Recognition of Visually Perceived Compositional Human Actions by
Multiple Spatio-Temporal Scales Recurrent Neural Networks

v1v2v3 (latest)

Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks

5 February 2016

ArXiv (abs)PDF HTML

Papers citing "Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks"

5 / 5 papers shown

Title
Distilled Mid-Fusion Transformer Networks for Multi-Modal Human Activity RecognitionKnowledge-Based Systems (KBS), 2023 Jingcheng Li Weitong Chen Binghao Li Claude Sammut 130 6 0 05 May 2023
Trear: Transformer-based RGB-D Egocentric Action RecognitionIEEE Transactions on Cognitive and Developmental Systems (IEEE TCDS), 2021 Xiangyu Li Yonghong Hou Pichao Wang Zhimin Gao Mingliang Xu Wanqing Li ViT 353 99 0 05 Jan 2021
Encoding Longer-term Contextual Multi-modal Information in a Predictive Coding Model Junpei Zhong T. Ogata Angelo Cangelosi AI4CE 81 4 0 17 Apr 2018
AFA-PredNet: The action modulation within predictive coding Junpei Zhong Angelo Cangelosi Xinzheng Zhang T. Ogata 106 12 0 11 Apr 2018
Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition Minju Jung Haanvid Lee Jun Tani AI4TS 157 42 0 24 May 2017