AI Paper Atlas

Research map / Video / Video-language understanding

Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding

Jiaqi Li, Shuntian Zheng, Yixian Shen, JIA-HONG HUANG, Xiaoman Lu, Minzhe Ni, Yu Guan

ECCV 2026 · 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
add semantic budget allocation to random sampling with random selection (ablation)SemVID (Qwen3-VL-4B) · Charades-STA 12.5%mIoU: 41.76 -> 43.26Improved
add semantic token identification to uniform budget (ablation)SemVID (Qwen3-VL-4B) · Charades-STA 12.5%mIoU: 39.80 -> 48.50Improved
combine budget allocation and token identification (ablation)SemVID (Qwen3-VL-4B) · Charades-STA 12.5%mIoU: 48.50 -> 49.89Improved
plug semantic budget allocation into FastVID (ablation)FastVID (Qwen3-VL-4B) · Charades-STA 12.5%mIoU: 35.98 -> 48.88Improved
use query relevance instead of attention for object selection (ablation)SemVID object tokens · Charades-STA 12.5%mIoU: 46.57 -> 49.89Improved
add MMR diversity to object selection (ablation)SemVID object tokens · Charades-STA 12.5%mIoU: 49.44 -> 49.89Improved
add object tokens (alpha 0 -> 0.6) (ablation)SemVID · Charades-STA 12.5%mIoU: 49.48 -> 49.89Improved
add motion tokens (alpha 1.0 -> 0.6) (ablation)SemVID · Charades-STA 12.5%mIoU: 48.11 -> 49.89Improved
add query-aware filtering of motion tokens (ablation)SemVID · Charades-STA 12.5%mIoU: 49.04 -> 49.89Improved
add 3 context tokens (ablation)SemVID · Charades-STA 12.5%mIoU: 49.20 -> 49.89Improved
increase context tokens from 3 to 10 (ablation)SemVID · Charades-STA 12.5%mIoU: 49.89 -> 48.52Hurt
SemVID vs FastVID on Qwen3-VL-4B under 12.5% token budgetSemVID · ActivityNet-GroundingmIoU: 33.16 -> 38.49Improved

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