Semantic Role Aware Correlation Transformer for Text to Video Retrieval

Published in IEEE ICIP 2021 (oral); also presented at the ICCV 2021 SRVU Workshop (oral), 2021

Burak Satar, Hongyuan Zhu, Xavier Bresson, Joo-Hwee Lim

Aligns semantic roles between text and video with a correlation transformer for retrieval.

Paper (IEEE) arXiv Code Talk Recording

Semantic Role Aware Correlation Transformer for Text to Video Retrieval figure

BibTeX
@inproceedings{DBLP:conf/icip/SatarZBL21,
  author       = {Burak Satar and
                  Hongyuan Zhu and
                  Xavier Bresson and
                  Joo Hwee Lim},
  title        = {Semantic Role Aware Correlation Transformer For Text To Video Retrieval},
  booktitle    = {2021 {IEEE} International Conference on Image Processing, {ICIP} 2021,
                  Anchorage, AK, USA, September 19-22, 2021},
  pages        = {1334--1338},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICIP42928.2021.9506267},
  doi          = {10.1109/ICIP42928.2021.9506267},
  timestamp    = {Wed, 15 Oct 2025 07:24:03 +0200},
  biburl       = {https://dblp.org/rec/conf/icip/SatarZBL21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}