The official repo of "End-to-End Joint Semantic Segmentation of Actors and Actions in Video". This work was presented as an oral talk in ECCV2018. The repository is in progress. Feel free to send any question to jingweij@cs.stanford.edu.
Quick links: [paper] [poster] [slides]
If you find our work is useful for your research, please use the following bibtex to cite our work:
@inproceedings{ji2018end,
title={End-to-end joint semantic segmentation of actors and actions in video},
author={Ji, Jingwei and Buch, Shyamal and Soto, Alvaro and Niebles, Juan Carlos},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
pages={702--717},
year={2018}
}