Results 61 to 70 of about 57,569 (167)

Decoupling Continual Semantic Segmentation

Proceedings of the AAAI Conference on Artificial Intelligence
Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods typically employ single-stage encoder-decoder architectures where segmentation masks and class labels are tightly ...
Yifu Guo, Yuquan Lu, Wentao Zhang 0005, Zishan Xu, Dexia Chen, Siyu Zhang, Yizhe Zhang 0001, Ruixuan Wang   +7 more
openaire   +2 more sources

Semantic Segmentation For Aerial Images

International Journal of Research Publication and Reviews
Semantic segmentation of aerial imagery plays a critical role in modern urban planning, environmental monitoring, and the development of smart cities. This project presents an interactive webbased application that performs semantic segmentation on high-resolution aerial images using a deep learning-based U-Net model.
Dr. B. Harika, M. Bharath, K. Himneesh
openaire   +2 more sources

Globally optimal breast mass segmentation from DCE-MRI using deep semantic segmentation as shape prior

, 2017
We introduce a new fully automated breast mass segmentation method from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). The method is based on globally optimal inference in a continuous space (GOCS) using a shape prior computed from a ...
Maicas, Gabriel, Bradley, Andrew P., Carneiro, Gustavo, Andrew P. Bradley, Gustavo Carneiro, Gabriel Maicas   +5 more
core   +1 more source

Text-based Semantic Annotation Service for Multimedia Content in the Esperonto project

, 2004
Within the Esperonto project, an integration of NLP, ontologies and other knowledge bases, is being performed with the goal to implement a semantic annotation service that upgrades the actual Web towards the emerging Semantic Web.
Corcho, Oscar, Contreras, Jesús, Crispi, C., Declerck, T.   +3 more
core  

Thai word segmentation for visualization of Thai Web sites

, 2011
Information overload is a problem in the Information Age and Information visualization is an approach to provide an overview of the content of a web site. Tag cloud is one of the ways to represent information as an image of a group of words.
Wigrai Thanadechteemapat, Chun-Che Fung, Fung, C.C., Thanadechteemapat, W.   +3 more
core   +1 more source

Semantic-Fast-SAM: Efficient Semantic Segmenter

2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
APSIPA ASC ...
openaire   +2 more sources

Semantic, Automatic Image Annotation Based On Multi-Layered Active Contours and Decision Trees

, 2013
In this paper, we propose a new approach for automatic image annotation (AIA) in order to automatically and efficiently assign linguistic concepts to visual data such as digital images, based on both numeric and semantic features.
Olszewska, Joanna Isabelle
core  

The Semantic Logger: Supporting Service Building from Personal Context

, 2006
The Semantic Logger SL) is presentedas a system for the importing, housing, and exploiting of personal information. The system has been implemented using a number of Semantic Web enabling technologies, and attempts to store the information in a manner ...
Shadbolt, Nigel R., Tuffield, Mischa M, Loizou, Antonis, Dupplaw, David, Dasmahapatra, Srinandan, Lewis, Paul H., Millard, David E.   +6 more
core  

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the hyperbolic radius as an indicator of data scarcity.
Luca Franco, Konstantinos Kallidromitis, Devin Guillory, Yu-Teng Li, Paolo Mandica, Trevor Darrell, Fabio Galasso   +6 more
core  

Automatic texture segmentation for content-based image retrieval application

, 2006
In this article, a brief review on texture segmentation is presented, before a novel automatic texture segmentation algorithm is developed. The algorithm is based on a modified discrete wavelet frames and the mean shift algorithm.
Fauzi, M.F.A., Fauzi, Mohammad Faizal Ahmad, Lewis, P.H., Lewis, Paul H.   +3 more
core   +1 more source