pfabreu / two-stream-networks
Multi-stream CNN architectures for action detection with actor-centric filtering
☆25Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for two-stream-networks
- experiments on classifying actions using poses☆26Updated 6 years ago
- Train action classification model based on individual frames☆42Updated 5 years ago
- Pytorch implementation of the paper "Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points", F. Baradel, C. Wolf, J…☆30Updated 4 years ago
- Our implementation of Recurrent Pose Attention in Du et al.: "RPAN: An End-to-End Recurrent Pose-attention Network for Action Recognition…☆37Updated 5 years ago
- Inflated 3D ConvNets for video understanding☆49Updated last year
- Lua☆58Updated 6 years ago
- Human action recognition from skeletal data☆41Updated 4 years ago
- Code for paper: Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition☆27Updated last year
- Multi 3DCNN for action recognition using global and local information☆37Updated 6 years ago
- This repository host the code for real-time action detection paper☆30Updated 6 years ago
- This review contains some action recognition methods.☆56Updated 5 years ago
- A one stop shop for all of your activity recognition needs.☆107Updated 5 years ago
- Cascaded Boundary Regression For Temporal Action Detection☆53Updated 6 years ago
- Keras implementation for Co-occurrence-Feature-Learning-from-Skeleton-Data-for-Action-Recognition☆46Updated 5 years ago
- Skeleton based action recognition models with TCN variants for learning interpretable representation.☆122Updated 6 years ago
- Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.☆39Updated 5 years ago
- ☆33Updated 7 years ago
- part-aware lstm implemented in tensorflow used in skeleton-based action recognition with dataset NTU RGB+D.☆48Updated 4 years ago
- Source code for the CVPR 2017 paper☆65Updated 6 years ago
- TensorFlow Implementation of "Action Recognition using Visual Attention"☆49Updated 7 years ago
- Deep networks with Temporal Pyramid Pooling. The official implementation for "End-to-end Video-level Representation Learning for Action R…☆73Updated 5 years ago
- generate action data using openpose or SSD☆30Updated 6 years ago
- Learning Spatiotemporal Features using 3DCNN and Convolutional LSTM for Gesture Recognition☆60Updated 5 years ago
- This repository is intended to host tools and demos for ActivityNet☆21Updated 7 years ago
- ☆15Updated 6 years ago
- Action Recognition based on Pose Estimation.☆27Updated 4 years ago
- using GPU to extract videos' dense optical flow fields☆38Updated 7 years ago
- ☆30Updated 5 years ago
- End-to-End, Single-Stream Temporal Action Detection in Untrimmed Videos (Official Repo for SS-TAD)☆107Updated 7 years ago