总览

• 模型权重文件数量: 220

• 配置文件数量: 196

• 论文数量: 27

  • ALGORITHM: 23

  • BACKBONE: 1

  • DATASET: 2

  • OTHERS: 1

有关受支持的数据集，可参见 数据集总览。

时空动作检测模型

• 模型权重文件数量: 22

• 配置文件数量: 20

• 论文数量: 5

  • [ALGORITHM] Actor-Centric Relation Network (->)

  • [ALGORITHM] Long-Term Feature Banks for Detailed Video Understanding (->)

  • [ALGORITHM] Omni-Sourced Webly-Supervised Learning for Video Recognition (->)

  • [ALGORITHM] Slowfast Networks for Video Recognition (->)

  • [DATASET] Ava: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions (-> ->)

时序动作检测模型

• 模型权重文件数量: 7

• 配置文件数量: 3

• 论文数量: 4

  • [ALGORITHM] Bmn: Boundary-Matching Network for Temporal Action Proposal Generation (->)

  • [ALGORITHM] Bsn: Boundary Sensitive Network for Temporal Action Proposal Generation (->)

  • [ALGORITHM] Temporal Action Detection With Structured Segment Networks (->)

  • [DATASET] Cuhk & Ethz & Siat Submission to Activitynet Challenge 2017 (->)

动作识别模型

• 模型权重文件数量: 175

• 配置文件数量: 157

• 论文数量: 17

  • [ALGORITHM] A Closer Look at Spatiotemporal Convolutions for Action Recognition (->)

  • [ALGORITHM] Audiovisual Slowfast Networks for Video Recognition (->)

  • [ALGORITHM] Is Space-Time Attention All You Need for Video Understanding? (->)

  • [ALGORITHM] Learning Spatiotemporal Features With 3d Convolutional Networks (->)

  • [ALGORITHM] Omni-Sourced Webly-Supervised Learning for Video Recognition (->)

  • [ALGORITHM] Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (->)

  • [ALGORITHM] Slowfast Networks for Video Recognition (-> ->)

  • [ALGORITHM] Tam: Temporal Adaptive Module for Video Recognition (->)

  • [ALGORITHM] Temporal Interlacing Network (->)

  • [ALGORITHM] Temporal Pyramid Network for Action Recognition (->)

  • [ALGORITHM] Temporal Relational Reasoning in Videos (->)

  • [ALGORITHM] Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (->)

  • [ALGORITHM] Tsm: Temporal Shift Module for Efficient Video Understanding (->)

  • [ALGORITHM] Video Classification With Channel-Separated Convolutional Networks (->)

  • [ALGORITHM] X3d: Expanding Architectures for Efficient Video Recognition (->)

  • [BACKBONE] Non-Local Neural Networks (-> ->)

  • [OTHERS] Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition (->)

骨骼动作识别模型

• 模型权重文件数量: 16

• 配置文件数量: 16

• 论文数量: 3

  • [ALGORITHM] Revisiting Skeleton-Based Action Recognition (->)

  • [ALGORITHM] Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition (->)

  • [ALGORITHM] Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition (->)