000751539 000__ 02962cam\a2200517Ii\4500
000751539 001__ 751539
000751539 005__ 20230306141255.0
000751539 006__ m\\\\\o\\d\\\\\\\\
000751539 007__ cr\cn\nnnunnun
000751539 008__ 140819t20152015si\a\\\\ob\\\\000\0\eng\d
000751539 019__ $$a892800356
000751539 020__ $$a9789812871671$$q(electronic book)
000751539 020__ $$a9812871675$$q(electronic book)
000751539 020__ $$z9812871667
000751539 020__ $$z9789812871664
000751539 0247_ $$a10.1007/978-981-287-167-1$$2doi
000751539 035__ $$aSP(OCoLC)ocn887843463
000751539 035__ $$aSP(OCoLC)887843463$$z(OCoLC)892800356
000751539 040__ $$aN$T$$beng$$erda$$epn$$cN$T$$dGW5XE$$dCOO$$dYDXCP$$dE7B$$dOCLCF$$dMYG$$dCDX$$dEBLCP$$dDEBSZ$$dWAU$$dVLB$$dOCLCQ
000751539 049__ $$aISEA
000751539 050_4 $$aQA166.2$$b.Y8 2015eb
000751539 08204 $$a511.52$$223
000751539 1001_ $$aYu, Gang,$$eauthor.
000751539 24510 $$aHuman action analysis with randomized trees$$h[electronic resource] /$$cGang Yu, Junsong Yuan, Zicheng Liu.
000751539 264_1 $$aSingapore :$$bSpringer Verlag,$$c[2015]
000751539 264_4 $$c©2015
000751539 300__ $$a1 online resource :$$bcolor illustrations.
000751539 336__ $$atext$$btxt$$2rdacontent
000751539 337__ $$acomputer$$bc$$2rdamedia
000751539 338__ $$aonline resource$$bcr$$2rdacarrier
000751539 4901_ $$aSpringer briefs in electrical and computer engineering. Signal processing
000751539 504__ $$aIncludes bibliographical references.
000751539 5050_ $$aIntroduction to Human Action Analysis -- Supervised Trees for Human Action Recognition and Detection -- Unsupervised Trees for Human Action Search -- Propagative Hough Voting to Leverage Contextual Information -- Human Action Prediction with Multi-class Balanced Random Forest -- Conclusion.
000751539 506__ $$aAccess limited to authorized users.
000751539 520__ $$aThis book will provide a comprehensive overview on human action analysis with randomized trees. It will cover both the supervised random trees and the unsupervised random trees. When there are sufficient amount of labeled data available, supervised random trees provides a fast method for space-time interest point matching. When labeled data is minimal as in the case of example-based action search, unsupervised random trees is used to leverage the unlabelled data. We describe how the randomized trees can be used for action classification, action detection, action search, and action prediction. We will also describe techniques for space-time action localization including branch-and-bound sub-volume search and propagative Hough voting.
000751539 588__ $$aOnline resource; title from PDF title page (viewed Aug. 19, 2014).
000751539 650_0 $$aTrees (Graph theory)
000751539 650_0 $$aHuman behavior$$xResearch.
000751539 7001_ $$aYuan, Junsong,$$eauthor.
000751539 7001_ $$aLiu, Zicheng,$$d1965-$$eauthor.
000751539 77608 $$iPrint version:$$z9789812871664
000751539 830_0 $$aSpringerBriefs in electrical and computer engineering.$$pSignal processing.
000751539 85280 $$bebk$$hSpringerLink
000751539 85640 $$3SpringerLink$$uhttps://univsouthin.idm.oclc.org/login?url=http://link.springer.com/10.1007/978-981-287-167-1$$zOnline Access$$91397441.1
000751539 909CO $$ooai:library.usi.edu:751539$$pGLOBAL_SET
000751539 980__ $$aEBOOK
000751539 980__ $$aBIB
000751539 982__ $$aEbook
000751539 983__ $$aOnline
000751539 994__ $$a92$$bISE