Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
Referring Video Object Segmentation (RVOS) addresses the task of segmenting target objects described by textual descriptions from videos. In order to ensure the consistency of objects segmented from video frames, inter-frame modeling is adopted to ca...
Neural networks : the official journal of the International Neural Network Society
Sep 1, 2025
In the field of real-time stereo matching, a concise and informative cost volume is crucial for achieving high efficiency and accuracy. To this end, in this paper, we propose the Tri-Fusion Volume (TFV) to effectively fuse both texture details and si...
Studies in health technology and informatics
Aug 7, 2025
In order to utilize clinical notes for research studies, it is necessary to identify the most relevant notes. Mapping to the LOINC Document Ontology makes this process easier by reducing the variability of note types. We experimented with three model...
Accurate recognition of human motion intention (HMI) is beneficial for exoskeleton robots to improve the wearing comfort level and achieve natural human-robot interaction. A classifier trained on labeled source subjects (domains) performs poorly on u...
BACKGROUND: Circumcision is a prevalent surgical procedure performed for medical, cultural, and religious reasons, requiring a thorough assessment of penile anatomy to determine eligibility, especially for identifying contraindications such as congen...
Neural networks : the official journal of the International Neural Network Society
Jul 1, 2025
Images degraded by geometric distortions pose a significant challenge to imaging and computer vision tasks such as object recognition. Deep learning-based imaging models usually fail to give accurate performance for geometrically distorted images. In...
Neural networks : the official journal of the International Neural Network Society
Jul 1, 2025
Recently, transformer-based methods have shown remarkable success in object re-identification. However, most works directly embed off-the-shelf transformer backbones for feature extraction. These methods treat all patch tokens equally, ignoring the d...
Neural networks : the official journal of the International Neural Network Society
Jul 1, 2025
Large language models (LLMs) roughly encode a sentence into a dense representation (a vector), which mixes up the semantic expression of all named entities within a sentence. So the decoding process is easily overwhelmed by sentence-specific informat...
Neural networks : the official journal of the International Neural Network Society
Jul 1, 2025
Benefiting from the booming development of Transformer methods, the performance of lane detection tasks has been rapidly improved. However, due to the influence of inaccurate lane line shape constraints, the query sequences of existing transformer-ba...
Neural networks : the official journal of the International Neural Network Society
Jul 1, 2025
Semi-supervised learning methods have wide applications thanks to the reasonable utilization for a part of label information of data. In recent years, non-negative matrix factorization (NMF) has received considerable attention because of its interpre...
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.