Matches in SemOpenAlex for { <https://semopenalex.org/work/W36699952> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W36699952 abstract "This dissertation addresses a number of inter-related and fundamental problems in computer vision. Specifically, we address object discovery, recognition, segmentation, and 3D pose estimation in images, as well as 3D scene reconstruction and scene interpretation. The key ideas behind our approaches include using shape as a basic object feature, and using structured prediction modeling paradigms for representing objects and scenes. In this work, we make a number of new contributions both in computer vision and machine learning. We address the vision problems of shape matching, shape-based mining of objects in arbitrary image collections, context-aware object recognition, monocular estimation of 3D object poses, and monocular 3D scene reconstruction using shape from texture. Our work on shape-based object discovery is the first to show that meaningful objects can be extracted from a collection of arbitrary images, without any human supervision, by shape matching. We also show that a spatial repetition of objects in images (e.g., windows on a building facade, or cars lined up along a street) can be used for 3D scene reconstruction from a single image. The aforementioned topics have never been addressed in the literature. The dissertation also presents new algorithms and object representations for the aforementioned vision problems. We fuse two traditionally different modeling paradigms Conditional Random Fields (CRF) and Random Forests (RF) into a unified framework, referred to as (RF)2. We also derive theoretical error bounds of estimating distribution ratios by a two-class RF, which is then used to derive the theoretical performance bounds of a two-class (RF)2. Thorough experimental evaluation of individual aspects of all our approaches is presented. In general, the experiments demonstrate that we outperform the state of the art on the benchmark datasets, without increasing complexity and supervision in training." @default.
- W36699952 created "2016-06-24" @default.
- W36699952 creator A5012026514 @default.
- W36699952 creator A5027742996 @default.
- W36699952 date "2011-01-01" @default.
- W36699952 modified "2023-09-23" @default.
- W36699952 title "From shape-based object recognition and discovery to 3d scene interpretation" @default.
- W36699952 hasPublicationYear "2011" @default.
- W36699952 type Work @default.
- W36699952 sameAs 36699952 @default.
- W36699952 citedByCount "0" @default.
- W36699952 crossrefType "dissertation" @default.
- W36699952 hasAuthorship W36699952A5012026514 @default.
- W36699952 hasAuthorship W36699952A5027742996 @default.
- W36699952 hasConcept C104114177 @default.
- W36699952 hasConcept C105795698 @default.
- W36699952 hasConcept C109950114 @default.
- W36699952 hasConcept C146159030 @default.
- W36699952 hasConcept C152565575 @default.
- W36699952 hasConcept C154945302 @default.
- W36699952 hasConcept C165064840 @default.
- W36699952 hasConcept C166957645 @default.
- W36699952 hasConcept C205649164 @default.
- W36699952 hasConcept C2779343474 @default.
- W36699952 hasConcept C2781238097 @default.
- W36699952 hasConcept C31972630 @default.
- W36699952 hasConcept C33923547 @default.
- W36699952 hasConcept C41008148 @default.
- W36699952 hasConcept C52102323 @default.
- W36699952 hasConcept C64876066 @default.
- W36699952 hasConcept C65909025 @default.
- W36699952 hasConcept C89600930 @default.
- W36699952 hasConceptScore W36699952C104114177 @default.
- W36699952 hasConceptScore W36699952C105795698 @default.
- W36699952 hasConceptScore W36699952C109950114 @default.
- W36699952 hasConceptScore W36699952C146159030 @default.
- W36699952 hasConceptScore W36699952C152565575 @default.
- W36699952 hasConceptScore W36699952C154945302 @default.
- W36699952 hasConceptScore W36699952C165064840 @default.
- W36699952 hasConceptScore W36699952C166957645 @default.
- W36699952 hasConceptScore W36699952C205649164 @default.
- W36699952 hasConceptScore W36699952C2779343474 @default.
- W36699952 hasConceptScore W36699952C2781238097 @default.
- W36699952 hasConceptScore W36699952C31972630 @default.
- W36699952 hasConceptScore W36699952C33923547 @default.
- W36699952 hasConceptScore W36699952C41008148 @default.
- W36699952 hasConceptScore W36699952C52102323 @default.
- W36699952 hasConceptScore W36699952C64876066 @default.
- W36699952 hasConceptScore W36699952C65909025 @default.
- W36699952 hasConceptScore W36699952C89600930 @default.
- W36699952 hasLocation W366999521 @default.
- W36699952 hasOpenAccess W36699952 @default.
- W36699952 hasPrimaryLocation W366999521 @default.
- W36699952 hasRelatedWork W1488760683 @default.
- W36699952 hasRelatedWork W1548329470 @default.
- W36699952 hasRelatedWork W1643817907 @default.
- W36699952 hasRelatedWork W1969546028 @default.
- W36699952 hasRelatedWork W1969579675 @default.
- W36699952 hasRelatedWork W2011511325 @default.
- W36699952 hasRelatedWork W2071042563 @default.
- W36699952 hasRelatedWork W2114111978 @default.
- W36699952 hasRelatedWork W2139413074 @default.
- W36699952 hasRelatedWork W2148777761 @default.
- W36699952 hasRelatedWork W2149919437 @default.
- W36699952 hasRelatedWork W2156802865 @default.
- W36699952 hasRelatedWork W2202987080 @default.
- W36699952 hasRelatedWork W2274711216 @default.
- W36699952 hasRelatedWork W2519369300 @default.
- W36699952 hasRelatedWork W2963646814 @default.
- W36699952 hasRelatedWork W3035178297 @default.
- W36699952 hasRelatedWork W3091835360 @default.
- W36699952 hasRelatedWork W3157353714 @default.
- W36699952 hasRelatedWork W3175844808 @default.
- W36699952 isParatext "false" @default.
- W36699952 isRetracted "false" @default.
- W36699952 magId "36699952" @default.
- W36699952 workType "dissertation" @default.