FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1609306619> ?p ?o ?g. }

• W1609306619 endingPage "5287" @default.
• W1609306619 startingPage "5274" @default.
• W1609306619 abstract "We present a new method for tracking human pose by employing max-margin Markov models. Representing a human body by part-based models, such as pictorial structure, the problem of pose tracking can be modeled by a discrete Markov random field. Considering max-margin Markov networks provide an efficient way to deal with both structured data and strong generalization guarantees, it is thus natural to learn the model parameters using the max-margin technique. Since tracking human pose needs to couple limbs in adjacent frames, the model will introduce loops and will be intractable for learning and inference. Previous work has resorted to pose estimation methods, which discard temporal information by parsing frames individually. Alternatively, approximate inference strategies have been used, which can overfit to statistics of a particular data set. Thus, the performance and generalization of these methods are limited. In this paper, we approximate the full model by introducing an ensemble of two tree-structured sub-models, Markov networks for spatial parsing and Markov chains for temporal parsing. Both models can be trained jointly using the max-margin technique, and an iterative parsing process is proposed to achieve the ensemble inference. We apply our model on three challengeable data sets, which contains highly varied and articulated poses. Comprehensive experimental results demonstrate the superior performance of our method over the state-of-the-art approaches." @default.
• W1609306619 created "2016-06-24" @default.
• W1609306619 creator A5039507264 @default.
• W1609306619 creator A5056569344 @default.
• W1609306619 creator A5068918243 @default.
• W1609306619 creator A5074103823 @default.
• W1609306619 date "2015-12-01" @default.
• W1609306619 modified "2023-10-14" @default.
• W1609306619 title "Tracking Human Pose Using Max-Margin Markov Models" @default.
• W1609306619 cites W1514928307 @default.
• W1609306619 cites W1970565565 @default.
• W1609306619 cites W1980369287 @default.
• W1609306619 cites W1981095481 @default.
• W1609306619 cites W1993149133 @default.
• W1609306619 cites W1994529670 @default.
• W1609306619 cites W2000088621 @default.
• W1609306619 cites W2013640163 @default.
• W1609306619 cites W2022215984 @default.
• W1609306619 cites W2022699039 @default.
• W1609306619 cites W2024387934 @default.
• W1609306619 cites W2026720449 @default.
• W1609306619 cites W2030536784 @default.
• W1609306619 cites W2031248101 @default.
• W1609306619 cites W2035299679 @default.
• W1609306619 cites W2037513725 @default.
• W1609306619 cites W2044038178 @default.
• W1609306619 cites W2044291182 @default.
• W1609306619 cites W2049768550 @default.
• W1609306619 cites W2052447093 @default.
• W1609306619 cites W2074587583 @default.
• W1609306619 cites W2080353936 @default.
• W1609306619 cites W2086482135 @default.
• W1609306619 cites W2091098068 @default.
• W1609306619 cites W2093949207 @default.
• W1609306619 cites W2095340493 @default.
• W1609306619 cites W2099305880 @default.
• W1609306619 cites W2099333815 @default.
• W1609306619 cites W2103015390 @default.
• W1609306619 cites W2118025528 @default.
• W1609306619 cites W2120458963 @default.
• W1609306619 cites W2121674447 @default.
• W1609306619 cites W2122346146 @default.
• W1609306619 cites W2124864523 @default.
• W1609306619 cites W2128271252 @default.
• W1609306619 cites W2131263044 @default.
• W1609306619 cites W2137549153 @default.
• W1609306619 cites W2141218264 @default.
• W1609306619 cites W2143158307 @default.
• W1609306619 cites W2150383810 @default.
• W1609306619 cites W2151057099 @default.
• W1609306619 cites W2154624311 @default.
• W1609306619 cites W2157939923 @default.
• W1609306619 cites W2161969291 @default.
• W1609306619 cites W2168356304 @default.
• W1609306619 cites W2407348013 @default.
• W1609306619 cites W2429914308 @default.
• W1609306619 cites W4249022109 @default.
• W1609306619 doi "https://doi.org/10.1109/tip.2015.2473662" @default.
• W1609306619 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26336122" @default.
• W1609306619 hasPublicationYear "2015" @default.
• W1609306619 type Work @default.
• W1609306619 sameAs 1609306619 @default.
• W1609306619 citedByCount "22" @default.
• W1609306619 countsByYear W16093066192016 @default.
• W1609306619 countsByYear W16093066192017 @default.
• W1609306619 countsByYear W16093066192018 @default.
• W1609306619 countsByYear W16093066192019 @default.
• W1609306619 countsByYear W16093066192020 @default.
• W1609306619 countsByYear W16093066192021 @default.
• W1609306619 countsByYear W16093066192022 @default.
• W1609306619 crossrefType "journal-article" @default.
• W1609306619 hasAuthorship W1609306619A5039507264 @default.
• W1609306619 hasAuthorship W1609306619A5056569344 @default.
• W1609306619 hasAuthorship W1609306619A5068918243 @default.
• W1609306619 hasAuthorship W1609306619A5074103823 @default.
• W1609306619 hasConcept C105795698 @default.
• W1609306619 hasConcept C115961682 @default.
• W1609306619 hasConcept C119857082 @default.
• W1609306619 hasConcept C124504099 @default.
• W1609306619 hasConcept C134306372 @default.
• W1609306619 hasConcept C153180895 @default.
• W1609306619 hasConcept C154945302 @default.
• W1609306619 hasConcept C159886148 @default.
• W1609306619 hasConcept C163836022 @default.
• W1609306619 hasConcept C177148314 @default.
• W1609306619 hasConcept C186644900 @default.
• W1609306619 hasConcept C22019652 @default.
• W1609306619 hasConcept C23224414 @default.
• W1609306619 hasConcept C2776214188 @default.
• W1609306619 hasConcept C2778045648 @default.
• W1609306619 hasConcept C33923547 @default.
• W1609306619 hasConcept C41008148 @default.
• W1609306619 hasConcept C50644808 @default.
• W1609306619 hasConcept C774472 @default.
• W1609306619 hasConcept C98763669 @default.
• W1609306619 hasConceptScore W1609306619C105795698 @default.
• W1609306619 hasConceptScore W1609306619C115961682 @default.
• W1609306619 hasConceptScore W1609306619C119857082 @default.

• next