...
机译:基于骨架的动作识别的关注机制立方体CNN模型
FIST LAB School of Information Science and Engineering Yunnan University Kunming Yunnan P.R.China;
Union Vision Innovations Technology Shenzhen P.R.China;
Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China;
CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China;
FIST LAB School of Information Science and Engineering Yunnan University Kunming Yunnan P.R.China;
Feature extraction; Skeleton; Sensors; Three-dimensional displays; Spatiotemporal phenomena; Hidden Markov models; Neural networks;
机译:通过双向LSTM-CNN探索基于骨架的动作识别的丰富的空间依赖关系模型
机译:基于骨架的注意力感知的动作检测和识别空间时间模型
机译:使用深度LSTM和CNN进行基于骨架的动作识别的多源学习
机译:利用预训练的CNN模型进行基于骨骼的动作识别
机译:使用Optical Flow和3D HMM进行面部表情识别,并使用长方体和主题模型进行人体动作识别
机译:结合视觉注意的主视觉皮层计算模型的动作识别
机译:一种辨别性双流模型,具有新颖的基于骨架人体行动识别的持续关注机制