Segment spatial-temporal representation and cooperative learning of convolution neural networks for multimodal-based action recognition
Ziliang Ren, Qieshi Zhang, Jun Cheng, Fusheng Hao, Xiangyang Gao
Topics & Concepts
RGB color modelArtificial intelligenceComputer scienceConvolutional neural networkPattern recognition (psychology)Benchmark (surveying)Convolution (computer science)Action recognitionDeep learningPoolingModalitiesMachine learningArtificial neural networkGeodesyClass (philosophy)SociologySocial scienceGeographyHuman Pose and Action RecognitionHand Gesture Recognition SystemsGait Recognition and Analysis