AI Paper Atlas

Research map / Video / Video-language understanding

VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding

Yue Fan, Xiaojian Ma, Rujie Wu, yuntao du, Jiaqi Li, Zhi Gao, Qing Li

ECCV 2024 · Video › Video-language understanding · approach: Long video understanding · 118 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
add object memory database to the agent (with VQA, grounding, captions) (ablation)VideoAgent · NExT-QA ablation subset (150 questions)average accuracy: 62.7 -> 71.3Improved
add object re-identification to the object memory (ablation)VideoAgent captions + object memory · NExT-QA ablation subset (150 questions)average accuracy: 48.7 -> 56.0Improved
add visual question answering and segment localization tools to caption-only agent (ablation)VideoAgent · NExT-QA ablation subset (150 questions)average accuracy: 40.7 -> 62.7Improved
switch VQA tool from Video-LLaVA to GPT-4V (ablation)VideoAgent · NExT-QA ablation subset (150 questions)average accuracy: 71.3 -> 74.7Improved
use caption-query similarity instead of video-query similarity for segment localization (ablation)VideoAgent segment localization · Ego4D NLQ val (zero-shot)R1@0.3: 8.40 -> 10.07Improved
use higher-quality captions (Ego4D narrations instead of LaViLa) (ablation)VideoAgent segment localization · Ego4D NLQ val (zero-shot)R1@0.3: 10.07 -> 16.41Improved
ensemble textual caption features with ViCLIP visual features for localization (ablation)VideoAgent segment localization · Ego4D NLQ val (zero-shot)R1@0.3: 16.41 -> 17.39Improved
use similarity-based segment localization instead of LLM-based localization (LifeLongMemory)VideoAgent · Ego4D NLQ valR1@0.3 vs R@0.3: 15.99 -> 16.41Improved
wrap Video-LLaVA as a tool inside the agent instead of using it aloneVideo-LLaVA · NExT-QA val subset (600 questions)average accuracy: 53.5 -> 70.8Improved
agent versus GPT-4V on open-ended QAVideoAgent · WorldQA Open-Endedscore: 35.37 (GPT-4V) vs 32.53Hurt
zero-shot agent versus supervised GroundNLQVideoAgent · Ego4D NLQ valR1@0.3: 27.20 vs 17.39Hurt

Later papers that compared with this method

18 later accepted papers report VideoAgent2 as a baseline in their results tables; 16 of them report a better number on most of the results they share with it.

10 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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