GitHub

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

We are excited to release the CapRL 2.0 series: CapRL-Qwen3VL-2B and CapRL-Qwen3VL-4B. These models feature fewer parameters while delivering even more powerful captioning performance. Notably, ...
IEEE

Tongue Image Segmentation Using Deep Learning for Diagnosis in Traditional Chinese Medicine

Abstract: Tongue image segmentation is important in tongue diagnosis, oral disease diagnosis, and health monitoring in traditional Chinese medicine (TCM). Traditional image segmentation methods ...
GitHub

GeoOSAM - Advanced Segmentation for QGIS

SAM3 ~160MB Auto-segment/Text 0.3-0.7s N/A SAM2.1_T (CPU) ~40MB Fast CPU N/A <1s SAM2.1_B (CPU) ~80MB Balanced CPU N/A 1-2s SAM2.1_L (CPU) ~224MB Quality CPU N/A 2-3s Select a class (Buildings, Water, ...
IEEE

Test-Time Medical Image Segmentation Using CLIP-Guided SAM Adaptation

Abstract: Test-time medical image segmentation is a critical component in clinical practice, enabling pre-trained medical segmentation models to effectively adapt unseen medical samples with potential ...
Frontiers

Image-text guided fundus vessel segmentation via attention mechanism and gated residual ...

Background: Fundus vessel segmentation is crucial for the early diagnosis of ocular diseases. However, existing deep learning-based methods, although effective for detecting coarse vessels, still face ...