Spatial-temporal interaction learning based two-stream network for action recognition

Tianyu Liu, Yujun Ma, Wenhan Yang, +3

Information Sciences

Cognitive ScienceEngineeringMachine LearningPattern RecognitionTwo-stream Network +4

Relative-position embedding based spatially and temporally decoupled Transformer for action recognition

Yujun Ma, Ruili Wang

Pattern Recognition

Image AnalysisMachine VisionEngineeringPattern RecognitionAction Recognition +7

Multi-head attention-based two-stream EfficientNet for action recognition

Aihua Zhou, Yujun Ma, Wanting Ji, +4

Multimedia Systems

Efficient Feature ExtractionMachine VisionMachine LearningImage AnalysisEngineering +12

Spatial and temporal saliency based four-stream network with multi-task learning for action recognition

Ming Zong, Ruili Wang, Yujun Ma, +1

Applied Soft Computing

Temporal SaliencyCognitive ScienceImage AnalysisMachine VisionEngineering +8

<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si65.svg" display="inline" id="d1e738"><mml:mi>k</mml:mi></mml:math>-NN attention-based video vision transformer for action recognition

Weirong Sun, Yujun Ma, Ruili Wang

Neurocomputing

EngineeringMachine LearningAction Recognition (Movement Science)Video ProcessingAction Recognition (Computer Vision) +18

Multi-cue based four-stream 3D ResNets for video-based action recognition

Lei Wang, Xiaoguang Yuan, Ming Zong, +4

Information Sciences

Machine VisionImage AnalysisEngineeringPattern RecognitionVideo Processing +5

Survey on deep learning in multimodal medical imaging for cancer detection

Yan Tian, Zhaocheng Xu, Yujun Ma, +6

Neural Computing and Applications

EngineeringMachine LearningMedical ImagingCancer DetectionMedical Image Computing +12

Convolutional transformer network for fine-grained action recognition

Yujun Ma, Ruili Wang, Ming Zong, +3

Neurocomputing

Convolutional Neural NetworkConvolutional Transformer NetworkMachine VisionEngineeringPattern Recognition +4

Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture Recognition

Yujun Ma, Benjia Zhou, Ruili Wang, +1

EngineeringMachine LearningHuman Pose EstimationVideo InterpretationImage Analysis +20

Laplacian eigenmaps based manifold regularized CNN for visual recognition

Ming Zong, Zhizhong Ma, Fangyi Zhu, +2

Information Sciences