zhoukang123's repositories
SDTNet_2022
spatial decision transofmer network for visual navigation via renforcement learning
ai2thor-triples-scraper
Code to mine triples from AI2Thor
Person_reID_baseline_pytorch
:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
ReID-Survey
Deep Learning for Person Re-identification: A Survey and Outlook
awesome-embodied-vision
Reading list for research topics in embodied vision
Co-NavGPT
We proposed to explore and search for the target in unknown environment based on Large Language Model for multi-robot system.
Demand-driven-navigation
Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation
depth_renderer
Rendering color and depth images for ShapeNet models.
fast-reid
SOTA Re-identification Methods and Toolbox
HOZ
Hierarchical Object-to-Zone Graph for Object Navigation
L3MVN
Leveraging Large Language Models for Visual Target Navigation
minimalRL
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
MJOLNIR
Python implementation of the paper Learning hierarchical relationships for object-goal navigation
MLwithWebSecurity
Using DBN,lstm,svm,cnn,rnn,nb,rf ect to build deep learning model applied in websecurity such as dga kddcup xss etc
models
Models and examples built with TensorFlow
MonoRUn
[CVPR'21] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
NavGPT
[AAAI 2024] Official implementation of NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models
prophet
Implementation of CVPR 2023 paper "Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering".
pyrobot
PyRobot: An Open Source Robotics Research Platform
Target-Driven-Visual-Navigation-with-Distributed-PPO
This repository has used AI2THOR CVPR data set.
VLN-BEVBert
[ICCV 2023} Official repo of "BEVBert: Multimodal Map Pre-training for Language-guided Navigation"