AI Paper Atlas

Research map / Video / Action recognition

ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification

Rohit Girdhar, Deva Ramanan, Abhinav Gupta, Josef Sivic, Bryan Russell

CVPR 2017 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 528 citations (OpenAlex)

Check 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
Train the ActionVLAD aggregation together with preceding network layers rather than keeping the initialized aggregation fixed (ablation)ActionVLAD on HMDB51 split 1 · HMDB51 split 1accuracy: 44.9 -> 51.2Improved
Use K=1 cluster instead of K=64 (ablation)ActionVLAD · HMDB51 split 1 RGBaccuracy: 51.2% -> 43.2%Hurt
Aggregate conv5_3 features instead of conv4_3 or fc7 (ablation)ActionVLAD · HMDB51 split 1accuracy: 45.0 -> 51.2; 43.3 -> 51.2Improved
Replace ActionVLAD with average pooling over conv5_3 features (ablation)VGG-16 two-stream architecture · HMDB51 split 1 RGBaccuracy: 51.2 -> 41.6Hurt
Replace ActionVLAD with max pooling over conv5_3 features (ablation)VGG-16 two-stream architecture · HMDB51 split 1 RGBaccuracy: 51.2 -> 41.5Hurt
Fuse appearance and motion by concatenating features before one ActionVLAD layer rather than separately late-fusing their representations (ablation)ActionVLAD · HMDB51 split 1validation accuracy: 66.9 -> 56.0Hurt
Pool appearance and motion together in one ActionVLAD layer rather than separately late-fusing their representations (ablation)ActionVLAD · HMDB51 split 1validation accuracy: 66.9 -> 64.8Hurt
Use five crops per frame instead of a single center crop at test time (ablation)ActionVLAD · HMDB51accuracy: 66.3 -> 66.9Improved
Use ActionVLAD rather than the two-stream baselineVGG-16 action classification · HMDB51accuracy: 58.5 -> 66.3Improved
Add iDT score fusion to ActionVLADActionVLAD (VGG-16) · CharadesmAP: 17.6 -> 21.0Improved

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