A list of resouces for multispectral pedestrian detection,including the datasets, methods, annotations and tools.

An AI prompt optimizer for writing better prompts and getting better AI results.

Expert Systems With Applications：Shooting condition insensitive unmanned aerial vehicle object detection

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

SCA-LSTM

M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision (ICCV 2025)

[ACM MM 2023 Oral] Multispectral Object Detection via Cross-Modal Conflict-Aware Learning.

This is the official repository for “Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning” (IEEE T-CSVT 2022).

Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning

End-to-End CLIP-driven Mamba Model for Multi-modal Fusion

MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration

Official Repo for MICCAI 25 Paper: Geometry-Guided Local Alignment for Multi-View Visual Language Pre-Training in Mammography

Use visible and infrared images to train the network. This method is better to face the dark environment.

GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding

YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework（Supports RGBT detection for all YOLO series from YOLOv3 to YOLOv13, as well as RTDETR. 【Ultralytics YOLOv…

[ECCV2024, CVPR2025] MambaIR and MambaIRv2!

Lightweight modal-guided cross-attention fusion network for visible-infrared object detection (Pattern Recognition, 2026)

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Reference PyTorch implementation and models for DINOv3

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Code of Paper OmniFuse: Composite Degradation-Robust Image Fusion with Language-Driven Semantics.

Official Code of Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion (CVPR 2024)