AI Paper Atlas

Research map / Video / Action recognition

Video Self-Stitching Graph Network for Temporal Action Localization

Chen Zhao, Ali K. Thabet, Bernard Ghanem

ICCV 2021 · Video › Action recognition · approach: Weakly supervised temporal action localization · 165 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 video self-stitching (VSS) to baseline (ablation)VSGN baseline · THUMOS-14short-action mAP: 45.1 -> 48.7Improved
add VSS to baseline (ablation)VSGN baseline · THUMOS-14mAP@0.5: 42.54 -> 45.52Improved
add xGPN to baseline (ablation)VSGN baseline · THUMOS-14mAP@0.5: 42.54 -> 50.24Improved
add VSS on top of xGPN (ablation)VSGN · THUMOS-14mAP@0.5: 50.24 -> 52.45Improved
add VSS on top of xGPN (ablation)VSGN · THUMOS-14short-action mAP: 53.4 -> 56.6Improved
add VSS to baseline (ablation)VSGN baseline · ActivityNet-v1.3average mAP: 34.25 -> 34.70Improved
add xGPN to baseline (ablation)VSGN baseline · ActivityNet-v1.3average mAP: 34.25 -> 33.79Hurt
add xGPN on top of VSS (ablation)VSGN · ActivityNet-v1.3average mAP: 34.70 -> 35.07Improved
combine Clip O and Clip U predictions (ablation)VSGN · ActivityNet-v1.3average mAP: 34.96 -> 35.07Improved
use xGN at all encoder levels instead of a single level (ablation)xGPN · ActivityNet-v1.3average mAP: 34.46 -> 35.07Improved
use half free and half cross-scale edges instead of only free edges (ablation)xGN · ActivityNet-v1.3average mAP: 34.48 -> 35.07Improved
use half free and half cross-scale edges instead of only cross-scale edges (ablation)xGN · ActivityNet-v1.3average mAP: 34.75 -> 35.07Improved

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