AI Paper Atlas

Research map / Video / Video-language understanding

ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos

Peijun Bao, Anwei Luo, Gang Pan, Alex C. Kot, Xudong Jiang

CVPR 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
add TADiff to ActionFormerTADiff / ActionFormer · ActivityForensics intra-domainavg AP: 70.67 -> 75.05 (+4.38)Improved
add TADiff to ActionFormerTADiff / ActionFormer · ActivityForensics intra-domainavg AR: 74.31 -> 77.15 (+2.84)Improved
add TADiff to ActionFormerTADiff / ActionFormer · ActivityForensics intra-domainAP@0.95: +9.78Improved
add TADiff to ActionFormerTADiff / ActionFormer · ActivityForensics open-world (Vidu)avg AP: 77.82 -> 83.64 (+5.82)Improved
add TADiff to ActionFormerTADiff / ActionFormer · ActivityForensics open-world (Vidu)AP@0.95: +11.98Improved
add TADiff to ActionFormerTADiff / ActionFormer · ActivityForensics cross-domain A->Bavg AP: 67.18 -> 69.63 (+2.45)Improved
add TADiff to ActionFormerTADiff / ActionFormer · ActivityForensics cross-domain B->Aavg AP: +3.75Improved
add noise injection alone (ablation)TADiff / ActionFormer · ActivityForensics intra-domainavg AP: 70.67 -> 70.38Hurt
add noise injection alone (ablation)TADiff / ActionFormer · ActivityForensics open-world (Vidu)avg AP: 77.82 -> 79.75 (+1.93)Improved
add denoising alone (ablation)TADiff / ActionFormer · ActivityForensics intra-domainavg AP: 70.67 -> 73.52Improved
add denoising alone (ablation)TADiff / ActionFormer · ActivityForensics open-world (Vidu)avg AP: 77.82 -> 80.10Improved
combine noise injection with denoising (full TADiff) (ablation)TADiff / ActionFormer · ActivityForensics intra-domainavg AP: 73.52 -> 75.05Improved

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