Browsing Computer Vision Group by Title
Now showing items 23-42 of 43
-
Multifeature analysis and semantic context learning for image classification
(ACM New York, NY, USA, 2013-05)This article introduces an image classification approach in which the semantic context of images and multiple low-level visual features are jointly exploited. The context consists of a set of semantic terms defining the ... -
Open-world Person Re-Identification by Multi-Label Assignment Inference.
(BMVA Press, 2014) -
Optimal kernel choice for domain adaption learning
(2016-05-01)© 2016 Elsevier Ltd. All rights reserved. In this paper, a kernel choice method is proposed for domain adaption, referred to as Optimal Kernel Choice Domain Adaption (OKCDA). It learns a robust classier and parameters ... -
Re-id: Hunting Attributes in the Wild.
(BMVA Press, 2014) -
Scalable DB+IR Technology: Processing Probabilistic Datalog with HySpirit.
(2016)Probabilistic Datalog (PDatalog, proposed in 1995) is a probabilistic variant of Datalog and a nice conceptual idea to model Information Retrieval in a logical, rule-based programming paradigm. Making PDatalog work in ... -
Transductive Multi-view Zero-Shot Learning
(2015-03-03) -
Transductive Multi-View Zero-Shot Learning
(2015-11) -
Unsupervised learning of generative topic saliency for person re-identification
(2014-01-01)© 2014. The copyright of this document resides with its authors. Existing approaches to person re-identification (re-id) are dominated by supervised learning based methods which focus on learning optimal similarity distance ... -
Wearable wireless tactile display for virtual interactions with soft bodies.
(2014)We describe here a wearable, wireless, compact, and lightweight tactile display, able to mechanically stimulate the fingertip of users, so as to simulate contact with soft bodies in virtual environments. The device was ...