Research
Official repository for TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.
Implementation of 'Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization' [CVPR 2021]
Code refactoring for paper "Domain Generalization with Adversarial Feature Learning" in VLCS datasets.
ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization 🚁 annotates 1652 buildings in 72 universities around the world.
ECCV 2024 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2024论文和开源项目
ACCV 2022 oral "CVLNet: Cross-View Semantic Correspondence Learning for \\Video-based Camera Localization"
MLNLP社区用来更好进行论文搜索的工具。Fully-automated scripts for collecting AI-related papers
Open source Structure-from-Motion pipeline
Official implementation of paper Gradient Matching for Domain Generalization
Official code repository for NeurIPS 2022 paper "SatMAE: Pretraining Transformers for Temporal and Multi-Spectral Satellite Imagery"
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)
[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"
A survey of occlusion handling in object detection
SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts
Learn the language basics in this 10-part course.
End-to-End Object Detection with Transformers
Download Datasets and Ground Truths: https://github.com/TuSimple/tusimple-benchmark/issues/3
A simple, fully convolutional model for real-time instance segmentation.
This repository is for the first comprehensive survey on Meta AI's Segment Anything Model (SAM).
OpenMMLab Rotated Object Detection Toolbox and Benchmark