AI Paper Atlas

Research map / Video / Action recognition

Graph Convolutional Module for Temporal Action Localization in Videos

Runhao Zeng, Wenbing Huang, Mingkui Tan, Yu Rong, Peilin Zhao, Junzhou Huang, Chuang Gan

TPAMI 2021 · Video › Action recognition · approach: Weakly supervised temporal action localization · 95 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 GCM to SSN (BSN proposals, I3D)SSN · THUMOS14 tIoU=0.5mAP: 49.3 -> 50.9Improved
add GCM to R-C3DR-C3D · THUMOS14 tIoU=0.5mAP: 28.90 -> 30.85Improved
add GCM to CBRCBR · THUMOS14 tIoU=0.5mAP: 31.00 -> 32.24Improved
add GCM to one-stage D-SSADD-SSAD · THUMOS14 tIoU=0.5mAP: 43.21 -> 44.77Improved
add graph relations (GCM) in place of MLP for both classification and regression branches (ablation)SSN · THUMOS14 tIoU=0.5 RGB / FlowmAP: 36.82 -> 39.38 (RGB); 46.74 -> 48.76 (Flow)Improved
use graph convolution instead of mean pooling over adjacent units (ablation)SSN · THUMOS14 tIoU=0.5 RGB / FlowmAP: 37.12 -> 39.38 (RGB); 46.96 -> 48.76 (Flow)Improved
add self-addition of node feature (ablation)GCM · THUMOS14 tIoU=0.5 RGB / FlowmAP: 38.32 -> 39.38 (RGB); 47.62 -> 48.76 (Flow)Improved
embed features before cosine edge weight (embed-cos-sim) (ablation)GCM · THUMOS14 tIoU=0.5mAP: 39.38 -> 39.27 (RGB); 48.76 -> 48.92 (Flow)No clear effect
use learned attention weights on a fully-connected graph instead of GCM graph (ablation)SSN · THUMOS14 tIoU=0.5mAP: 50.9 -> 49.7Hurt
add surrounding edges (ablation)GCM · THUMOS14 tIoU=0.5 RGB / FlowmAP: 38.80 -> 39.38 (RGB); 47.69 -> 48.76 (Flow)Improved
add contextual edges (ablation)GCM · THUMOS14 tIoU=0.5 RGB / FlowmAP: 38.28 -> 39.38 (RGB); 47.57 -> 48.76 (Flow)Improved
add semantic edges (ablation)GCM · THUMOS14 tIoU=0.5 RGB / FlowmAP: 39.02 -> 39.38 (RGB); 47.38 -> 48.76 (Flow)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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