Use human pose information to help action recognition, explored with attention-pooling method, C3D method and two-stream architecture, implemented in pytorch.
☆18Jun 7, 2018Updated 8 years ago
Alternatives and similar repositories for Pose-guided-action-recognition
Users that are interested in Pose-guided-action-recognition are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- We want to derive a effective way to utilize pose information in action recognition☆12Mar 27, 2018Updated 8 years ago
- generate action data using openpose or SSD☆30Aug 21, 2018Updated 8 years ago
- Temporal augmentation with two-stream ConvNet features on human action recognition☆18Apr 3, 2017Updated 9 years ago
- PyTorch implementation of Human Action Recognition Based on Spatial-Temporal Attention at ICLR 2019☆14Dec 12, 2018Updated 7 years ago
- Action localization Proposals from dense Trajectories☆21Jan 14, 2016Updated 10 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- optimized caffe for GBD☆27Oct 7, 2016Updated 10 years ago
- A two-stream convolutional neural network for learning abitrary similarity functions over two sets of training data☆23Oct 12, 2017Updated 9 years ago
- Make your character with facial blendshapes show natural facial expressions. Designed for models from Autodesk Character Generator.☆15Feb 27, 2017Updated 9 years ago
- Code/Model release for NIPS 2017 paper "Attentional Pooling for Action Recognition"☆259May 20, 2018Updated 8 years ago
- Independently Recurrent Neural Network - IndRNN using "NTU RGB+D" Action Recognition Dataset☆10May 13, 2019Updated 7 years ago
- Our implementation of Recurrent Pose Attention in Du et al.: "RPAN: An End-to-End Recurrent Pose-attention Network for Action Recognition…☆37Nov 24, 2018Updated 7 years ago
- The code for shuttleNet.☆31Jul 25, 2017Updated 9 years ago
- Tvnet implemented in pytorch☆45Apr 9, 2019Updated 7 years ago
- experiments on classifying actions using poses☆26May 5, 2018Updated 8 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Distance Matrix Neural Networks for human action recognition☆13Oct 23, 2017Updated 9 years ago
- Multi 3DCNN for action recognition using global and local information☆38Jan 16, 2018Updated 8 years ago
- ☆19Jul 30, 2016Updated 10 years ago
- ☆11May 31, 2020Updated 6 years ago
- Video Classifier using CNNs + LSTMs☆12Dec 18, 2018Updated 7 years ago
- Support LRCN(both rgb and optical-flow). This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework wh…☆13Mar 6, 2018Updated 8 years ago
- Code for AdaScan: Adaptive Scan Pooling (CVPR 2017)☆45Mar 6, 2018Updated 8 years ago
- Non-Local salience_object detection☆10May 19, 2018Updated 8 years ago
- an end-to-end instance-segmentation framework inspired by YOLO and mask R-CNN☆13Nov 22, 2019Updated 6 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Geometric Mean Metric Learning☆12Aug 18, 2019Updated 7 years ago
- WACV 2017☆10Feb 14, 2017Updated 9 years ago
- Learning Spatiotemporal Features using 3DCNN and Convolutional LSTM for Gesture Recognition☆62Dec 6, 2018Updated 7 years ago
- mutil_column CNN for crowd counting☆12Dec 13, 2018Updated 7 years ago
- Pedestrian Datasets, Papers, Resources☆22Sep 11, 2019Updated 7 years ago
- ☆16Oct 31, 2026Updated last week
- Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification☆48May 17, 2018Updated 8 years ago
- TensorFlow Implementation of "Action Recognition using Visual Attention"☆48Aug 16, 2017Updated 9 years ago
- python wrapper for opencv gpu pyramid-lk-flow and tv-l1-flow☆10Jul 15, 2017Updated 9 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Read the skeleton files provided in NTU RGB skeleton dataset and draw the skeleton on the corresponding RGB video.☆18Jul 3, 2019Updated 7 years ago
- ☆13Nov 6, 2021Updated 5 years ago
- Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysis☆12Sep 27, 2018Updated 8 years ago
- ☆107Mar 20, 2018Updated 8 years ago
- ☆16Jun 22, 2017Updated 9 years ago
- The Official PyTorch implementation of "Learning Multi-View Interactional Skeleton Graph for Action Recognition" in TPAMI 2020☆24Mar 28, 2021Updated 5 years ago
- Object detection and classification☆12Oct 19, 2018Updated 8 years ago