Mambular is a Python package that simplifies tabular deep learning by providing a suite of models for regression, classification, and distributional regression tasks. It includes models such as Mam…

Datasets for remote sensing images (Paper:Exploring Models and Data for Remote Sensing Image Caption Generation)

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

Meta Captioning

Code Release for the paper Segmentation Grounded Scene Graph Generation

A curated list of scene graph generation and related area resources. :-)

TinyTNAS is a hardware-aware, multi-objective, time-bound Neural Architecture Search (NAS) tool designed for TinyML time series classification. Unlike GPU-based NAS methods, it runs efficiently on …

Crowd Sourced Emotional Multimodal Actors Dataset (CREMA-D)

RelTR: Relation Transformer for Scene Graph Generation: https://arxiv.org/abs/2201.11460v2

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiase…

Scene Graph Parsing as Dependency Parsing

A list of awesome remote sensing image captioning resources

Automatically generating language descriptions for remote sensing images has emerged as a significant research area within the field of remote sensing. This project focuses on attention-based capti…

A curated list of awesome vision and language resources for earth observation.

List of datasets, codes, and contests related to remote sensing change detection

RSCaMa: Remote Sensing Image Change Captioning with State Space Model

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

Multimodal Large Language Models for Remote Sensing (RS-MLLMs): A Survey

Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day