Publication | Closed Access

Segment spatial-temporal representation and cooperative learning of convolution neural networks for multimodal-based action recognition

Cognitive ScienceMachine VisionMachine LearningData ScienceImage AnalysisPattern RecognitionEngineeringObject RecognitionMultimodal Signal ProcessingComputer ScienceVideo UnderstandingConvolution Neural NetworksDeep LearningActivity RecognitionCooperative LearningVideo InterpretationComputer VisionSegment Spatial-temporal Representation