LAUSR

Text-Driven Medical Image Segmentation with LLM Semantic Bridge and LLM Prompt Bridge

Sign Up to like & get
recommendations!
0 Published in 2025 at "IEEE Signal Processing Letters"

DOI: 10.1109/lsp.2025.3639352

Abstract: Text-driven medical image segmentation aims to accurately segment pathological regions in medical images based on textual descriptions. Existing methods face two major challenges: (a) The significant modality heterogeneity between textual and visual features leads to… read more here.

Keywords: bridge; text driven; llm; driven medical ... See more keywords

Text-Driven Adaptive Semantic Alignment Network for Cross-Scene Hyperspectral Image Classification

Sign Up to like & get
recommendations!
0 Published in 2025 at "IEEE Transactions on Geoscience and Remote Sensing"

DOI: 10.1109/tgrs.2025.3548607

Abstract: Land cover in different scenes generally exhibits scene-invariant category semantic, typically represented and described consistently in a textual modality. Traditional cross-scene classification methods often treat categories as discrete class labels, neglecting their semantic information, or… read more here.

Keywords: classification; text driven; scene; cross scene ... See more keywords

Zero-Shot Text-Driven Dynamic Neural Radiance Fields Stylization

Sign Up to like & get
recommendations!
0 Published in 2025 at "IEEE Transactions on Multimedia"

DOI: 10.1109/tmm.2025.3565983

Abstract: Text-driven style transfer for Neural Radiance Fields (NeRFs) is an emerging research topic that leverages text descriptions instead of reference style images to apply style transfer. However, existing methods for stylizing NeRFs predominantly struggle to… read more here.

Keywords: text driven; style; zero shot; neural radiance ... See more keywords

GUESS: GradUally Enriching SyntheSis for Text-Driven Human Motion Generation

Sign Up to like & get
recommendations!
0 Published in 2024 at "IEEE Transactions on Visualization and Computer Graphics"

DOI: 10.1109/tvcg.2024.3352002

Abstract: In this article, we propose a novel cascaded diffusion-based generative framework for text-driven human motion synthesis, which exploits a strategy named GradUally Enriching SyntheSis (GUESS as its abbreviation). The strategy sets up generation objectives by… read more here.

Keywords: text driven; human motion; generation; synthesis ... See more keywords