AI Paper Atlas

Research map / Video / Video-language understanding

TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding

Chaohong Guo, Xun Mo, Yongwei Nie, Fei Ma, Xuemiao Xu, Chengjiang Long

ECCV 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
add T-anchor reward and anchor reasoning on top of Time-R1 (ablation)Qwen2.5-VL-7B · Charades-STA (fine-tuned)R1@0.7: 47.5 -> 50.2Improved
replace standard IoU reward with soft IoU in Time-R1 (ablation)Time-R1 7B · Charades-STA (fine-tuned)R1@0.7: 47.5 -> 48.1Improved
add SFT cold start on bootstrapped CoT data before GRPO (ablation)TAR 7B · Charades-STA (fine-tuned)R1@0.7: 45.9 -> 50.2Improved
add GRPO after SFT (versus SFT alone) (ablation)TAR 7B · Charades-STA (fine-tuned)R1@0.7: 21.0 -> 50.2Improved
add progressive refinement reward (ablation)TAR reward · Charades-STA (fine-tuned)mIoU: 58.5 -> 61.1Improved
add length penalty TAR_num on anchor count (ablation)TAR reward · Charades-STA (fine-tuned)mIoU: 41.1 -> 61.1Improved
add progressive refinement to sIoU-only reward (ablation)TAR reward · Charades-STA (fine-tuned)mIoU: 39.1 -> 41.1Improved
TAR vs Time-R1 on ActivityNet-Captions zero-shot R1@0.7Qwen2.5-VL-7B · ActivityNet-Captions (zero-shot)R1@0.7: 21.4 -> 19.8Hurt
TAR vs Time-R1 on TVGBench zero-shotQwen2.5-VL-7B · TVGBench (zero-shot)mIoU: 29.2 -> 30.6Mixed
TAR reasoning pattern transferred to zero-shot VQAQwen2.5-VL-7B · VideoMME (zero-shot VQA)accuracy: 53.0 -> 54.9Improved
TAR vs Time-R1 on QVHighlightsQwen2.5-VL-7B · QVHighlights (fine-tuned)mIoU: 59.1 -> 65.9Improved

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