SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.12679 · ECCV · 2024

Goldfish: Vision-Language Understanding of Arbitrarily Long Videos

Mohamed Elhoseiny, Jürgen Schmidhuber, Eslam Abdelrahman, Mingchen Zhuge, Xiaoqian Shen, Deyao Zhu, Jian Ding, Essam Sleiman, Kirolos Ataallah

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Most current LLM-based models for video understanding can process videos within minutes. However, they struggle with lengthy videos due to challenges such as "noise and redundancy", as well as "memory and computation" constraints. In this paper, we present Goldfish, a methodology tailored for comprehending videos of arbitrary lengths. We also introduce the TVQA-long benchmark, specifically designed to evaluate models' capabilities in understanding long videos with questions in both vision and text content. Goldfish approaches these challenges with an efficient retrieval mechanism that initially gathers the top-k video clips relevant to the instruction before proceeding to provide the desired response. This design of the retrieval mechanism enables the Goldfish to efficiently process arbitrarily long video sequences, facilitating its application in contexts such as movies or television series. To facilitate the retrieval process, we developed MiniGPT4-Video that generates detailed descriptions for the video clips. In addressing the scarcity of benchmarks for long video evaluation, we adapted the TVQA short video benchmark for extended content analysis by aggregating questions from entire episodes, thereby shifting the evaluation from partial to full episode comprehension. We attained a 41.78% accuracy rate on the TVQA-long benchmark, surpassing previous methods by 14.94%. Our MiniGPT4-Video also shows exceptional performance in short video comprehension, exceeding existing state-of-the-art methods by 3.23%, 2.03%, 16.5% and 23.59% on the MSVD, MSRVTT, TGIF,and TVQA short video benchmarks, respectively. These results indicate that our models have significant improvements in both long and short-video understanding.Our models and code have been made publicly available Goldfish.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.12679")
get_code_for_paper("2407.12679")
have("2407.12679")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.12679.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.12679.svg)](https://syntology.ai/paper/2407.12679)

Connect an agent — have() is free.