AI Paper Atlas

Research map / Video / Video-language understanding

MovieChat+: Question-Aware Sparse Memory for Long Video Question Answering

Enxin Song, Wenhao Chai, Ye Tian, Jenq–Neng Hwang, Xi Li, Gaoang Wang

TPAMI 2025 · Video › Video-language understanding · approach: Video question answering · 80 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 question-aware memory consolidation (MovieChat+ over MovieChat)MovieChat · MovieChat-1K globalaccuracy: 62.3 -> 71.2Improved
add question-aware memory consolidationMovieChat · MovieChat-1K breakpointaccuracy: 48.3 -> 49.6Improved
add question-aware consolidationMovieChat · MSVD-QAaccuracy: 75.2 -> 76.5No clear effect
add question-aware consolidationMovieChat · EgoSchemaaccuracy: 53.5 -> 56.4Improved
add memory mechanism (ablation)MovieChat · MovieChat-1K globalaccuracy: 51.4 -> 67.8Improved
add memory mechanism (ablation)MovieChat · MovieChat-1K breakpointaccuracy: 38.2 -> 50.4Improved
replace LLaMA with LLaMA2 decoder (ablation)MovieChat · MovieChat-1K globalaccuracy: 67.8 -> 64.2Hurt
replace LLaMA with LLaMA2 decoder (ablation)MovieChat · MovieChat-1K breakpointaccuracy: 50.4 -> 48.1Hurt
use more input frames with spatial pooling (ablation)Spatial Pooling · ActivityNet CIDErCIDEr: 27.6 -> 27.4No clear effect
use more input frames with EMA (ablation)EMA · ActivityNet CIDErCIDEr: 28.2 -> 16.3Hurt
use more frames with proposed memory (ablation)MovieChat memory · ActivityNet CIDErCIDEr: 29.3 -> 29.3No clear effect
judge relevance by maximum rather than average similarity (ablation)MovieChat+ · MovieChat-1KaccuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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