AI Paper Atlas

Research map / Video / Video-language understanding

From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment

Yucheng Suo, Fan Ma, Linchao Zhu, Tianyi Wang, Fengyun Rao, Yi Yang

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 9 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 marginal confidence score S^mc to frequency score (ablation)Llava-Video-7B · MLVUaccuracy: 69.37 -> 71.17Improved
add voting score S^v on top of S^f and S^mc (ablation)Llava-Video-7B · Video-MMEaccuracy: 64.48 -> 66.52Improved
add marginal confidence score S^mc to frequency score (ablation)VideoLLaMA2-7B · Video-MMEaccuracy: 49.11 -> 49.81Improved
add voting score S^v on top of S^f and S^mc (ablation)VideoLLaMA2-7B · MLVUaccuracy: 53.98 -> 55.31Improved
use Deepseek-R1 instead of Llama-3.3-70B as external LLM (ablation)Llava-Video-7B · Video-MMEaccuracy: 66.30 -> 66.52Improved
use marginal confidence instead of max logit (intra-sample) (ablation)Llava-Video-7B · Video-MMEaccuracy: 66.26 -> 66.52Improved
use max instead of mean across samples (inter-sample) (ablation)Llava-Video-7B · Video-MMEaccuracy: 66.22 -> 66.52Improved
reduce frames per sample from 32 to 8 (ablation)Llava-Video-7B · Video-MMEaccuracy: 66.52 -> 62.48Hurt
method gain over baseline at 8 frames (ablation)Llava-Video-7B · Video-MME (8 frames)accuracy: 56.26 -> 62.48Improved
method gain over baseline at 16 frames (ablation)Llava-Video-7B · Video-MME (16 frames)accuracy: 60.18 -> 63.45Improved
bin-wise instead of fully random frame sampling (ablation)Llava-Video-7B · Video-MMEmajority accuracy: +2%Improved
use 32 instead of 8 frames per sample for majority voting (ablation)Llava-Video-7B · Video-MMEmajority accuracy: over 5%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