FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1963610420> ?p ?o ?g. }

• W1963610420 endingPage "1205" @default.
• W1963610420 startingPage "1190" @default.
• W1963610420 abstract "While 3D object-centered shape-based models are appealing in comparison with 2D viewer-centered appearance-based models for their lower model complexities and potentially better view generalizabilities, the learning and inference of 3D models has been much less studied in the recent literature due to two factors: i) the enormous complexities of 3D shapes in geometric space; and ii) the gap between 3D shapes and their appearances in images. This paper aims at tackling the two problems by studying an And-Or Tree (AoT) representation that consists of two parts: i) a geometry-AoT quantizing the geometry space, i.e. the possible compositions of 3D volumetric parts and 2D surfaces within the volumes; and ii) an appearance-AoT quantizing the appearance space, i.e. the appearance variations of those shapes in different views. In this AoT, an And-node decomposes an entity into constituent parts, and an Or-node represents alternative ways of decompositions. Thus it can express a combinatorial number of geometry and appearance configurations through small dictionaries of 3D shape primitives and 2D image primitives. In the quantized space, the problem of learning a 3D object template is transformed to a structure search problem which can be efficiently solved in a dynamic programming algorithm by maximizing the information gain. We focus on learning 3D car templates from the AoT and collect a new car dataset featuring more diverse views. The learned car templates integrate both the shape-based model and the appearance-based model to combine the benefits of both. In experiments, we show three aspects: 1) the AoT is more efficient than the frequently used octree method in space representation; 2) the learned 3D car template matches the state-of-the art performances on car detection and pose estimation in a public multi-view car dataset; and 3) in our new dataset, the learned 3D template solves the joint task of simultaneous object detection, pose/view estimation, and part localization. It can generalize over unseen views and performs better than the version 5 of the DPM model in terms of object detection and semantic part localization." @default.
• W1963610420 created "2016-06-24" @default.
• W1963610420 creator A5015720040 @default.
• W1963610420 creator A5034228010 @default.
• W1963610420 date "2015-06-01" @default.
• W1963610420 modified "2023-09-30" @default.
• W1963610420 title "Learning 3D Object Templates by Quantizing Geometry and Appearance Spaces" @default.
• W1963610420 cites W1964725035 @default.
• W1963610420 cites W1967378103 @default.
• W1963610420 cites W1977045647 @default.
• W1963610420 cites W1988552531 @default.
• W1963610420 cites W1999160507 @default.
• W1963610420 cites W2001127164 @default.
• W1963610420 cites W2006500012 @default.
• W1963610420 cites W2065090505 @default.
• W1963610420 cites W2079930597 @default.
• W1963610420 cites W2111187045 @default.
• W1963610420 cites W2112074816 @default.
• W1963610420 cites W2118217749 @default.
• W1963610420 cites W2123456673 @default.
• W1963610420 cites W2124386111 @default.
• W1963610420 cites W2131225894 @default.
• W1963610420 cites W2145743319 @default.
• W1963610420 cites W2145757385 @default.
• W1963610420 cites W2147629985 @default.
• W1963610420 cites W2148599527 @default.
• W1963610420 cites W2151274603 @default.
• W1963610420 cites W2155217696 @default.
• W1963610420 cites W2156406284 @default.
• W1963610420 cites W2168356304 @default.
• W1963610420 cites W2535401692 @default.
• W1963610420 cites W302291682 @default.
• W1963610420 cites W4205969993 @default.
• W1963610420 doi "https://doi.org/10.1109/tpami.2014.2362141" @default.
• W1963610420 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26357342" @default.
• W1963610420 hasPublicationYear "2015" @default.
• W1963610420 type Work @default.
• W1963610420 sameAs 1963610420 @default.
• W1963610420 citedByCount "16" @default.
• W1963610420 countsByYear W19636104202014 @default.
• W1963610420 countsByYear W19636104202015 @default.
• W1963610420 countsByYear W19636104202016 @default.
• W1963610420 countsByYear W19636104202017 @default.
• W1963610420 countsByYear W19636104202018 @default.
• W1963610420 countsByYear W19636104202021 @default.
• W1963610420 countsByYear W19636104202022 @default.
• W1963610420 countsByYear W19636104202023 @default.
• W1963610420 crossrefType "journal-article" @default.
• W1963610420 hasAuthorship W1963610420A5015720040 @default.
• W1963610420 hasAuthorship W1963610420A5034228010 @default.
• W1963610420 hasBestOaLocation W19636104201 @default.
• W1963610420 hasConcept C108882727 @default.
• W1963610420 hasConcept C111919701 @default.
• W1963610420 hasConcept C113174947 @default.
• W1963610420 hasConcept C114614502 @default.
• W1963610420 hasConcept C120665830 @default.
• W1963610420 hasConcept C121332964 @default.
• W1963610420 hasConcept C153180895 @default.
• W1963610420 hasConcept C154945302 @default.
• W1963610420 hasConcept C17744445 @default.
• W1963610420 hasConcept C192209626 @default.
• W1963610420 hasConcept C199360897 @default.
• W1963610420 hasConcept C199539241 @default.
• W1963610420 hasConcept C2524010 @default.
• W1963610420 hasConcept C2776214188 @default.
• W1963610420 hasConcept C2776359362 @default.
• W1963610420 hasConcept C2778572836 @default.
• W1963610420 hasConcept C2781238097 @default.
• W1963610420 hasConcept C29123130 @default.
• W1963610420 hasConcept C31972630 @default.
• W1963610420 hasConcept C33923547 @default.
• W1963610420 hasConcept C41008148 @default.
• W1963610420 hasConcept C82714645 @default.
• W1963610420 hasConcept C94625758 @default.
• W1963610420 hasConceptScore W1963610420C108882727 @default.
• W1963610420 hasConceptScore W1963610420C111919701 @default.
• W1963610420 hasConceptScore W1963610420C113174947 @default.
• W1963610420 hasConceptScore W1963610420C114614502 @default.
• W1963610420 hasConceptScore W1963610420C120665830 @default.
• W1963610420 hasConceptScore W1963610420C121332964 @default.
• W1963610420 hasConceptScore W1963610420C153180895 @default.
• W1963610420 hasConceptScore W1963610420C154945302 @default.
• W1963610420 hasConceptScore W1963610420C17744445 @default.
• W1963610420 hasConceptScore W1963610420C192209626 @default.
• W1963610420 hasConceptScore W1963610420C199360897 @default.
• W1963610420 hasConceptScore W1963610420C199539241 @default.
• W1963610420 hasConceptScore W1963610420C2524010 @default.
• W1963610420 hasConceptScore W1963610420C2776214188 @default.
• W1963610420 hasConceptScore W1963610420C2776359362 @default.
• W1963610420 hasConceptScore W1963610420C2778572836 @default.
• W1963610420 hasConceptScore W1963610420C2781238097 @default.
• W1963610420 hasConceptScore W1963610420C29123130 @default.
• W1963610420 hasConceptScore W1963610420C31972630 @default.
• W1963610420 hasConceptScore W1963610420C33923547 @default.
• W1963610420 hasConceptScore W1963610420C41008148 @default.
• W1963610420 hasConceptScore W1963610420C82714645 @default.
• W1963610420 hasConceptScore W1963610420C94625758 @default.
• W1963610420 hasFunder F4320306076 @default.

• next