English

Text-Conditioned Resampler For Long Form Video Understanding

Computer Vision and Pattern Recognition 2024-08-20 v3

Abstract

In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time with plain attention and without optimised implementations. We make the following contributions: (i) we design a transformer-based sampling architecture that can process long videos conditioned on a task, together with a training method that enables it to bridge pre-trained visual and language models; (ii) we identify tasks that could benefit from longer video perception; and (iii) we empirically validate its efficacy on a wide variety of evaluation tasks including NextQA, EgoSchema, and the EGO4D-LTA challenge.

Keywords

Cite

@article{arxiv.2312.11897,
  title  = {Text-Conditioned Resampler For Long Form Video Understanding},
  author = {Bruno Korbar and Yongqin Xian and Alessio Tonioni and Andrew Zisserman and Federico Tombari},
  journal= {arXiv preprint arXiv:2312.11897},
  year   = {2024}
}

Comments

Accepted to the ECCV24 conference

R2 v1 2026-06-28T13:55:41.370Z