Stars
Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.
A JAX research toolkit for building, editing, and visualizing neural networks.
E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.
Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.
Sequence modeling benchmarks and temporal convolutional networks
Human Scene Transformer: A framework for trajectory prediction and wrappers for reframing the JRDB dataset for the prediction task.
Refine high-quality datasets and visual AI models
Scenic: A Jax Library for Computer Vision Research and Beyond
Official Pytorch implementation of 'GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network' (NeurIPS 2020)
Extending SORT's Kalman filter measurement model to add a velocity component derived from Optical Flow.
A General Toolbox for Identifying Object Detection Errors
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).
Official implementation of "MetaSDF: Meta-learning Signed Distance Functions"
This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).
Tools to Design or Visualize Architecture of Neural Network
Learning to Transfer Texture from Clothing Images to 3D Humans, CVPR 2020
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
MOT using deepsort and yolov3 with pytorch
Simultaneous object detection and tracking using center points.
Implementation for the Neural Logic Machines (NLM).
Object detection in images, and tracking across video frames
(IROS 2020, ECCVW 2020) Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics"
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
Experimenting with sort different classical tracking algorithms for real time multiple object tracking (MOT)
Collection of reinforcement learning algorithms