AI Paper Atlas

Research map / Video / Video-language understanding

A Training-Free Framework for Long Video Understanding via Video-Query-Options Similarity

Zhirong Wu, Xiaodong Wang, Langling Huang, Teng Xu, Peixi Peng

ICLR 2026 · Video › Video-language understanding · approach: Long video understanding

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 top-N frames retrieval (ablation)LLaVA-Video-7B / Qwen2.5-VL-7B · 5 benchmarks (Table 2)avg gain: +4.3 and +2.0Improved
add top-k segments uniform sampling (ablation)LLaVA-Video-7B / Qwen2.5-VL-7B · 5 benchmarks (Table 2)avg gain: +0.2 and +0.0No clear effect
add adaptive frame sampling (AFS) (ablation)LLaVA-Video-7B / Qwen2.5-VL-7B · 5 benchmarks (Table 2)avg gain: +0.7 and +0.8Improved
add dynamic resolution allocation (DRA) (ablation)Qwen2.5-VL-7B · 5 benchmarks (Table 2)avg gain: +2.1Improved
add generated options for similarity (ablation)LLaVA-Video-7B / Qwen2.5-VL-7B · 5 benchmarks (Table 2)avg gain: +0.7 and +0.4Improved
add provided multiple-choice options for similarity (ablation)LLaVA-Video-7B / Qwen2.5-VL-7B · 5 benchmarks (Table 2)avg gain: +1.5 and +1.2Improved
use larger PE-G/14 retriever instead of CLIP-B/32 (ablation)Ours · LVBenchaccuracy: 49.8 -> 54.2Improved
use 8s segments instead of single images (length 0) (ablation)Ours LLaVA-Video-7B · LVBenchaccuracy: 51.4 -> 54.2Improved
use 64s segments instead of 8s (ablation)Ours LLaVA-Video-7B · LVBenchaccuracy: 54.2 -> 47.4Hurt
generate options for 3 rounds instead of question only (ablation)Ours LLaVA-Video-7B · LVBenchaccuracy: 50.2 -> 51.3Improved
generate options for 4 rounds instead of 3 (ablation)Ours LLaVA-Video-7B · VideoEval-Pro MCQaccuracy: 55.3% -> 55.1%Hurt
increase option-generation rounds from 1 to 4 (ablation)Ours LLaVA-Video-7B · VideoEval-ProOCA: 54.6% -> 63.8%Improved

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