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
Related projects: ⓘ
- Improved trajectories for action recognition☆22Updated 8 years ago
- Code for "Harvesting Multiple Views for Marker-less 3D Human Pose Annotations", CVPR 2017☆46Updated 7 years ago
- Evaluation code for human pose estimation includes strict PCP, PDJ, and PCK.☆38Updated 8 years ago
- Fast and accurate 3D hand pose estimation from single depth images☆63Updated 7 years ago
- Disentangling Motion, Foreground and Background Features in Videos☆26Updated 6 years ago
- This is the code for our work "Structured Feature Learning for Pose estimation"☆43Updated 7 years ago
- 2D human pose regression☆73Updated 4 years ago
- ☆65Updated 7 years ago
- Demo code for "Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose", CVPR 2017☆81Updated 7 years ago
- ☆37Updated 7 years ago
- Code for the semi-supervised method proposed in our CVPR 2018 paper "Learning Pose Specific Representations by Predicting Different Views…☆60Updated 4 years ago
- source code for Finding Action Tubes, CVPR 2015☆65Updated 8 years ago
- Code for "Predictive-Corrective Networks for Action Detection"☆16Updated 6 years ago
- Caffe: a fast open framework for deep learning.☆16Updated 8 years ago
- ☆18Updated 6 years ago
- Iterative Error Feedback☆55Updated 7 years ago
- Diagnostic tools and additional visualizations from "What Actions are Needed for Understanding Human Actions in Videos?" ICCV 2017☆87Updated 6 years ago
- Wiki for my research notes☆52Updated 6 years ago
- The code for shuttleNet.☆31Updated 7 years ago
- ☆11Updated 7 years ago
- Toolkit for the VLOG dataset☆36Updated 6 years ago
- Code for Temporal Relation Networks☆24Updated 6 years ago
- Training code for "Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose", CVPR 2017☆116Updated 7 years ago
- The project is official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1…☆10Updated 4 years ago
- Pytorch implementation of FlowTrack (Simple Baselines for Human Pose Estimation and Tracking).☆74Updated 5 years ago
- ☆49Updated this week
- GPU implementation of improved dense trajectory☆10Updated 9 years ago
- ☆18Updated this week
- a branc caffe with feature of Data Augmentation using a configurable stochastic combination of 7 data augmentation techniques.☆32Updated 9 years ago