AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Event-Relevant Factors for Video Anomaly Detection

Che Sun, Chenrui Shi, Yunde Jia, Yuwei Wu

AAAI 2023 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 13 citations (OpenAlex)

Read the paper

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 event-relevant factor learning and counterfactual finetuning to HF2-VADHF2-VAD · ShanghaiTech, Setting-AAUROC: 76.2 -> 78.6Improved
Add event-relevant factor learning and counterfactual finetuning to HF2-VADHF2-VAD · CUHK Avenue, Setting-AAUROC: 91.1 -> 91.5Improved
Add event-relevant factor learning and counterfactual finetuning to HF2-VADHF2-VAD · UCSD Ped2, Setting-AAUROC: 99.3 -> 99.4Improved
Add event-relevant factor learning and counterfactual finetuning to HF2-VADHF2-VAD · ShanghaiTech, Setting-BAUROC: 73.8 -> 76.4Improved
Add event-relevant factor learning and counterfactual finetuning to HF2-VADHF2-VAD · CUHK Avenue, Setting-BAUROC: 82.2 -> 87.8Improved
Add event-relevant factor learning and counterfactual finetuning to HF2-VADHF2-VAD · UCSD Ped2, Setting-BAUROC: 98.4 -> 99.2Improved
Use standard VAE instead of memory-augmented VAE with two representations (ablation)Event-relevant factor learning with HF2-VAD · ShanghaiTech, Setting-BAUROC: 74.2 -> 76.4Improved
Use memory-augmented VAE with one representation instead of two (ablation)Event-relevant factor learning with HF2-VAD · ShanghaiTech, Setting-BAUROC: 72.6 -> 76.4Improved
Use standard VAE with two representations instead of memory-augmented VAE (ablation)Event-relevant factor learning with HF2-VAD · ShanghaiTech, Setting-BAUROC: 75.0 -> 76.4Improved
Add the causal information-flow loss (ablation)Memory-augmented VAE with two representations and counterfactual finetuning · ShanghaiTech, Setting-BAUROC: 74.1 -> 76.4Improved
Add the causal information-flow loss (ablation)Memory-augmented VAE with two representations and counterfactual finetuning · CUHK Avenue, Setting-BAUROC: 85.8 -> 87.8Improved
Use additive interventions instead of dropout-based interventions for counterfactual generation (ablation)Memory-augmented VAE with two representations and causal loss · ShanghaiTech, Setting-BAUROC: 75.2 -> 76.4Improved

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