FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2282298624> ?p ?o ?g. }

• W2282298624 abstract "Image understanding depends critically on learning visual models which can be formulated in terms of probabilistic structured representations. But the two-dimensional nature of images makes it much hard to design efficient image understanding systems and the form of the representations is also unclear. The key assumption used to address these problems in this thesis is that the visual world is recursively compositional. This enables us to construct representations, by recursively combining elementary stochastic templates, and makes inference and unsupervised learning practical. By introducing elementary visual constituents of recursion properties, we design recursively compositional systems for two basic image understanding problems, deformable object parsing and image parsing. We first propose a recursive deformable template model to represent objects in a hierarchical form. The object template consists of a small number of small sub-templates which is composed by smaller subsub-templates, and so on. The composition of templates and their deformation are imposed at different levels to capture both short-range and long-range correlations. The recursive design enables us to perform rapid parsing by dynamic programming, efficient unsupervised learning by recursive composition and supervised training by structured-perceptron. The learnt model together with the inference algorithms are capable of performing different vision tasks simultaneously, such as object detection, segmentation and parsing (e.g. matching/alignment of object parts). Next we extend the recursive deformable template model to a novel AND/OR graph representation for parsing articulated objects into parts and recovering their poses. The recursion design in the AND/OR graph allows us to handle an enormous variety of articulated poses with a compact graphical model where the rapid inference can be performed. We present a novel structure-learning method, Max Margin AND/OR Graph (MM-AOG), to learn the parameters of the AND/OR graph model discriminatively. Finally, we present a recursive segmentation and recognition template model for 2D image parsing. This representation consists of recursive segmentation-recognition templates which account for image segmentation and object recognition simultaneously at multiple layers. The recursive templates result in a coarse-to-fine representation which is capable of capturing long-range dependency and exploiting different levels of contextual information. The recursive structure also allows us to design a rapid inference algorithm, based on dynamic programming, which enables us to parse the image rapidly in polynomial time, and learn the model efficiently in a discriminative manner. We demonstrate the significant benefits of the recursive design on several vision tasks including deformable articulated object detection, parsing and segmentation, and image segmentation and scene understanding. Our experiments on the challenging public datasets show that the recursively compositional systems achieve the state-of-the-art performance." @default.
• W2282298624 created "2016-06-24" @default.
• W2282298624 creator A5039979770 @default.
• W2282298624 creator A5086706224 @default.
• W2282298624 date "2008-01-01" @default.
• W2282298624 modified "2023-09-27" @default.
• W2282298624 title "Recursive composition for modeling, inference and learning in computer vision" @default.
• W2282298624 hasPublicationYear "2008" @default.
• W2282298624 type Work @default.
• W2282298624 sameAs 2282298624 @default.
• W2282298624 citedByCount "0" @default.
• W2282298624 crossrefType "journal-article" @default.
• W2282298624 hasAuthorship W2282298624A5039979770 @default.
• W2282298624 hasAuthorship W2282298624A5086706224 @default.
• W2282298624 hasConcept C11413529 @default.
• W2282298624 hasConcept C119857082 @default.
• W2282298624 hasConcept C153180895 @default.
• W2282298624 hasConcept C154945302 @default.
• W2282298624 hasConcept C168773036 @default.
• W2282298624 hasConcept C186644900 @default.
• W2282298624 hasConcept C199360897 @default.
• W2282298624 hasConcept C2776214188 @default.
• W2282298624 hasConcept C2781238097 @default.
• W2282298624 hasConcept C41008148 @default.
• W2282298624 hasConcept C80444323 @default.
• W2282298624 hasConcept C82714645 @default.
• W2282298624 hasConceptScore W2282298624C11413529 @default.
• W2282298624 hasConceptScore W2282298624C119857082 @default.
• W2282298624 hasConceptScore W2282298624C153180895 @default.
• W2282298624 hasConceptScore W2282298624C154945302 @default.
• W2282298624 hasConceptScore W2282298624C168773036 @default.
• W2282298624 hasConceptScore W2282298624C186644900 @default.
• W2282298624 hasConceptScore W2282298624C199360897 @default.
• W2282298624 hasConceptScore W2282298624C2776214188 @default.
• W2282298624 hasConceptScore W2282298624C2781238097 @default.
• W2282298624 hasConceptScore W2282298624C41008148 @default.
• W2282298624 hasConceptScore W2282298624C80444323 @default.
• W2282298624 hasConceptScore W2282298624C82714645 @default.
• W2282298624 hasLocation W22822986241 @default.
• W2282298624 hasOpenAccess W2282298624 @default.
• W2282298624 hasPrimaryLocation W22822986241 @default.
• W2282298624 hasRelatedWork W2304710340 @default.
• W2282298624 hasRelatedWork W2521644007 @default.
• W2282298624 hasRelatedWork W345667141 @default.
• W2282298624 isParatext "false" @default.
• W2282298624 isRetracted "false" @default.
• W2282298624 magId "2282298624" @default.
• W2282298624 workType "article" @default.