AI Paper Atlas

Research map / Video / Video-language understanding

VideoAgent: Long-form Video Understanding with Large Language Model as Agent

Xiaohan Wang, Yuhui Zhang, Orr Zohar, Serena Yeung-Levy

ECCV 2024 · Video › Video-language understanding · approach: Long video understanding · 196 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use iterative frame selection instead of uniform sampling of 180 frames (ablation)VideoAgent · EgoSchema (500-question subset)accuracy: 59.6% -> 60.2% with 8.4 vs 180 framesImproved
increase iterative rounds from 1 to 3 (ablation)VideoAgent · EgoSchema (500-question subset)accuracy: 53.8% -> 58.6% -> 60.2%Improved
increase rounds from 3 to 4 (ablation)VideoAgent · EgoSchema (500-question subset)accuracy: 60.2% -> 59.8%No clear effect
use 5 initial frames rather than 3 or 8 (ablation)VideoAgent · EgoSchema (500-question subset)accuracy: 58.4% / 57.4% -> 60.2%Improved
add self-evaluation to stop iteration early (ablation)VideoAgent · EgoSchema (500-question subset)accuracy and frames: 59.6% -> 60.2%; frames 11.8 -> 8.4Improved
add segment selection when generating retrieval queries (ablation)VideoAgent · EgoSchema (500-question subset)accuracy: +3.6%Improved
use GPT-4 as the agent LLM instead of LLaMA-2-70B, Mixtral-8x7B or GPT-3.5VideoAgent · EgoSchema (500-question subset)accuracyImproved
use CogAgent or LaViLa captions instead of BLIP-2 captionsVideoAgent · EgoSchema (500-question subset)accuracyImproved
swap among OpenCLIP ViT-G, EVA-CLIP-8B, EVA-CLIP-8B-plus for retrievalVideoAgent · EgoSchema (500-question subset)accuracyNo clear effect
replace LLoVi with VideoAgentzero-shot long-video QA · NExT-QA (val)Acc@All: 67.7 -> 71.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy