AI Paper Atlas

Research map / Video / Video-language understanding

Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

Yue Feng, Jingjing Li, Qijia Lu, Wei Ji, Jingrou Zhang, Fei Shen, Xiao Li, Yizhen Jia, Qiang Chen, Limin Wang, Wentong Li, Jie Qin

ICML 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 0 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
fine-tune on TASLEBusterX++ · TASLE in-domainF1Det: 8.3 -> 33.6Improved
use four-class boundary-aware labels instead of binary real/fake (ablation)DeMamba · TASLE in-domainF1Det: 54.9 -> 67.5Improved
add MSLoc-PG proposals before Trace (ablation)Trace · TASLE in-domainF1Loc: 41.4 -> 70.9Improved
use DeMamba proposals instead of none for Trace (ablation)Trace · TASLE in-domainF1Loc: 41.4 -> 59.1Improved
add boundary-focused MSLoc-PR refinement over Trace w. MSLoc-PG (ablation)MSLoc · TASLE in-domainF1Loc: 70.9 -> 72.2Improved
add MLLM refinement over MSLoc-PG on out-of-domain data (ablation)MSLoc · TASLE out-of-domainF1Det / F1Loc: +7.8 F1Det, +17.6 F1LocImproved
add DAM (boundary dense sampling) to backbone (ablation)MSLoc-PR · TASLE testF1Loc / RQ: F1Loc 62.3 -> 63.0; RQ 3.77 -> 3.56Mixed
add EAM on top of DAM (ablation)MSLoc-PR · TASLE testRQ: 3.56 -> 3.79Improved
add anomaly-aware loss LAA (ablation)MSLoc-PR · TASLE testRQ: 3.79 -> 3.99Improved
reduce boundary frames from 16 to 8 (ablation)MSLoc-PR · TASLE testF1Det / F1Loc / RQ: 64.0 -> 63.2 F1Det; 63.8 -> 63.0 F1LocHurt
widen boundary region phi from 10% to 30% (ablation)MSLoc-PR · TASLE testRQ: 3.80 -> 4.01Improved
widen boundary region phi to 30% for localization (ablation)MSLoc-PR · TASLE testF1Loc: 64.0 -> 63.7No clear effect

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