sjtuytc Goto Github PK

aaai21-routineaugmentedpolicylearning

Source code to the AAAI21 publication Augmenting Policy Learning with Routines Discovered from a Single Demonstration

ai2thor

An open-source platform for Visual AI.

am5749_sch

pdf release of AM5749_Sch

awesome-6d-object

Awesome work on object 6 DoF pose estimation

awesome-program

A curated list of papers related to program synthesis, program induction, program execution, program and code repair, and programmatic reinforcement learning.

awesome-visual-question-answering

A curated list of Visual Question Answering(VQA)(Image/Video Question Answering),Visual Question Generation ,Visual Dialog ,Visual Commonsense Reasoning and related area.

awesome-visual-transformer

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

barcodes

Estimate quality parameters for several images of linear barcodes according to the specific ISO/IEC 15416.

betapose

Betapose for 6D pose estimation

bottom-up-attention.pytorch

An PyTorch reimplementation of bottom-up-attention models

bytetrack

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

chinavis2019_proj

Analysis Transportation of Chengdu (Winner in ChinaVis 2019)

classified-transformer-papers

transformer papers with their classified ideas, links, and main ideas

cuhk-csci-2017-2021-course-source-repository

CUHK CSCI students shared course data, from lecture notes to homework source codes.

dqn_mountaincar

A simple implementation of DQN

elevator-marl

Asynchronous Elevator Control Simulator + Multi-Agent Reinforcement Learning training algorithms

fairmot

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

fungus

An easy to use Unity 3D library for creating illustrated Interactive Fiction games

kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

lab

A customisable 3D platform for agent-based AI research

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

mmaction2

OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark

mmtracking

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

models

Models and examples built with TensorFlow

motr

mulfagrid-web

Website of MulFAGrid

neurips21-proto-program-guided-transformers-for-program-guided-tasks

Official code repo for "ProTo: program-guided Transformers for Program-guided Tasks

neurips_visualization

visualize neurips submission material

opencv_3rdparty

OpenCV - 3rdparty

oscar

Oscar and VinVL