AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Representing Videos As Discriminative Sub-Graphs for Action Recognition

Dong Li, Zhaofan Qiu, Yingwei Pan, Ting Yao, Houqiang Li, Tao Mei

CVPR 2021 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 29 citations (OpenAlex)

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 clip-level classification with discriminative sub-graph reasoning (ablation)LGD Base · Something-Something V2 valtop-1 accuracy: 60.8 -> 63.2Improved
Use 4-node rather than 3-node sub-graphs (ablation)Base+Sub-graph · Something-Something V2 valtop-1 accuracy: 62.7 -> 63.2Improved
Use 5-node rather than 4-node sub-graphs (ablation)Base+Sub-graph · Something-Something V2 valtop-1 accuracy: 63.2 -> 62.2Hurt
Add tubelet coordinate features (ablation)Base+Sub-graph (4 nodes) · Something-Something V2 valtop-1 accuracy: +0.3%Improved
Add relative coordinate changes to graph edges (ablation)Node Coord (4 nodes) · Something-Something V2 valtop-1 accuracy: +0.6%Improved
Combine sub-graphs across three scales (ablation)Edge Coord (4 nodes) · Something-Something V2 valtop-1 accuracy: 64.1 -> 65.0Improved
Use sub-graph prototypes instead of whole-graph GCN reasoning (ablation)Base+GCN · Something-Something V2 valtop-1 accuracy: 61.3 -> 63.2Improved
Use MUSLE instead of TEAResNet-50 action recognition · Something-Something V1 valtop-1 accuracy: 0.6%Improved
Use MUSLE instead of STMResNet-50 action recognition · Something-Something V2 valtop-1 accuracy: 0.8%Improved
Transfer Kinetics-trained action prototypes without fine-tuningMUSLE · UCF101accuracy: 9.6%Improved
Transfer Kinetics-trained action prototypes without fine-tuningMUSLE · HMDB51accuracy: 13.5%Improved

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