000160453 001__ 160453
000160453 005__ 20190316235002.0
000160453 02470 $$2ISI$$a000260656000005
000160453 037__ $$aCONF
000160453 245__ $$aKeypoint Signatures for Fast Learning and Recognition
000160453 269__ $$a2008
000160453 260__ $$bSpringer-Verlag New York, Ms Ingrid Cunningham, 175 Fifth Ave, New York, Ny 10010 Usa$$c2008
000160453 336__ $$aConference Papers
000160453 490__ $$aLecture Notes In Computer Science
000160453 520__ $$aStatistical learning techniques have been used to dramatically speed-up keypoint matching by training a classifier to recognize a specific set of keypoints. However, the training itself is usually relatively slow and performed offline. Although methods have recently been proposed to train the classifier online, they can only learn a very limited number of new keypoints. This represents a handicap for real-time applications, such as Simultaneous Localization and Mapping (SLAM), which require incremental addition of arbitrary numbers of keypoints as they become visible.
000160453 6531_ $$aRandomized Trees
000160453 700__ $$0242711$$g172803$$aCalonder, Michael
000160453 700__ $$0240235$$g149007$$aLepetit, Vincent
000160453 700__ $$0240252$$g112366$$aFua, Pascal
000160453 7112_ $$dOct 12-18, 2008$$cMarseille, FRANCE$$aEuropean Conference on Computer Vision 
000160453 773__ $$j5302$$tComputer Vision - Eccv 2008, Pt I, Proceedings$$q58-71
000160453 8564_ $$uhttps://infoscience.epfl.ch/record/160453/files/top.pdf$$zn/a$$s1970856$$yn/a
000160453 909C0 $$xU10659$$0252087$$pCVLAB
000160453 909CO $$qGLOBAL_SET$$pconf$$ooai:infoscience.tind.io:160453$$pIC
000160453 917Z8 $$xWOS-2010-11-30
000160453 917Z8 $$x112366
000160453 937__ $$aEPFL-CONF-160453
000160453 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000160453 980__ $$aCONF