AI Paper Atlas

Research map / Video / Video-language understanding

VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization

Xinye Cao, Hongcan Guo, Jiawen Qian, Guoshun Nan, Chao Wang, Yuqi Pan, Tianhao Hou, Xiaojuan Wang, Yutong Gao

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 5 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
plug VideoMiner key-frame tree into Qwen2-VL-7BQwen2-VL · EgoSchemaaccuracy: 50.0 -> 66.2Improved
plug VideoMiner key-frame tree into Qwen2-VL-7BQwen2-VL · LongVideoBench (900-3600s)accuracy: 38.0 -> 49.3Improved
plug VideoMiner key-frame tree into Qwen2-VL-7BQwen2-VL · Video-MME (long)accuracy: 45.8 -> 52.2Improved
plug VideoMiner key-frame tree into Qwen2-VL-7BQwen2-VL · MLVU M-Avgaccuracy: 60.1 -> 65.1Improved
plug VideoMiner into Qwen2-VL-7B on short videosQwen2-VL · LongVideoBench (8-15s)accuracy: 68.8 -> 65.1Hurt
add event clustering instead of frame clustering (ablation)VideoMiner · long-video benchmarksaccuracyImproved
add clustering instead of no clustering (ablation)VideoMiner · long-video benchmarksaccuracyImproved
train policy with T-GRPO instead of other RL methods (ablation)VideoMiner · three long-video benchmarksaccuracyImproved
add RL training to the policy model (ablation)VideoMiner · long-video benchmarksaccuracyImproved
increase response length from 20 to 400 tokens (ablation)VideoMiner T-GRPO · three long-video benchmarksaccuracy: 20 -> 400 tokens, accuracy improved by over 10%Improved
set tree growth rate below 1 (ablation)VideoMiner T-GRPO · long-video benchmarksaccuracyHurt
lower growth rate toward more continue actions (ablation)VideoMiner T-GRPO · long-video benchmarksaccuracyMixed

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