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.
@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}
}