Matches in SemOpenAlex for { <https://semopenalex.org/work/W2110122948> ?p ?o ?g. }
- W2110122948 endingPage "2578" @default.
- W2110122948 startingPage "2549" @default.
- W2110122948 abstract "Most discriminative techniques for detecting instances from object categories in still images consist of looping over a partition of a pose space with dedicated binary classifiers. The efficiency of this strategy for a complex pose, that is, for fine-grained descriptions, can be assessed by measuring the effect of sample size and pose resolution on accuracy and computation. Two conclusions emerge: (1) fragmenting the training data, which is inevitable in dealing with high in-class variation, severely reduces accuracy; (2) the computational cost at high resolution is prohibitive due to visiting a massive pose partition. To overcome data-fragmentation we propose a novel framework centered on pose-indexed features which assign a response to a pair consisting of an image and a pose, and are designed to be stationary: the probability distribution of the response is always the same if an object is actually present. Such features allow for efficient, one-shot learning of pose-specific classifiers. To avoid expensive scene processing, we arrange these classifiers in a hierarchy based on nested partitions of the pose; as in previous work on coarse-to-fine search, this allows for efficient processing. The hierarchy is then ”folded” for training: all the classifiers at each level are derived from one base predictor learned from all the data. The hierarchy is ”unfolded” for testing: parsing a scene amounts to examining increasingly finer object descriptions only when there is sufficient evidence for coarser ones. In this way, the detection results are equivalent to an exhaustive search at high resolution. We illustrate these ideas by detecting and localizing cats in highly cluttered greyscale scenes." @default.
- W2110122948 created "2016-06-24" @default.
- W2110122948 creator A5013551450 @default.
- W2110122948 creator A5076094010 @default.
- W2110122948 date "2008-01-01" @default.
- W2110122948 modified "2023-10-04" @default.
- W2110122948 title "Stationary Features and Cat Detection" @default.
- W2110122948 cites W109283469 @default.
- W2110122948 cites W1530454533 @default.
- W2110122948 cites W1552060966 @default.
- W2110122948 cites W1582044912 @default.
- W2110122948 cites W1601741105 @default.
- W2110122948 cites W1608462934 @default.
- W2110122948 cites W1759219755 @default.
- W2110122948 cites W1819990927 @default.
- W2110122948 cites W1932758808 @default.
- W2110122948 cites W1970255615 @default.
- W2110122948 cites W2030536784 @default.
- W2110122948 cites W2099972257 @default.
- W2110122948 cites W2100428290 @default.
- W2110122948 cites W2104577112 @default.
- W2110122948 cites W2118010438 @default.
- W2110122948 cites W2125199814 @default.
- W2110122948 cites W2134557905 @default.
- W2110122948 cites W2145073242 @default.
- W2110122948 cites W2162708558 @default.
- W2110122948 cites W2166770390 @default.
- W2110122948 cites W2170296207 @default.
- W2110122948 cites W2217896605 @default.
- W2110122948 cites W3097096317 @default.
- W2110122948 cites W3146079624 @default.
- W2110122948 hasPublicationYear "2008" @default.
- W2110122948 type Work @default.
- W2110122948 sameAs 2110122948 @default.
- W2110122948 citedByCount "24" @default.
- W2110122948 countsByYear W21101229482012 @default.
- W2110122948 countsByYear W21101229482013 @default.
- W2110122948 countsByYear W21101229482014 @default.
- W2110122948 countsByYear W21101229482015 @default.
- W2110122948 countsByYear W21101229482016 @default.
- W2110122948 countsByYear W21101229482017 @default.
- W2110122948 countsByYear W21101229482019 @default.
- W2110122948 crossrefType "journal-article" @default.
- W2110122948 hasAuthorship W2110122948A5013551450 @default.
- W2110122948 hasAuthorship W2110122948A5076094010 @default.
- W2110122948 hasConcept C11413529 @default.
- W2110122948 hasConcept C114614502 @default.
- W2110122948 hasConcept C119857082 @default.
- W2110122948 hasConcept C153180895 @default.
- W2110122948 hasConcept C154945302 @default.
- W2110122948 hasConcept C162324750 @default.
- W2110122948 hasConcept C2776151529 @default.
- W2110122948 hasConcept C2781238097 @default.
- W2110122948 hasConcept C31170391 @default.
- W2110122948 hasConcept C33923547 @default.
- W2110122948 hasConcept C34447519 @default.
- W2110122948 hasConcept C41008148 @default.
- W2110122948 hasConcept C42812 @default.
- W2110122948 hasConcept C45374587 @default.
- W2110122948 hasConcept C48372109 @default.
- W2110122948 hasConcept C52102323 @default.
- W2110122948 hasConcept C94375191 @default.
- W2110122948 hasConcept C97931131 @default.
- W2110122948 hasConceptScore W2110122948C11413529 @default.
- W2110122948 hasConceptScore W2110122948C114614502 @default.
- W2110122948 hasConceptScore W2110122948C119857082 @default.
- W2110122948 hasConceptScore W2110122948C153180895 @default.
- W2110122948 hasConceptScore W2110122948C154945302 @default.
- W2110122948 hasConceptScore W2110122948C162324750 @default.
- W2110122948 hasConceptScore W2110122948C2776151529 @default.
- W2110122948 hasConceptScore W2110122948C2781238097 @default.
- W2110122948 hasConceptScore W2110122948C31170391 @default.
- W2110122948 hasConceptScore W2110122948C33923547 @default.
- W2110122948 hasConceptScore W2110122948C34447519 @default.
- W2110122948 hasConceptScore W2110122948C41008148 @default.
- W2110122948 hasConceptScore W2110122948C42812 @default.
- W2110122948 hasConceptScore W2110122948C45374587 @default.
- W2110122948 hasConceptScore W2110122948C48372109 @default.
- W2110122948 hasConceptScore W2110122948C52102323 @default.
- W2110122948 hasConceptScore W2110122948C94375191 @default.
- W2110122948 hasConceptScore W2110122948C97931131 @default.
- W2110122948 hasIssue "85" @default.
- W2110122948 hasOpenAccess W2110122948 @default.
- W2110122948 hasRelatedWork W1678356000 @default.
- W2110122948 hasRelatedWork W1971616954 @default.
- W2110122948 hasRelatedWork W1988790447 @default.
- W2110122948 hasRelatedWork W1990937109 @default.
- W2110122948 hasRelatedWork W2024046085 @default.
- W2110122948 hasRelatedWork W2032194607 @default.
- W2110122948 hasRelatedWork W2047508432 @default.
- W2110122948 hasRelatedWork W2086274040 @default.
- W2110122948 hasRelatedWork W2104095591 @default.
- W2110122948 hasRelatedWork W2112076978 @default.
- W2110122948 hasRelatedWork W2124386111 @default.
- W2110122948 hasRelatedWork W2136000821 @default.
- W2110122948 hasRelatedWork W2149997693 @default.
- W2110122948 hasRelatedWork W2151103935 @default.
- W2110122948 hasRelatedWork W2161969291 @default.