Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval (EPIC-KITCHENS-100 Challenge 2022)

Published in CVPR 2022, Joint Ego4D/EPIC Workshop (challenge technical report, joint 3rd place), 2022

Burak Satar, Hongyuan Zhu, Hanwang Zhang, Joo-Hwee Lim

Joint 3rd place in the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge at CVPR 2022.

Technical Report (arXiv) Code

BibTeX
@article{DBLP:journals/corr/abs-2206-14381,
  author       = {Burak Satar and
                  Hongyuan Zhu and
                  Hanwang Zhang and
                  Joo Hwee Lim},
  title        = {Exploiting Semantic Role Contextualized Video Features for Multi-Instance
                  Text-Video Retrieval {EPIC-KITCHENS-100} Multi-Instance Retrieval
                  Challenge 2022},
  journal      = {CoRR},
  volume       = {abs/2206.14381},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2206.14381},
  doi          = {10.48550/ARXIV.2206.14381},
  eprinttype   = {arXiv},
  eprint       = {2206.14381},
  timestamp    = {Wed, 15 Oct 2025 07:24:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-14381.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}