Alena's repositories
MinkowskiEngine
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
AOT
Associating Objects with Transformers for Video Object Segmentation
aot-benchmark
An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch
CLIP4Clip
An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"
cornerstone
JavaScript library to display interactive medical images including but not limited to DICOM
CSF
LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation
deepdetect
Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
EasyNLP
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
ffmpegcv
The ffmpegcv is a ffmpeg backbone for open-cv like Video Reader and Writer
flv.js
HTML5 FLV Player
imgaug
Image augmentation for machine learning experiments.
ImprovedAssociationTrack-cpp
C++ implementation of An Improved Association Pipeline for Multi-Person Tracking
kalibr
The Kalibr visual-inertial calibration toolbox
label-studio-frontend
Data labeling react app that is backend agnostic and can be embedded into your applications — distributed as an NPM package
learnopencv
Learn OpenCV : C++ and Python Examples
lift-splat-shoot
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
nginx-rtmp-module
NGINX-based Media Streaming Server
OC_SORT_CPP
OC_SORT implemented in C++ with Eigen Library
PPDM
Code for "PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection".
pycuda
CUDA integration for Python, plus shiny features
pytracking
Visual tracking library based on PyTorch.
sara
Easy-to-Use C++ Computer Vision Library
segment-anything-webui
Yet another SAM webui + CLIP
Segment-Everything-Everywhere-All-At-Once
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
SGDiff
Official implementation for "Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training" https://arxiv.org/abs/2211.11138
siam-mot
SiamMOT: Siamese Multi-Object Tracking
webui-aria2
The aim for this project is to create the worlds best and hottest interface to interact with aria2. Very simple to use, just download and open index.html in any web browser.
YOLO3D
YOLO 3D Object Detection for Autonomous Driving Vehicle