Matches in SemOpenAlex for { <https://semopenalex.org/work/W2564554865> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2564554865 abstract "Author(s): Xia, Fangting | Advisor(s): Yuille, Alan L. | Abstract: Human semantic part segmentation and human pose estimation are two fundamental and complementary tasks in computer vision. The localization of joints in pose estimation can be much more accurate with the support of part segment consistency while the local confusions in part segmentation can be greatly reduced with the support of top-down pose information. In natural scenes which consist of multiple people, human pose estimation and human part segmentation are still challenging due to multi-instance confusion and large variations in pose, scale, appearance and occlusion. Current state-of-the-art methods for both tasks rely on deep neural networks to extract data-dependent features, and combine them with a carefully designed graphical model. However, these methods have no efficient mechanism to handle multi-person overlapping or to adapt to the scale of human instances, thus are still limited when facing large variability in human pose and scale. To improve the performance of both tasks over current methods, we propose three models that tackle the difficulty of pose/scale variation in two major directions: (1) introduce top-down pose consistency into semantic part segmentation and introduce part segment consistency into human pose estimation, letting the two tasks benefit each other; (2) handle the scale variation by designing a mechanism to adapt to the size of human instances and their corresponding parts. Our first model incorporates pose cues into a graphical model-based part segmentation framework while our third model combines pose information within a framework made up of fully convolutional networks (FCN). Our second model is a hierarchical FCN framework that performs object/part scale estimation and part segmentation jointly, adapting to the size of objects and parts. We show that all our three models achieve state-of-the-art performance on challenging datasets." @default.
- W2564554865 created "2017-01-06" @default.
- W2564554865 creator A5037738952 @default.
- W2564554865 date "2016-01-01" @default.
- W2564554865 modified "2023-09-26" @default.
- W2564554865 title "Pose-Guided Human Semantic Part Segmentation" @default.
- W2564554865 hasPublicationYear "2016" @default.
- W2564554865 type Work @default.
- W2564554865 sameAs 2564554865 @default.
- W2564554865 citedByCount "0" @default.
- W2564554865 crossrefType "journal-article" @default.
- W2564554865 hasAuthorship W2564554865A5037738952 @default.
- W2564554865 hasConcept C119857082 @default.
- W2564554865 hasConcept C121332964 @default.
- W2564554865 hasConcept C153180895 @default.
- W2564554865 hasConcept C154945302 @default.
- W2564554865 hasConcept C184337299 @default.
- W2564554865 hasConcept C199360897 @default.
- W2564554865 hasConcept C205649164 @default.
- W2564554865 hasConcept C22100474 @default.
- W2564554865 hasConcept C2776436953 @default.
- W2564554865 hasConcept C2778334786 @default.
- W2564554865 hasConcept C2778755073 @default.
- W2564554865 hasConcept C31972630 @default.
- W2564554865 hasConcept C36613465 @default.
- W2564554865 hasConcept C41008148 @default.
- W2564554865 hasConcept C44870925 @default.
- W2564554865 hasConcept C52102323 @default.
- W2564554865 hasConcept C58640448 @default.
- W2564554865 hasConcept C89600930 @default.
- W2564554865 hasConceptScore W2564554865C119857082 @default.
- W2564554865 hasConceptScore W2564554865C121332964 @default.
- W2564554865 hasConceptScore W2564554865C153180895 @default.
- W2564554865 hasConceptScore W2564554865C154945302 @default.
- W2564554865 hasConceptScore W2564554865C184337299 @default.
- W2564554865 hasConceptScore W2564554865C199360897 @default.
- W2564554865 hasConceptScore W2564554865C205649164 @default.
- W2564554865 hasConceptScore W2564554865C22100474 @default.
- W2564554865 hasConceptScore W2564554865C2776436953 @default.
- W2564554865 hasConceptScore W2564554865C2778334786 @default.
- W2564554865 hasConceptScore W2564554865C2778755073 @default.
- W2564554865 hasConceptScore W2564554865C31972630 @default.
- W2564554865 hasConceptScore W2564554865C36613465 @default.
- W2564554865 hasConceptScore W2564554865C41008148 @default.
- W2564554865 hasConceptScore W2564554865C44870925 @default.
- W2564554865 hasConceptScore W2564554865C52102323 @default.
- W2564554865 hasConceptScore W2564554865C58640448 @default.
- W2564554865 hasConceptScore W2564554865C89600930 @default.
- W2564554865 hasLocation W25645548651 @default.
- W2564554865 hasOpenAccess W2564554865 @default.
- W2564554865 hasPrimaryLocation W25645548651 @default.
- W2564554865 hasRelatedWork W1932321571 @default.
- W2564554865 hasRelatedWork W2222082930 @default.
- W2564554865 hasRelatedWork W2342674081 @default.
- W2564554865 hasRelatedWork W2554777659 @default.
- W2564554865 hasRelatedWork W2784342561 @default.
- W2564554865 hasRelatedWork W2794475071 @default.
- W2564554865 hasRelatedWork W2795270651 @default.
- W2564554865 hasRelatedWork W2804461760 @default.
- W2564554865 hasRelatedWork W2958537753 @default.
- W2564554865 hasRelatedWork W2959141096 @default.
- W2564554865 hasRelatedWork W3027710736 @default.
- W2564554865 hasRelatedWork W3035637226 @default.
- W2564554865 hasRelatedWork W3131171384 @default.
- W2564554865 hasRelatedWork W3137989970 @default.
- W2564554865 hasRelatedWork W3138282301 @default.
- W2564554865 hasRelatedWork W3156996278 @default.
- W2564554865 hasRelatedWork W3185034762 @default.
- W2564554865 hasRelatedWork W3188937449 @default.
- W2564554865 hasRelatedWork W3205412492 @default.
- W2564554865 hasRelatedWork W78453151 @default.
- W2564554865 isParatext "false" @default.
- W2564554865 isRetracted "false" @default.
- W2564554865 magId "2564554865" @default.
- W2564554865 workType "article" @default.