gccheng / actiongraph
Action recognition based on action graph, which describes the spatio-temporal relationship between dense trajectory clusters. The program consists of three parts: 1) Dense trajectory extraction based on Wang Heng's CVPR paper; 2) Action graph construction; 3) Video classification based on action recognition.
☆11Updated 9 years ago
Related projects ⓘ
Alternatives and complementary repositories for actiongraph
- Action recognition with STIP features and my own Fisher vector implementation☆14Updated 7 years ago
- Face recognition and segmentation using Python, dlib, and One Millisecond Face Alignment with an Ensemble of Regression Trees.☆15Updated 7 years ago
- My solution to FashionAI Key Points Detection of Apparel.☆13Updated 6 years ago
- Action Recognition & Categories via Spatial-Temporal Features☆31Updated 7 years ago
- Code and models of paper " Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection"…☆27Updated 6 years ago
- Filter multiple pose datasets (coco, flic, lsp, mpii, ai_challenge)☆30Updated 6 years ago
- experiments on classifying actions using poses☆26Updated 6 years ago
- Real-time multi-person pose estimation☆22Updated 6 years ago
- Cross-Platform Annotation Tool for Person Search Datasets☆11Updated 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…☆37Updated 5 years ago
- This is the proposal network for MultiPerson Pose Estimation.☆14Updated 7 years ago
- code for Two-Stream SR-CNNs for Action Recognition in Videos 2016☆34Updated 5 years ago
- contrastive loss for face recognition.The idea is similar to DeepID2, but only in positive pairs.☆12Updated 7 years ago
- The source code for our CVPR 2016 work "Slicing Convolutional Neural Network for Crowd Video Understanding".☆48Updated 8 years ago
- Vivid faces contains a demo of applying FRCNN on mobile platforms for extracting and training facial landmarks and 3D morph animations. C…☆19Updated 5 years ago
- Deep learning mechanism to predict the dense optical flow of every pixel given a static image. This approach considers non-semantic form…☆13Updated 7 years ago
- Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians, CVPR 2016 (Spotlight)☆25Updated 8 years ago
- It is an implementation of the method presented by L. Bourdev (paper is available here http://arxiv.org/pdf/1407.0717v1.pdf)☆9Updated 9 years ago
- ROIAlign from Mask-RCNN☆14Updated 6 years ago
- Master in Computer Vision - M5 Visual recognition☆13Updated 7 years ago
- The Realtime Abnormal Event Detection Project☆13Updated 9 years ago
- Spatio-Temporal Saliency Networks for Dynamic Saliency Prediction☆11Updated 6 years ago
- An approximate but simple implementation of HetConv☆7Updated 5 years ago
- P-CNN: Pose-based CNN Features for Action Recognition☆51Updated 6 years ago
- ☆9Updated 4 years ago
- Training code for the SPPE and SSTN of our RMPE framework☆30Updated 7 years ago
- OpenCourse assignments and projects☆10Updated 6 years ago
- Source code for abnormal detection on MIT video surveillance dataset using Nonnegative Matrix Factorization☆11Updated 4 years ago
- Using Caffe and python to reproduce the results of MTCNN on FDDB dataset.☆17Updated 6 years ago