cvondrick / vatic
Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces. IJCV 2012
☆604Updated 4 years ago
Related projects: ⓘ
- Video annotation tool for deep learning training labels☆202Updated 5 years ago
- The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"☆999Updated 5 years ago
- Sloth is a tool for labeling image and video data for computer vision research.☆610Updated 4 years ago
- Flow-Guided Feature Aggregation for Video Object Detection☆722Updated 2 years ago
- ROLO is short for Recurrent YOLO, aimed at simultaneous object detection and tracking☆883Updated 7 years ago
- Visipedia Annotation Tools☆280Updated last year
- Python implementation of the IOU Tracker☆691Updated 4 years ago
- Code release for "Detect to Track and Track to Detect", ICCV 2017☆551Updated 6 years ago
- ImageNet 2015 Object Detection from Video (VID)☆369Updated 7 years ago
- Deep Feature Flow for Video Recognition☆1,304Updated 2 years ago
- Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016☆882Updated 4 years ago
- Experimenting with sort different classical tracking algorithms for real time multiple object tracking (MOT)☆438Updated 7 years ago
- Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow☆524Updated 2 years ago
- vatic.js A pure Javascript video annotation tool☆130Updated 6 years ago
- Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition☆502Updated 4 years ago
- A fork of Caffe with OpenMPI-based Multi-GPU (mainly data parallel) support for action recognition and more. More documentation please se…☆551Updated 6 years ago
- Video detection library☆183Updated 7 years ago
- Demo code for PVANet☆651Updated 2 years ago
- A simple tool for labeling object bounding boxes in images☆1,123Updated 4 years ago
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking☆468Updated 4 years ago
- R-FCN with joint training and python support☆1,045Updated 3 years ago
- C3D is a modified version of BVLC caffe to support 3D ConvNets.☆1,161Updated 5 years ago
- Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification☆532Updated 4 years ago
- Download Caltech Pedestrian Dataset and convert them for Python users without using MATLAB☆202Updated 7 years ago
- Cascaded Pyramid Network for Multi-Person Pose Estimation (CVPR 2018)☆792Updated 4 years ago
- Convert between visual object detection datasets☆307Updated 4 years ago
- ☆288Updated this week
- Object Detection☆778Updated 5 years ago
- This is the python-caffe implementation of single object tracking from GOTURN paper☆214Updated 3 years ago
- Joint Detection and Identification Feature Learning for Person Search☆735Updated 4 months ago