun-Lung Yang, Li-Ling Chiu, Ting-Wei Wang, Gueter Josmy Faure, and Shang-Hong Lai

In Asian Conference on Pattern Recognition , 2021

Bib HTML

@inproceedings{wu2021confidence,
  title = {Confidence-aware anomaly detection in human actions},
  author = {Wu, Tsung-Hsuan and Yang, Chun-Lung and Chiu, Li-Ling and Wang, Ting-Wei and Faure, Gueter Josmy and Lai, Shang-Hong},
  booktitle = {Asian Conference on Pattern Recognition},
  pages = {240--254},
  year = {2021},
  organization = {Springer},
}

CVPR Workshop

FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding

2026

CVPR’26 Workshop

Bib HTML

@misc{faure2026finebench,
  title = {FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding},
  author = {},
  year = {2026},
  note = {CVPR'26 Workshop},
}