🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

[NeurIPS'25] Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Latest Papers, Codes and Datasets on VTG-LLMs.

"VideoAgent: All-in-One Agentic Framework for Video Understanding, Editing, and Remaking"

Fully Open Framework for Democratized Multimodal Training

Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

3d building geometry viewer based on OpenStreetMap data

Code for Neural Plasticity-Inspired Foundation Model for Observing the Earth Crossing Modalities

Lightning-UQ-Box: Uncertainty Quantification for Neural Networks with PyTorch and Lightning

3D adaptive binary space partitioning and beyond [JOSS]

A curated list of foundation models for vision and language tasks

SSL4EO-S12: a large-scale dataset for self-supervised learning in Earth observation

Official implementation of TGRS paper: "Pseudo Features Guided Self-training for Domain Adaptive Semantic Segmentation of Satellite Images"

Stable Diffusion web UI

RSVG: Exploring Data and Model for Visual Grounding on Remote Sensing Data, 2022

Source code for CVPR 2022 paper Sylph A Hypernetwork Framework for Few-shot Object Detection

[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

[NeurIPS 2021] LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

OpenMMLab Detection Toolbox and Benchmark

Image/Scene Classification for RemoteSensing Images;Officail Repo for the EarthNets Platform. https://arxiv.org/pdf/2210.04936.pdf

Officail Repo for the EarthNets Platform. https://ieeexplore.ieee.org/abstract/document/10731951

Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.

An application for mosaicing remote sensing images 🛰️ [Project definitively moved in OTB the 06/2019]

PyTorch dataset extended with map, cache etc. (tensorflow.data like)

Packages intended to assist in the preprocessing of SpaceNet satellite imagery data corpus to a format that is consumable by machine learning algorithms.