Human Action Recognition: Pose-Based Attention Draws Focus to Hands

Keywords

Discriminative model, Computer science, Artificial intelligence, Recurrent neural network, Action recognition

References

• Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionKelvin Xu, Jimmy Ba, Ryan Kiros — 2015
• Jointly Learning Heterogeneous Features for RGB-D Activity RecognitionJian–Fang Hu, Wei‐Shi Zheng, Jianhuang Lai — 2015
• Describing Multimedia Content Using Attention-Based Encoder-Decoder NetworksKyunghyun Cho, Aaron Courville, Yoshua Bengio — 2015
• Hierarchical recurrent neural network for skeleton based action recognitionY. Du, Wei Wang, Liang Wang — 2015
• The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and DetectionMihai Zanfir, Marius Leordeanu, Cristian Sminchisescu — 2013
• Further toward a model of the Mind’s eye’s movementJohn Jonides — 1983
• Skeletal Quads: Human Action Recognition Using Joint QuadruplesGeorgios Evangelidis, Gurkirt Singh, Radu Horaud — 2014
• Human Action Recognition by Representing 3D Skeletons as Points in a Lie GroupRaviteja Vemulapalli, Felipe Arrate, Rama Chellappa — 2014
• Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber — 1997
• ImageNet Large Scale Visual Recognition ChallengeOlga Russakovsky, Jia Deng, Hao Su — 2014
• A Model of Saliency-Based Visual Attention for Rapid Scene AnalysisLaurent Itti, Christof Koch, Ernst Niebur — 1998
• Learning to combine foveal glimpses with a third-order Boltzmann machineHugo Larochelle, Geoffrey E. Hinton — 2010
• Action Recognition using Visual AttentionShikhar Sharma, Ryan Kiros, Ruslan Salakhutdinov — 2015
• Rethinking the Inception Architecture for Computer VisionChristian Szegedy, Vincent Vanhoucke, Sergey Ioffe — 2015
• Every Moment Counts: Dense Detailed Labeling of Actions in Complex VideosSerena Yeung, Olga Russakovsky, Ning Jin — 2015
• Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and RecognitionDi Wu, Lionel Pigou, Pieter-Jan Kindermans — 2016
• Deep Multimodal Feature Analysis for Action Recognition in RGB+D VideosAmir Shahroudy, Tian-Tsong Ng, Yihong Gong — 2016
• Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural NetworksPavlo Molchanov, Xiaodong Yang, Shalini Gupta — 2016
• Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural NetworksPichao Wang, Zhaoyang Li, Yonghong Hou — 2016
• Modout: Learning to Fuse Face and Gesture Modalities with Stochastic RegularizationFan Li, Natalia Neverova, Christian Wolf — 2017

Cited by

• Deep-Temporal LSTM for Daily Living Action RecognitionSrijan Das, Michal Koperski, François Brémond — 2018
• Glimpse Clouds: Human Activity Recognition from Unstructured Feature PointsFabien Baradel, Christian Wolf, Julien Mille — 2018
• Graph Edge Convolutional Neural Networks for Skeleton-Based Action RecognitionXikun Zhang, Chang Xu, Xinmei Tian — 2018
• Hands on the wheel: A Dataset for Driver Hand Detection and TrackingGuido Borghi, Elia Frigieri, Roberto Vezzani — 2018
• Human Activity Recognition with Pose-driven Attention to RGBFabien Baradel, Christian Wolf, Julien Mille — 2018
• Similarity-Based Processing of Motion Capture DataJan Sedmidubský, Pavel Zezula — 2018
• DeepGRU: Deep Gesture Recognition UtilityMehran Maghoumi, Joseph J. LaViola — 2018
• Video Action Transformer NetworkRohit Girdhar, João Carreira, Carl Doersch — 2018
• Where to Focus on for Human Action Recognition?Srijan Das, Arpit Chaudhary, François Brémond — 2019
• Egocentric Hand Track and Object-Based Human Action RecognitionGeorgios Kapidis, Ronald Poppe, Elsbeth van Dam — 2019
• Learning to Represent Spatio-Temporal Features for Fine Grained Action RecognitionKaustubh Sakhalkar, François Brémond — 2018
• Spatio-Temporal Grids for Daily Living Action RecognitionSrijan Das, Kaustubh Sakhalkar, Michal Koperski — 2018
• Recognizing User-Defined Subsequences in Human Motion DataJan Sedmidubský, Pavel Zezula — 2019
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action RecognitionChenyang Si, Wentao Chen, Wei Wang — 2019
• Pose-based multisource networks using convolutional neural network and long short-term memory for action recognitionFangqiang Hu, Qianyu Wu, Sai Zhang — 2019
• Magnitude-Orientation Stream network and depth information applied to activity recognitionCarlos Caetano, Victor Hugo Cunha de Melo, François Brémond — 2019
• Learning attentive dynamic maps (ADMs) for Understanding Human ActionsChuankun Li, Yonghong Hou, Wanqing Li — 2019
• Toyota Smarthome: Real-World Activities of Daily LivingSrijan Das, Rui Dai, Michal Koperski — 2019
• Cross-domain Knowledge Transfer Schemes for 3D Human Action RecognitionAthanasios Psaltis, Georgios Th. Papadopoulos, Petros Daras — 2019
• Weakly-Supervised Video Re-Localization with Multiscale Attention ModelYung-Han Huang, Kuang-Jui Hsu, Shyh‐Kang Jeng — 2020

Related papers

• Recurrent attention network using spatial-temporal relations for action recognitionMingxing Zhang, Yang Yang, Yanli Ji — 2018
• Where and When to Look? Spatio-temporal Attention for Action Recognition in VideosLili Meng, Bo Zhao, Bo Chang — 2018
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton DataSijie Song, Cuiling Lan, Junliang Xing — 2016
• Recurrent Spatial-Temporal Attention Network for Action Recognition in VideosWenbin Du, Yali Wang, Yu Qiao — 2018
• Joint spatial-temporal attention for action recognitionTingzhao Yu, Chaoxu Guo, Lingfeng Wang — 2018
• Learning Recurrent 3D Attention for Video-Based Person Re-IdentificationGuangyi Chen, Jiwen Lu, Ming Yang — 2020
• Attention-Based Multiview Re-Observation Fusion Network for Skeletal Action RecognitionZhaoxuan Fan, Xu Zhao, Tianwei Lin — 2019
• Dual Stream Spatio-Temporal Motion Fusion With Self-Attention For Action RecognitionMd Asif Jalal, Waqas Aftab, Roger K. Moore — 2019