From Article to Short-Form Video That Holds Attention

Learn how to convert existing articles into short-form video scripts using platform-tested structures, retention strategies, ...
IEEE

Text-Driven Medical Image Segmentation With Text-Free Inference via Knowledge Distillation

Abstract: Medical image segmentation plays a pivotal role in ensuring accurate diagnosis. Traditional methods are predominantly monomodal, relying solely on image data. These image-only methods ...
GitHub

️ wtpsplit-lite

🪓 wtpsplit is a Python package that offers training, inference, and evaluation of state-of-the-art Segment any Text (SaT) models for partitioning text into sentences. ️ wtpsplit-lite is a lightweight ...
IEEE

Grounding DINO-US-SAM: Text-Prompted Multiorgan Segmentation in Ultrasound With LoRA-Tuned Vision–Language Models

Abstract: Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated data. In ...
Frontiers

Deep learning-enabled hybrid systems for accurate recognition of text in seal images

Chinese seals are widely used in various fields within Chinese society as a tool for certifying legal documents. However, recognizing text on these seals presents challenges due to background text, ...