Matches in SemOpenAlex for { <https://semopenalex.org/work/W2734178003> ?p ?o ?g. }
- W2734178003 abstract "This work introduces a novel Convolutional Networkarchitecture (ConvNet) for the task of human poseestimation, that is the localization of body joints in a singlestatic image. The proposed coarse to fine architecture addressesshortcomings of the baseline architecture that stem from thefact that large inaccuracies of its coarse ConvNet cannot becorrected by the refinement ConvNet that refines the estimationwithin small windows of the coarse prediction. This is achievedby a) changes in architectural parameters that both increase theaccuracy of the coarse model and make the refinement modelmore capable of correcting the errors of the coarse model,b) the introduction of a Markov Random Field (MRF)-basedspatial model network between the coarse and the refinementmodel that introduces geometric constraints and c) a trainingscheme that adapts the data augmentation and the learning rateaccording to the difficulty of the data examples. The proposedarchitecture is trained in an end-to-end fashion. Experimentalresults show that the proposed method improves the baselinemodel and provides state of the art results on the FashionPose[8] and MPII benchmarks [1]." @default.
- W2734178003 created "2017-07-14" @default.
- W2734178003 creator A5031205865 @default.
- W2734178003 creator A5066594047 @default.
- W2734178003 creator A5085009855 @default.
- W2734178003 date "2017-05-01" @default.
- W2734178003 modified "2023-09-25" @default.
- W2734178003 title "Deep Refinement Convolutional Networks for Human Pose Estimation" @default.
- W2734178003 cites W1445015017 @default.
- W2734178003 cites W1936750108 @default.
- W2734178003 cites W1975961009 @default.
- W2734178003 cites W2013640163 @default.
- W2734178003 cites W2022699039 @default.
- W2734178003 cites W2023866509 @default.
- W2734178003 cites W2043217799 @default.
- W2734178003 cites W2080873731 @default.
- W2734178003 cites W2097151019 @default.
- W2734178003 cites W2100526149 @default.
- W2734178003 cites W2103015390 @default.
- W2734178003 cites W2113325037 @default.
- W2734178003 cites W2120419212 @default.
- W2734178003 cites W2121969814 @default.
- W2734178003 cites W2128271252 @default.
- W2734178003 cites W2135533529 @default.
- W2734178003 cites W2143487029 @default.
- W2734178003 cites W2146502635 @default.
- W2734178003 cites W2155394491 @default.
- W2734178003 cites W2157939923 @default.
- W2734178003 cites W2174722029 @default.
- W2734178003 cites W2175012183 @default.
- W2734178003 cites W2307770531 @default.
- W2734178003 cites W2518965973 @default.
- W2734178003 cites W2535410496 @default.
- W2734178003 cites W2949117887 @default.
- W2734178003 cites W2949447708 @default.
- W2734178003 cites W2952422028 @default.
- W2734178003 cites W2963474899 @default.
- W2734178003 cites W2964304707 @default.
- W2734178003 doi "https://doi.org/10.1109/fg.2017.148" @default.
- W2734178003 hasPublicationYear "2017" @default.
- W2734178003 type Work @default.
- W2734178003 sameAs 2734178003 @default.
- W2734178003 citedByCount "1" @default.
- W2734178003 countsByYear W27341780032018 @default.
- W2734178003 crossrefType "proceedings-article" @default.
- W2734178003 hasAuthorship W2734178003A5031205865 @default.
- W2734178003 hasAuthorship W2734178003A5066594047 @default.
- W2734178003 hasAuthorship W2734178003A5085009855 @default.
- W2734178003 hasConcept C108583219 @default.
- W2734178003 hasConcept C115961682 @default.
- W2734178003 hasConcept C123657996 @default.
- W2734178003 hasConcept C124504099 @default.
- W2734178003 hasConcept C142362112 @default.
- W2734178003 hasConcept C153180895 @default.
- W2734178003 hasConcept C153349607 @default.
- W2734178003 hasConcept C154945302 @default.
- W2734178003 hasConcept C162324750 @default.
- W2734178003 hasConcept C187736073 @default.
- W2734178003 hasConcept C2778045648 @default.
- W2734178003 hasConcept C2780451532 @default.
- W2734178003 hasConcept C41008148 @default.
- W2734178003 hasConcept C52102323 @default.
- W2734178003 hasConcept C81363708 @default.
- W2734178003 hasConceptScore W2734178003C108583219 @default.
- W2734178003 hasConceptScore W2734178003C115961682 @default.
- W2734178003 hasConceptScore W2734178003C123657996 @default.
- W2734178003 hasConceptScore W2734178003C124504099 @default.
- W2734178003 hasConceptScore W2734178003C142362112 @default.
- W2734178003 hasConceptScore W2734178003C153180895 @default.
- W2734178003 hasConceptScore W2734178003C153349607 @default.
- W2734178003 hasConceptScore W2734178003C154945302 @default.
- W2734178003 hasConceptScore W2734178003C162324750 @default.
- W2734178003 hasConceptScore W2734178003C187736073 @default.
- W2734178003 hasConceptScore W2734178003C2778045648 @default.
- W2734178003 hasConceptScore W2734178003C2780451532 @default.
- W2734178003 hasConceptScore W2734178003C41008148 @default.
- W2734178003 hasConceptScore W2734178003C52102323 @default.
- W2734178003 hasConceptScore W2734178003C81363708 @default.
- W2734178003 hasLocation W27341780031 @default.
- W2734178003 hasOpenAccess W2734178003 @default.
- W2734178003 hasPrimaryLocation W27341780031 @default.
- W2734178003 hasRelatedWork W2153378748 @default.
- W2734178003 hasRelatedWork W2177568369 @default.
- W2734178003 hasRelatedWork W2604233003 @default.
- W2734178003 hasRelatedWork W2742056655 @default.
- W2734178003 hasRelatedWork W2765889543 @default.
- W2734178003 hasRelatedWork W2778250624 @default.
- W2734178003 hasRelatedWork W2798976292 @default.
- W2734178003 hasRelatedWork W2804951452 @default.
- W2734178003 hasRelatedWork W2805980550 @default.
- W2734178003 hasRelatedWork W2890197410 @default.
- W2734178003 hasRelatedWork W2902017744 @default.
- W2734178003 hasRelatedWork W2950947934 @default.
- W2734178003 hasRelatedWork W2951596696 @default.
- W2734178003 hasRelatedWork W2957789898 @default.
- W2734178003 hasRelatedWork W3004773672 @default.
- W2734178003 hasRelatedWork W3103815090 @default.
- W2734178003 hasRelatedWork W3165867039 @default.
- W2734178003 hasRelatedWork W3200539537 @default.
- W2734178003 hasRelatedWork W3203372401 @default.