AI Paper Atlas

Research map / Video / Video segmentation and tracking

Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection

Jiaqi Tang, Zhaoyang Liu, Chen Qian, Wayne Wu, Limin Wang

CVPR 2022 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 16 citations (OpenAlex)

Check 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
Use dense difference maps with RGB features instead of RGB features alone (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.6793 -> 0.7643Improved
Replace optical flow with DDM in the motion representation (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.6625 -> 0.7512Improved
Combine RGB with DDM instead of using a two-stream RGB and optical-flow representation (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.6881 -> 0.7643Improved
Use a local clip with stride s=6 rather than a much wider view with s=30 (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.6914 -> 0.7643Improved
Use more frames, with w=15 instead of w=5 (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7643 -> 0.7703Improved
Add multi-level spatial and temporal features instead of using a single feature level (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7353 -> 0.7643Improved
Replace Euclidean distance with Manhattan distance for DDM (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7643 -> 0.7632No clear effect
Replace Euclidean distance with Chebyshev distance for DDM (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7643 -> 0.7540Hurt
Add both intra-modal and cross-modal attention instead of averaging features (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7498 -> 0.7643Improved
Replace pyramidal feature hierarchy with FPN (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7643 -> 0.7511Hurt
Increase intra-modal and cross-modal attention layers from 1 each to 6 each (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7584 -> 0.7643Improved
Use 5 learnable queries rather than 1 or 10 (ablation)DDM-Net · Kinetics-GEBDF1@0.05: 0.7579 -> 0.7643; 0.7592 -> 0.7643Improved

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