Action Recognition.
Riferimenti bibliografici
- [Sze11], Ch. 8
- [Davies18], Ch.20
Link utili
- Deep Learning for Action Recognition: A Review
- 3D Convolution in Pytorch
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Quo vadis, action recognition? a new model and the kinetics dataset
- 3d convolutional neural networks for human action recognition
- Large-Scale Video Classification with Convolutional Neural Networks
- Learning spatio-temporal representation with pseudo-3d residual networks
- Rethinking Spatiotemporal Feature Learning
- Spatiotemporal residual networks for video action recognition
- Long-Term Feature Banks for Detailed Video Understanding
- The Kinetics Human Action Recognition Dataset
- Long-term Recurrent Convolutional Networks for Visual Recognition and Description
- Action Recognition Using Visual Attention
- Recurrent Tubelet Proposal and Recognition Networks for Action Detection
- VideoLSTM Convolves, Attends and Flows for Action Recognition
- Beyond Short Snippets: Deep Networks for Video Classification
- An Iterative Image Registration Technique with an Application to Stero Vision
- Two-Frame Motion Estimation with Polynomial Expansion
- Introduction to Motion Estimation with Optical Flow
- Optical Flow Estimation
- FlowNet: Learning Optical Flow with Convolutional Networks
- Two-Stream Convolutional Networks for Action Recognition in Videos
- What is optical flow and why does it matter in deep learning
- Michael Black’s lecture on Optical Flow