AI Paper Atlas

Research map / Video / Video-language understanding

TargetVAU: Multimodal Anomaly-Aware Reasoning for Target Behavior Understanding in Videos

Lingru Zhou, Peng Wu, Manqing Zhang, Qingsheng Wang, Guansong Pang, Peng Wang

AAAI 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 2 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 Anomaly-focused Temporal Sampler (vs uniform sampling) (ablation)TargetVAU · UCCDCIDEr: 0.591 -> 0.665Improved
add Anomaly-focused Temporal Sampler (ablation)TargetVAU · UCCDBLEU: 0.509 -> 0.582Improved
add frozen Q-Former fusion (vs linear projection) (ablation)TargetVAU · UCCDCIDEr: 0.603 -> 0.665Improved
add Q-Former fusion (ablation)TargetVAU · UCCDBLEU: 0.521 -> 0.582Improved
add Spatio-Temporal Interaction Graph (ablation)TargetVAU · UCCDBLEU/CIDErImproved
add global features to human-centric features (ablation)TargetVAU · UCCDBLEU/CIDErImproved
raise anomaly detection loss weight (2:1:1 vs 1:1:2) (ablation)TargetVAU · UCCDCIDEr: 0.665 -> 0.641Hurt
raise contrastive loss weight (1:2:1 vs 1:1:2) (ablation)TargetVAU · UCCDCIDEr: 0.665 -> 0.649Hurt
raise caption loss weight to 2 (vs equal weights) (ablation)TargetVAU · UCCDCIDEr: 0.658 -> 0.665Improved
TargetVAU vs Holmes-VAU zero-shotTargetVAU · HIVAU-70KCIDEr: 1.437 -> 1.424Hurt
TargetVAU vs Holmes-VAU zero-shotTargetVAU · HIVAU-70KParaScore: 0.909 -> 0.901Hurt
TargetVAU vs Holmes-VAU for detectionTargetVAU · UCF-CrimeAUC (%): 88.96 -> 89.57Improved

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