dreamdragon / vatic
An extension to original vatic tools for human action labeling. vatic is an online, interactive video annotation tool for computer vision research that crowdsources work to Amazon's Mechanical Turk. Our tool makes it easy to build massive, affordable video data sets. Written in Python + C + Javascript, vatic is free and open-source software.
☆28Updated 10 years ago
Alternatives and similar repositories for vatic:
Users that are interested in vatic are comparing it to the libraries listed below
- Demo code for "Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose", CVPR 2017☆82Updated 7 years ago
- Evaluation code for human pose estimation includes strict PCP, PDJ, and PCK.☆38Updated 8 years ago
- Disentangling Motion, Foreground and Background Features in Videos☆26Updated 7 years ago
- Fast and accurate 3D hand pose estimation from single depth images☆63Updated 7 years ago
- ☆65Updated 8 years ago
- Iterative Error Feedback☆57Updated 8 years ago
- Training code for "Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose", CVPR 2017☆117Updated 7 years ago
- Code for Temporal Relation Networks☆24Updated 7 years ago
- This is the code for our work "Structured Feature Learning for Pose estimation"☆43Updated 7 years ago
- An open source deep learning action recognition and segmentation framework☆51Updated 7 years ago
- Code for "Harvesting Multiple Views for Marker-less 3D Human Pose Annotations", CVPR 2017☆48Updated 7 years ago
- ☆37Updated 8 years ago
- Improved trajectories for action recognition☆22Updated 9 years ago
- 2D human pose regression☆73Updated 5 years ago
- Code for the semi-supervised method proposed in our CVPR 2018 paper "Learning Pose Specific Representations by Predicting Different Views…☆60Updated 5 years ago
- Diagnostic tools and additional visualizations from "What Actions are Needed for Understanding Human Actions in Videos?" ICCV 2017☆88Updated 7 years ago
- ☆18Updated 7 years ago
- Xi Peng et al. "A Recurrent Encoder-Decoder Network for Sequential Face Alignment", ECCV 2016. (Oral)☆61Updated 8 years ago
- Toolkit for the VLOG dataset☆37Updated 7 years ago
- The code for Recombinator Networks paper.☆59Updated 6 years ago
- Learning Human Optical Flow☆64Updated 6 years ago
- source code for Finding Action Tubes, CVPR 2015☆64Updated 8 years ago
- ☆11Updated 8 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
- The source code of ECCV18 'Flow-Grounded Spatial-Temporal Video Prediction from Still Images'.☆60Updated 6 years ago
- ☆165Updated 7 years ago
- Code for Paper: Self-supervised Learning of Motion Capture☆90Updated 7 years ago
- Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency☆83Updated 6 years ago
- TensorFlow interface for SMPL model. Code by https://github.com/akanazawa/hmr extracted as a separate repo.☆33Updated 6 years ago
- Actionness Estimation Using Hybrid Fully Convolutional Networks☆30Updated 8 years ago