AI Paper Atlas

Research map / Video / Action recognition

Boundary Content Graph Neural Network for Temporal Action Proposal Generation

Yueran Bai, Yingying Wang, Yunhai Tong, Yang Yang, Qiyue Liu, Junhui Liu

ECCV 2020 · Video › Action recognition · approach: Fully supervised temporal action detection · 161 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
replace GCN with BC-GNN graph reasoning (undirected, no edge update) (ablation)BC-GNN · ActivityNet-1.3 val proposalsAR@100: 75.57 -> 76.18Improved
replace GCN with BC-GNN graph reasoning (undirected, no edge update) (ablation)BC-GNN · ActivityNet-1.3 val proposalsAUC: 66.88 -> 67.36Improved
add edge updating to undirected graph (ablation)BC-GNN · ActivityNet-1.3 val proposalsAR@100: 76.18 -> 76.40Improved
add edge updating to undirected graph (ablation)BC-GNN · ActivityNet-1.3 val proposalsAUC: 67.36 -> 67.79Improved
add directed edges without edge updating (ablation)BC-GNN · ActivityNet-1.3 val proposalsAR@100: 76.18 -> 76.15No clear effect
add directed edges without edge updating (ablation)BC-GNN · ActivityNet-1.3 val proposalsAUC: 67.36 -> 67.53Improved
add directed edges with edge updating (ablation)BC-GNN · ActivityNet-1.3 val proposalsAR@100: 76.40 -> 76.73Improved
add directed edges with edge updating (ablation)BC-GNN · ActivityNet-1.3 val proposalsAUC: 67.79 -> 68.05Improved
add both directed edges and edge updating (ablation)BC-GNN · ActivityNet-1.3 val proposalsAR@100: 76.18 -> 76.73Improved
use BC-GNN proposals instead of BMN proposals for detectiontwo-stage detector · ActivityNet-1.3 val detectionaverage mAP: 33.85 -> 34.26Improved
use BC-GNN proposals instead of BMN proposals for detection (UNet)two-stage detector · THUMOS-14 test detection, tIoU 0.5mAP: 38.8 -> 40.4Improved
Soft-NMS instead of NMS for BC-GNNBC-GNN · THUMOS-14 test proposals (2Stream)AR@100: 50.35 -> 49.60Hurt

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