Sciweavers

800 search results - page 95 / 160
» Extracting Structures in Image Collections for Object Recogn...
Sort
View
CVPR
2007
IEEE
14 years 9 months ago
Learning and Matching Line Aspects for Articulated Objects
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...
Xiaofeng Ren
ICMCS
2005
IEEE
169views Multimedia» more  ICMCS 2005»
14 years 1 months ago
Dynamic language model adaptation using latent topical information and automatic transcripts
This paper considers dynamic language model adaptation for Mandarin broadcast news recognition. Both contemporary newswire texts and in-domain automatic transcripts were exploited...
Berlin Chen
RAS
2008
112views more  RAS 2008»
13 years 7 months ago
Learning and generalising semantic knowledge from object scenes
The robot described in this paper learns words that relate to objects and their attributes and also learns concepts, which may be recursive, that involve relationships between sev...
Claire D'Este, Claude Sammut
CRV
2011
IEEE
337views Robotics» more  CRV 2011»
12 years 7 months ago
Object Detection Using Principal Contour Fragments
Abstract—Contour features play an important role in object recognition. Psychological experiments have shown that maximum-curvature points are most distinctive along a contour [6...
Changhai Xu, Benjamin Kuipers
WWW
2009
ACM
14 years 2 months ago
Mining cultural differences from a large number of geotagged photos
We propose a novel method to detect cultural differences over the world automatically by using a large amount of geotagged images on the photo sharing Web sites such as Flickr. W...
Keiji Yanai, Bingyu Qiu