HY's repositories
AcurusTrack
A multi-object tracking component. Works in the conditions where identification and classical object trackers don't (e.g. shaky/unstable camera footage, occlusions, motion blur, covered faces, etc.). Works on any object despite their nature.
baby-vision
Self-supervised learning through the eyes of a child
BlurbGenreCollection-HMC
Hierarchical multi-label text classification of the BlurbGenreCollection using capsule networks.
convolutional_occupancy_networks
[ECCV'20] Convolutional Occupancy Networks
core
Production scale vision AI platform, with fully integrated components for model building, automated labeling, data processing and model training pipelines.
DeepCamera
Protect your privacy, open source AI-powered video surveillance on Android, featuring face recognition, human shape recognition(ReID), etc. The world's first AutoML Deep Learning edge AI platform. No programming exp needed to train a new model for your privacy.
deformation_aware_embedding
Deformation-Aware 3D Model Embedding and Retrieval, ECCV 2020
Detectron2DeepSortPlus
Egocentric Hand Detection, Identification, Segmentation and Tracking
EvenVizion
Camera localization and video stabilization component. Fixed coordinates system. Using Python and OpenCV.
Generative-3D-Part-Assembly
NeurIPS 2020
GeoTrackNet
A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection
InterHand2.6M
Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020
lambda-networks
Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute
landcover
Land Cover Mapping
lift-splat-shoot
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
MultispectralPedestrianDetection
Code, detections, and plots related to our research in multispectral pedestrian detection.
NOL
An official implementation of the paper, Neural Object Learning for 6D Pose Estimation Using a Few Cluttered Images
OMG-Planner
An Optimization-based Motion and Grasp Planner
psi
Platform for Situated Intelligence
pyHGT
Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on pytorch_geometric
pytorch_active_learning
PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book
RobustChangeCaptioning
Code and dataset release for Park et al., Robust Change Captioning (ICCV 2019)
se3-transformer-public
code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503
Self6D-Diff-Renderer
The differentiable rendering code for "Self6D: Self-Supervised Monocular 6D Object Pose Estimation (ECCV 2020)"
SketchGraphs
A dataset of 15 million CAD sketches with geometric constraint graphs.
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
WIMP
[arXiv] What-If Motion Prediction for Autonomous Driving ❓🚗💨