Matches in SemOpenAlex for { <https://semopenalex.org/work/W2566800323> ?p ?o ?g. }
- W2566800323 abstract "During the past few years we have witnessed the development of many methodologies for building and fitting Statistical Deformable Models (SDMs). The construction of accurate SDMs requires careful annotation of images with regards to a consistent set of landmarks. However, the manual annotation of a large amount of images is a tedious, laborious and expensive procedure. Furthermore, for several deformable objects, e.g. human body, it is difficult to define a consistent set of landmarks, and, thus, it becomes impossible to train humans in order to accurately annotate a collection of images. Nevertheless, for the majority of objects, it is possible to extract the shape by object segmentation or even by shape drawing. In this paper, we show for the first time, to the best of our knowledge, that it is possible to construct SDMs by putting object shapes in dense correspondence. Such SDMs can be built with much less effort for a large battery of objects. Additionally, we show that, by sampling the dense model, a part-based SDM can be learned with its parts being in correspondence. We employ our framework to develop SDMs of human arms and legs, which can be used for the segmentation of the outline of the human body, as well as to provide better and more consistent annotations for body joints." @default.
- W2566800323 created "2017-01-06" @default.
- W2566800323 creator A5011498965 @default.
- W2566800323 creator A5029931791 @default.
- W2566800323 creator A5054309068 @default.
- W2566800323 creator A5080553022 @default.
- W2566800323 creator A5088680073 @default.
- W2566800323 date "2016-06-01" @default.
- W2566800323 modified "2023-09-23" @default.
- W2566800323 title "Estimating Correspondences of Deformable Objects “In-the-Wild”" @default.
- W2566800323 cites W1445015017 @default.
- W2566800323 cites W1570420153 @default.
- W2566800323 cites W1604643028 @default.
- W2566800323 cites W1796263212 @default.
- W2566800323 cites W1861492603 @default.
- W2566800323 cites W1915668717 @default.
- W2566800323 cites W1931557824 @default.
- W2566800323 cites W1931980004 @default.
- W2566800323 cites W1936750108 @default.
- W2566800323 cites W1960706641 @default.
- W2566800323 cites W1962739028 @default.
- W2566800323 cites W1963599662 @default.
- W2566800323 cites W1969158966 @default.
- W2566800323 cites W1978881539 @default.
- W2566800323 cites W1981011640 @default.
- W2566800323 cites W1993977496 @default.
- W2566800323 cites W2011700682 @default.
- W2566800323 cites W2013640163 @default.
- W2566800323 cites W2021523856 @default.
- W2566800323 cites W2023866509 @default.
- W2566800323 cites W2026427195 @default.
- W2566800323 cites W2031869209 @default.
- W2566800323 cites W2036868818 @default.
- W2566800323 cites W2038952578 @default.
- W2566800323 cites W2041075748 @default.
- W2566800323 cites W2046316885 @default.
- W2566800323 cites W2047508432 @default.
- W2566800323 cites W2049981393 @default.
- W2566800323 cites W2058961190 @default.
- W2566800323 cites W2076017598 @default.
- W2566800323 cites W2078113769 @default.
- W2566800323 cites W2080873731 @default.
- W2566800323 cites W2081589848 @default.
- W2566800323 cites W2082308025 @default.
- W2566800323 cites W2082908671 @default.
- W2566800323 cites W2087681821 @default.
- W2566800323 cites W2089439257 @default.
- W2566800323 cites W2090549674 @default.
- W2566800323 cites W2101866605 @default.
- W2566800323 cites W2103559027 @default.
- W2566800323 cites W2110070888 @default.
- W2566800323 cites W2111372597 @default.
- W2566800323 cites W2114208002 @default.
- W2566800323 cites W2121684305 @default.
- W2566800323 cites W2122791209 @default.
- W2566800323 cites W2124386111 @default.
- W2566800323 cites W2128271252 @default.
- W2566800323 cites W2128409098 @default.
- W2566800323 cites W2130563197 @default.
- W2566800323 cites W2132825567 @default.
- W2566800323 cites W2138406903 @default.
- W2566800323 cites W2140404463 @default.
- W2566800323 cites W2143451044 @default.
- W2566800323 cites W2143478373 @default.
- W2566800323 cites W2152826865 @default.
- W2566800323 cites W2153410696 @default.
- W2566800323 cites W2157145630 @default.
- W2566800323 cites W2161969291 @default.
- W2566800323 cites W2168722300 @default.
- W2566800323 cites W2284800790 @default.
- W2566800323 cites W2294046137 @default.
- W2566800323 cites W2535410496 @default.
- W2566800323 cites W602397586 @default.
- W2566800323 doi "https://doi.org/10.1109/cvpr.2016.624" @default.
- W2566800323 hasPublicationYear "2016" @default.
- W2566800323 type Work @default.
- W2566800323 sameAs 2566800323 @default.
- W2566800323 citedByCount "6" @default.
- W2566800323 countsByYear W25668003232016 @default.
- W2566800323 countsByYear W25668003232017 @default.
- W2566800323 countsByYear W25668003232018 @default.
- W2566800323 crossrefType "proceedings-article" @default.
- W2566800323 hasAuthorship W2566800323A5011498965 @default.
- W2566800323 hasAuthorship W2566800323A5029931791 @default.
- W2566800323 hasAuthorship W2566800323A5054309068 @default.
- W2566800323 hasAuthorship W2566800323A5080553022 @default.
- W2566800323 hasAuthorship W2566800323A5088680073 @default.
- W2566800323 hasBestOaLocation W25668003232 @default.
- W2566800323 hasConcept C153180895 @default.
- W2566800323 hasConcept C154945302 @default.
- W2566800323 hasConcept C177264268 @default.
- W2566800323 hasConcept C199360897 @default.
- W2566800323 hasConcept C2776321320 @default.
- W2566800323 hasConcept C2780801425 @default.
- W2566800323 hasConcept C2781238097 @default.
- W2566800323 hasConcept C31972630 @default.
- W2566800323 hasConcept C41008148 @default.
- W2566800323 hasConcept C89600930 @default.
- W2566800323 hasConceptScore W2566800323C153180895 @default.
- W2566800323 hasConceptScore W2566800323C154945302 @default.