https://github.com/BubblyYi/MMPedestron
공식 코드When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Only using RGB cameras for automatic outdoor scene analysis is challenging when, for example, facing insufficient illumination or adverse weather. To improve the recognition reliability, multispectral systems add additional cameras (e.g. infra-red) and perform object detection from multispectral data. Although multispectral scene analysis with deep learning has be shown to have a great potential, there are still many open research questions and it has not been widely deployed in industrial contexts.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset
Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems
Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks
Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection
Cross-Modality Fusion Transformer for Multispectral Object Detection
MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation
ADJUST: A Dictionary-Based Joint Reconstruction and Unmixing Method for Spectral Tomography
UniRGB-IR: A Unified Framework for RGB-Infrared Semantic Tasks via Adapter Tuning
Multispectral Detection Transformer with Infrared-Centric Sensor Fusion
YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework
Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection
$\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
$\mathbf{C}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.