Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Cross Modal Retrieval On Rsicd

Metriken

Image-to-text R@1

Mean Recall

text-to-image R@1

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Image-to-text R@1	Mean Recall	text-to-image R@1	Paper Title	Repository
AMFMN	5.21%	15.53%	4.08%	Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval	-
PE-RSITR (MRS-Adapter)	14.13%	31.12%	11.63%	Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval
HarMA (w/ GeoRSCLIP)	20.52%	38.95%	15.84%	Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment	-
GLISA	20.68%	37.69%	14.73%	Global–Local Information Soft-Alignment for Cross-Modal Remote-Sensing Image–Text Retrieval	-
PIR	9.88%	24.46%	6.97%	A Prior Instruction Representation Framework for Remote Sensing Image-text Retrieval
DOVE	8.66%	22.72%	6.04%	Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval	-
SWAN	7.41%	20.61%	5.56%	Reducing Semantic Confusion: Scene-aware Aggregation Network for Remote Sensing Cross-modal Retrieval
GeoRSCLIP-FT	21.13%	38.87%	15.59%	RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing
RemoteCLIP	18.39%	36.35%	14.73%	RemoteCLIP: A Vision Language Foundation Model for Remote Sensing
GaLR	6.59%	18.96%	4.69%	Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information	-

0 of 10 row(s) selected.