2019 · 79 citations · 22 references
ComputingComputer ScienceComputer VisionFeature EngineeringMovement AnalysisAction RecognitionDeep LearningJoint Motion AnalysisMotion AnalysisMulti-task LearningRepresentation LearningActivity RecognitionConvolutional Neural NetworksFeature LearningMotion FeaturesMulti-task Deep LearningMulti-task Feature LearningSkeleton-based Action RecognitionSkeleton-based Representation
In this paper, we propose a three-stream convolutional neural network (3SCNN) for action recognition from skeleton sequences, which aims to thoroughly and fully exploit the skeleton data by extracting, learning, fusing and inferring multiple motion-related features, including 3D joint positions and joint displacements across adjacent frames as well as oriented bone segments. The proposed 3SCNN involves three sequential stages. The first stage enriches three independently extracted features by co-occurrence feature learning. The second stage involves multi-channel pairwise fusion to take advantage of the complementary and diverse nature among three features. The third stage is a multi-task and ensemble learning network to further improve the generalization ability of 3SCNN. Experimental results on the standard dataset show the effectiveness of our proposed multi-stream feature learning, fusion and inference method for skeleton-based 3D action recognition.
22
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Amir Shahroudy, Jun Liu, Tian-Tsong Ng et al. · 2016 · 2.9K citations
A New Representation of Skeleton Sequences for 3D Action Recognition
2017 · 768 citations · Full text