AI Paper Atlas

Research map / Video / Video segmentation and tracking

Local Compressed Video Stream Learning for Generic Event Boundary Detection

Libo Zhang, Xin Gu, Congcong Li, Tiejian Luo, Heng Fan

IJCV 2023 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 6 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 local frames bag (k=2 versus k=0) (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.685 -> 0.741Improved
add LSTM temporal extractor instead of no temporal module (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.742 -> 0.768Improved
LSTM instead of Transformer (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.751 -> 0.768Improved
LSTM instead of GRU (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.760 -> 0.768No clear effect
LSTM instead of average pooling (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.699 -> 0.768Improved
add SCAM (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.653 -> 0.685Improved
add Gaussian-smoothed soft labels (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.760 -> 0.768Improved
larger backbone for motion vectors and residuals (ResNet-50/101 instead of ResNet-18) (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.768 -> 0.753 (ResNet-50), 0.750 (ResNet-101)Hurt
bag size k=8 instead of k=10 or 12 (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.747 -> 0.768 (k=10), 0.745 -> 0.768 (k=12)Improved
fuse I-frame, motion vector and residual features (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.650 -> 0.768Improved
sample 3 P-frames per GOP instead of 5 (ablation)LCVSL · Kinetics-GEBD minvalF1: 0.761 -> 0.768Improved
use top-2 annotators' labels instead of top-1 for training (ablation)LCVSL · Kinetics-GEBD minvalF1Improved

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