AI Paper Atlas

Research map / Video / Video-language understanding

Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding

Jialuo Li, Bin Li, Jiahao Li, Yan Lu

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding · 8 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 DIG query-adaptive frame selection instead of uniform samplingQwen2.5-VL-7B · MLVU (32 frames)accuracy: 59.52 -> 67.20Improved
use DIG instead of uniform samplingQwen2.5-VL-7B · LongVideoBench (32 frames)accuracy: 56.92 -> 60.43Improved
use DIG instead of uniform samplingQwen2.5-VL-32B · MLVU (128 frames)accuracy: 70.24 -> 75.20Improved
use DIG instead of uniform samplingQwen2.5-VL-7B · VideoMME (long, 256 frames)accuracy: 57.12 -> 57.76No clear effect
use AKS instead of uniform sampling at high frame countsQwen2.5-VL-7B · LongVideoBench (128 frames)accuracy: 61.86 -> 60.36Hurt
use Q-Frame instead of uniform samplingQwen2.5-VL-32B · MLVU (32 frames)accuracy: 61.91 -> 60.95Hurt
increase uniformly sampled input frames beyond an optimum (ablation)Qwen2.5-VL-7B, InternVL3-8B, LLaVA-OneVision-7B · MLVU, VideoMME, LongVideoBenchaccuracyHurt
replace CLIPScore with LMM (Qwen2.5-VL-7B) reward scoring (ablation)DIG · MLVU (128 frames)accuracy: 69.6 -> 71.4Improved
replace CLIPScore with LMM reward scoring (ablation)DIG · VideoMME (long, 8 frames)accuracy: 49.0 -> 46.9Hurt
use Qwen2.5-VL-32B instead of 7B as reward model (ablation)DIG · VideoMME (medium, 128 frames)accuracy: 66.8 -> 69.2Improved
set window length wlen=0 instead of 2 (ablation)DIG · MLVU, LongVideoBench, VideoMMEaccuracyHurt
increase window length from 2 to 8 (ablation)DIG · MLVU, LongVideoBench, VideoMMEaccuracyHurt

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