Tech Xplore

An AI approach for single-image-based 3D character animation with preserved proportions

In Proceedings of the SIGGRAPH Asia 2025 Conference Papers, a research team affiliated with UNIST reports a new AI technology ...
IEEE

Exploring Generalizable Distillation for Efficient Medical Image Segmentation

Abstract: Efficient medical image segmentation aims to provide accurate pixel-wise predictions with a lightweight implementation framework. However, existing lightweight networks generally overlook ...
IEEE

Bilateral Knowledge Interaction Network for Referring Image Segmentation

Abstract: Referring image segmentation aims to segment objects that are described by natural language expressions. Although remarkable advancements have been made to align natural language expressions ...

A zero-shot learning framework for maize cob phenotyping

A new study presents a zero-shot learning (ZSL) framework for maize cob phenotyping, enabling the extraction of geometric ...
GitHub

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...