AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Dividing and Aggregating Network for Multi-view Action Recognition

Dongang Wang, Wanli Ouyang, Wen Li, Dong Xu

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 81 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 message passing module to multi-branch + fusion (ablation)DA-Net · NTU RGB+D cross-viewtwo-stream accuracy: 90.7% -> 92.0%Improved
add view-prediction-guided fusion module (ablation)DA-Net · NTU RGB+D cross-viewtwo-stream accuracy: 90.9% -> 92.0%Improved
add message passing to basic multi-branch module (ablation)DA-Net · NTU RGB+D cross-viewtwo-stream accuracy: 89.8% -> 90.9%Improved
add fusion module to basic multi-branch module (ablation)DA-Net · NTU RGB+D cross-viewtwo-stream accuracy: 89.8% -> 90.7%Improved
use view-specific branches with shared CNN instead of TSN (ablation)DA-Net · NTU RGB+D cross-viewtwo-stream accuracy: 85.4% -> 89.8%Improved
shared view-independent CNN instead of separate ensemble TSN per view (ablation)DA-Net · NTU RGB+D cross-viewtwo-stream accuracy: 87.8% -> 89.8%Improved
add message passing to RGB stream (ablation)DA-Net · NTU RGB+D cross-viewRGB-stream accuracy: 73.9% -> 74.5%Improved
DA-Net instead of TSNDA-Net · NTU RGB+D cross-subjectaccuracy: 84.93% -> 88.12%Improved
DA-Net instead of TSNDA-Net · NTU RGB+D cross-viewaccuracy: 85.36% -> 91.96%Improved
DA-Net instead of TSNDA-Net · NUMA cross-subjectaverage accuracy: 90.3% -> 92.1%Improved
DA-Net instead of TSN for unseen viewDA-Net · NUMA cross-view train {2,3} test 1accuracy: 76.8% -> 83.1%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