AI Paper Atlas

Research map / Video / Action recognition

Enriching Local and Global Contexts for Temporal Action Localization

Zixin Zhu, Wei Tang, Le Wang, Nanning Zheng, Gang Hua

ICCV 2021 · Video › Action recognition · approach: Weakly supervised temporal action localization · 144 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 L-Net before P-Net (non-local) (ablation)P-Net (non-local) · THUMOS14 testavg mAP: 39.76 -> 42.64Improved
add G-Net before P-Net (non-local) (ablation)P-Net (non-local) · THUMOS14 testavg mAP: 39.76 -> 41.33Improved
add L-Net before P-Net (P-GCN) (ablation)P-Net (P-GCN) · THUMOS14 testavg mAP: 42.43 -> 45.12Improved
add G-Net before P-Net (P-GCN) (ablation)P-Net (P-GCN) · THUMOS14 testavg mAP: 42.43 -> 43.51Improved
add L-Net before P-Net (P-GCN) (ablation)P-Net (P-GCN) · THUMOS14 test (tIoU 0.5)mAP: 49.10 -> 53.17Improved
add L-Net and G-Net to P-GCN (ablation)P-Net (P-GCN) · THUMOS14 test (tIoU 0.5)mAP: 49.10 -> 54.30Improved
add global context adaptation in G-Net (ablation)ContextLoc · THUMOS14 testavg mAP (fusion): 43.23 -> 45.70Improved
add interaction between adapted global contexts (ablation)ContextLoc · THUMOS14 testavg mAP (fusion): 44.14 -> 45.70Improved
process extended proposal as three proposals instead of one (dim 1024) (ablation)ContextLoc · THUMOS14 testavg mAP (fusion): 40.04 -> 45.70Improved
process extended proposal as three proposals instead of one (dim 3072) (ablation)ContextLoc · THUMOS14 testavg mAP (fusion): 44.57 -> 45.70Improved
add graph convolutional layers to P-GCN (Deep) (ablation)P-GCN · THUMOS14 testavg mAP: 42.43 -> 42.20No clear effect
add two graph convolutional layers to P-GCN (Deeper) (ablation)P-GCN · THUMOS14 testavg mAP: 42.43 -> 42.03Hurt

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