xiaogangLi / tensorflow-VTN
An implementation of Video Transformer Network (VTN) approach for Action Recognition in TensorFlow.
☆55Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for tensorflow-VTN
- Train I3D model on ucf101 or hmdb51 by tensorflow☆112Updated 5 years ago
- TensorFlow code for finetuning I3D model on UCF101.☆143Updated 6 years ago
- Decoupling Localization and Classification in Single Shot Temporal Action Detection☆94Updated 5 years ago
- Code for paper: Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition☆27Updated last year
- Use human pose information to help action recognition, explored with attention-pooling method, C3D method and two-stream architecture, im…☆17Updated 6 years ago
- Cascaded Boundary Regression For Temporal Action Detection☆53Updated 6 years ago
- [Codes of paper]: PAN: Towards Fast Action Recognition via Learning Persistence of Appearance☆102Updated 4 years ago
- A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognitio…☆60Updated 5 years ago
- Pytorch implementation of StNet: Local and Global Spatial-Temporal Modeling for Action Recognition☆58Updated 5 years ago
- Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.☆39Updated 5 years ago
- Two Stream CNN implemented in Keras using in skeleton-based action recognition with dataset NTU RGB+D☆76Updated 6 years ago
- Temporal Segment Networks (TSN) in Tensorflow☆25Updated 5 years ago
- Inflated 3D ConvNets for video understanding☆49Updated last year
- This is an i3d version which can be used to finetune on other video dataset.☆40Updated 6 years ago
- SmallBigNet: Integrating Core and Contextual Views for Video Classification (CVPR2020)☆41Updated 2 years ago
- implementation of the paper 'SlowFast Networks for Video Recognition ' with Pytorch☆27Updated 5 years ago
- Preprocess data for deepmind's kinetics i3d network☆14Updated 4 years ago
- Learning Spatiotemporal Features using 3DCNN and Convolutional LSTM for Gesture Recognition☆61Updated 5 years ago
- A implementation of "SlowFast Networks for Video Recognition" with tf.keras☆50Updated 5 years ago
- using GPU to extract videos' dense optical flow fields☆38Updated 7 years ago
- Gate-Shift Networks for Video Action Recognition - CVPR 2020☆149Updated 4 years ago
- MARS: Motion-Augmented RGB Stream for Action Recognition☆161Updated last year
- Code of the STAGE module for video action detection☆49Updated 3 years ago
- Spatiotemporal-separable 3D convolution network.☆117Updated 6 years ago
- Train action classification model based on individual frames☆42Updated 5 years ago
- The code is for the CVPR 2019 paper 'Dance with Flow: Two-in-One Stream for Action Detection '☆31Updated 2 years ago
- This review contains some action recognition methods.☆56Updated 5 years ago
- ☆90Updated 6 years ago
- ☆28Updated 5 years ago
- ☆30Updated 5 years ago