CVPR2019
- 1、An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
作者：Chenyang Si, Wentao Chen, Wei Wang, Liang Wang, Tieniu Tan
論文鏈接：https://arxiv.org/abs/1902.09130
- 2、Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training
作者：Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel
鏈接：https://arxiv.org/abs/1812.06145
- 3、Collaborative Spatio-temporal Feature Learning for Video Action Recognition
作者：Chao Li, Qiaoyong Zhong, Di Xie, Shiliang Pu
論文鏈接：https://arxiv.org/abs/1903.01197
- 4、Peeking into the Future: Predicting Future Person Activities and Locations in Videos(行為預測）
作者：Junwei Liang, Lu Jiang, Juan Carlos Niebles, Alexander Hauptmann, Li Fei-Fei
論文鏈接：https://arxiv.org/abs/1902.03748
ECCV 2018
- Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
- Dividing and Aggregating Network for Multi-view Action Recognition
- Deep Bilinear Learning for RGB-D Action Recognition
- Modality Distillation with Multiple Stream Networks for Action Recognition
- Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
- Motion Feature Network: Fixed Motion Filter for Action Recognition
- Spatio-Temporal Channel Correlation Networks for Action Classification
- Recurrent Tubelet Proposal and Recognition Networks for Action Detection
- PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
- RESOUND: Towards Action Recognition without Representation Bias
CVPR 2018
- MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition
- Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
- 2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning
- Temporal Hallucinating for Action Recognition With Few Still Images
- Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition
- Im2Flow: Motion Hallucination From Static Images for Action Recognition
- Compressed Video Action Recognition
- A Closer Look at Spatiotemporal Convolutions for Action Recognition
- Temporal Deformable Residual Networks for Action Segmentation in Videos
- PoTion: Pose MoTion Representation for Action Recognition
- What Have We Learned From Deep Representations for Action Recognition?
- Towards Universal Representation for Unseen Action Recognition
AAAI 2018
- Action Recognition from Skeleton Data via Analogical Generalization over Qualitative Representations
- Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
- Cooperative Training of Deep Aggregation Networks for RGB-D Action Recognition
- Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map based Feature Extraction for Human Action Recognition
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition [code: https://github.com/yysijie/st-gcn]
- T-C3D: Temporal Convolutional 3D Network for Real-time Action Recognition [code:tc3d/tc3d]
- Unsupervised Deep Learning of Mid-Level Video Representation for Action Recognition
- Unsupervised Representation Learning with Long-Term Dynamics for Skeleton Based Action Recognition