AI Paper Atlas

Research map / Video / Action recognition

Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition

Pichao Wang, Wanqing Li, Jun Wan, Philip Ogunbona, Xinwang Liu

AAAI 2018 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 111 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
Train one network cooperatively on RGB and depth with joint softmax and intra-/cross-modality ranking losses instead of separate conventional ConvNetsRGB-D dynamic-image action recognition · ChaLearn LAP IsoGD validationaccuracy: 35.65% -> 44.80%Improved
Train one network cooperatively on RGB and depth with joint softmax and intra-/cross-modality ranking losses instead of separate conventional ConvNetsRGB-D dynamic-image action recognition · NTU RGB+D cross-subjectaccuracy: 84.99% -> 86.42%Improved
Train one network cooperatively on RGB and depth with joint softmax and intra-/cross-modality ranking losses instead of separate conventional ConvNetsRGB-D dynamic-image action recognition · NTU RGB+D cross-viewaccuracy: 87.51% -> 89.08%Improved
Train one network cooperatively on RGB and depth with joint softmax and intra-/cross-modality ranking losses instead of separate conventional ConvNetsRGB-D dynamic-image action recognition · SYSU 3D HOIaccuracy: 97.92% -> 98.33%Improved
Use all four forward and backward RGB/depth dynamic-image channels rather than only one or two channels (ablation)c-ConvNet · ChaLearn LAP IsoGD validationaccuracy: 41.01% -> 44.80%Improved
Use all four forward and backward RGB/depth dynamic-image channels rather than only one or two channels (ablation)c-ConvNet · NTU RGB+D cross-viewaccuracy: 85.21% -> 89.08%Improved
Replace product score fusion with max or average score fusion (ablation)Four-channel c-ConvNet predictions · ChaLearn LAP IsoGDaccuracy: 44.80% vs. 42.01% / 43.48%Hurt
Replace product score fusion with max or average score fusion (ablation)Four-channel c-ConvNet predictions · NTU RGB+D cross-subjectaccuracy: 86.42% vs. 84.69% / 85.86%Hurt
Replace product score fusion with max or average score fusion (ablation)Four-channel c-ConvNet predictions · SYSU 3D HOIaccuracy: 98.33% vs. 97.08% / 97.92%Hurt
Increase the cross-modality triplet-loss weight λ (ablation)c-ConvNet DDIf + VDIf · ChaLearn LAP IsoGDaccuracy: 39.68 -> 39.51 -> 39.61 -> 39.71 -> 41.01 -> 40.13Mixed
Increase the cross-modality triplet-loss weight λ (ablation)c-ConvNet DDIf + VDIf · NTU RGB+D cross-subjectaccuracy: 80.36 -> 81.15 -> 82.64 -> 80.18 -> 80.06 -> 80.11Mixed
Use bidirectional rather than forward-only dynamic images (ablation)RGB-D c-ConvNet · ChaLearn LAP IsoGD validationaccuracyImproved

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