Matches in SemOpenAlex for { <https://semopenalex.org/work/W2517598410> ?p ?o ?g. }
- W2517598410 abstract "Objects in fine-grained categories always share a high degree of shape similarity, making both “localizing discriminative parts” and “learning appearance descriptors” extremely difficult. We propose a framework to leverage 2D+3D cues to handle above two challenges. Towards the goal of image alignment to localize discriminative parts, traditional methods rely on either manual part annotation or image segmentation. Instead, our framework leverages each image's 3D camera pose estimation to align images; Towards the goal of “learning appearance descriptors” confined with small training data and memory/computation cost, we propose an unsupervised Convolutional Sparse Coding (CSC) + manifold learning that significantly reduces model complexity, but still successfully produces highly diverse feature filters like deep neural network. Our experimental results attest the advocated framework's accuracy is comparable to a deep network, demonstrating its great potential on mobile devices." @default.
- W2517598410 created "2016-09-16" @default.
- W2517598410 creator A5005873257 @default.
- W2517598410 creator A5018394419 @default.
- W2517598410 creator A5066028215 @default.
- W2517598410 date "2016-09-01" @default.
- W2517598410 modified "2023-09-23" @default.
- W2517598410 title "Leveraging 2D and 3D cues for fine-grained object classification" @default.
- W2517598410 cites W1515999713 @default.
- W2517598410 cites W1523493493 @default.
- W2517598410 cites W1530965581 @default.
- W2517598410 cites W1603508051 @default.
- W2517598410 cites W1898560071 @default.
- W2517598410 cites W1972960842 @default.
- W2517598410 cites W1975517671 @default.
- W2517598410 cites W2001242835 @default.
- W2517598410 cites W2001810343 @default.
- W2517598410 cites W2005876975 @default.
- W2517598410 cites W2033819227 @default.
- W2517598410 cites W2050173620 @default.
- W2517598410 cites W2076562229 @default.
- W2517598410 cites W2078046525 @default.
- W2517598410 cites W2091759811 @default.
- W2517598410 cites W2097117768 @default.
- W2517598410 cites W2102605133 @default.
- W2517598410 cites W2104294146 @default.
- W2517598410 cites W2115706991 @default.
- W2517598410 cites W2115891208 @default.
- W2517598410 cites W2117228865 @default.
- W2517598410 cites W2117259536 @default.
- W2517598410 cites W2117553576 @default.
- W2517598410 cites W2134905716 @default.
- W2517598410 cites W2139212933 @default.
- W2517598410 cites W2143055991 @default.
- W2517598410 cites W2150112333 @default.
- W2517598410 cites W2155839910 @default.
- W2517598410 cites W2156598602 @default.
- W2517598410 cites W2167254323 @default.
- W2517598410 cites W2169488311 @default.
- W2517598410 cites W2203580091 @default.
- W2517598410 cites W302237248 @default.
- W2517598410 cites W56385144 @default.
- W2517598410 doi "https://doi.org/10.1109/icip.2016.7532579" @default.
- W2517598410 hasPublicationYear "2016" @default.
- W2517598410 type Work @default.
- W2517598410 sameAs 2517598410 @default.
- W2517598410 citedByCount "2" @default.
- W2517598410 countsByYear W25175984102017 @default.
- W2517598410 crossrefType "proceedings-article" @default.
- W2517598410 hasAuthorship W2517598410A5005873257 @default.
- W2517598410 hasAuthorship W2517598410A5018394419 @default.
- W2517598410 hasAuthorship W2517598410A5066028215 @default.
- W2517598410 hasConcept C108583219 @default.
- W2517598410 hasConcept C115961682 @default.
- W2517598410 hasConcept C124504099 @default.
- W2517598410 hasConcept C153083717 @default.
- W2517598410 hasConcept C153180895 @default.
- W2517598410 hasConcept C154945302 @default.
- W2517598410 hasConcept C2776321320 @default.
- W2517598410 hasConcept C31972630 @default.
- W2517598410 hasConcept C41008148 @default.
- W2517598410 hasConcept C52102323 @default.
- W2517598410 hasConcept C52622490 @default.
- W2517598410 hasConcept C59404180 @default.
- W2517598410 hasConcept C75294576 @default.
- W2517598410 hasConcept C77637269 @default.
- W2517598410 hasConcept C81363708 @default.
- W2517598410 hasConcept C89600930 @default.
- W2517598410 hasConcept C97931131 @default.
- W2517598410 hasConceptScore W2517598410C108583219 @default.
- W2517598410 hasConceptScore W2517598410C115961682 @default.
- W2517598410 hasConceptScore W2517598410C124504099 @default.
- W2517598410 hasConceptScore W2517598410C153083717 @default.
- W2517598410 hasConceptScore W2517598410C153180895 @default.
- W2517598410 hasConceptScore W2517598410C154945302 @default.
- W2517598410 hasConceptScore W2517598410C2776321320 @default.
- W2517598410 hasConceptScore W2517598410C31972630 @default.
- W2517598410 hasConceptScore W2517598410C41008148 @default.
- W2517598410 hasConceptScore W2517598410C52102323 @default.
- W2517598410 hasConceptScore W2517598410C52622490 @default.
- W2517598410 hasConceptScore W2517598410C59404180 @default.
- W2517598410 hasConceptScore W2517598410C75294576 @default.
- W2517598410 hasConceptScore W2517598410C77637269 @default.
- W2517598410 hasConceptScore W2517598410C81363708 @default.
- W2517598410 hasConceptScore W2517598410C89600930 @default.
- W2517598410 hasConceptScore W2517598410C97931131 @default.
- W2517598410 hasLocation W25175984101 @default.
- W2517598410 hasOpenAccess W2517598410 @default.
- W2517598410 hasPrimaryLocation W25175984101 @default.
- W2517598410 hasRelatedWork W158943247 @default.
- W2517598410 hasRelatedWork W1923332106 @default.
- W2517598410 hasRelatedWork W1988074537 @default.
- W2517598410 hasRelatedWork W2000810902 @default.
- W2517598410 hasRelatedWork W2070961462 @default.
- W2517598410 hasRelatedWork W2087889803 @default.
- W2517598410 hasRelatedWork W2133713754 @default.
- W2517598410 hasRelatedWork W2138011018 @default.
- W2517598410 hasRelatedWork W2212893572 @default.
- W2517598410 hasRelatedWork W2344150445 @default.
- W2517598410 hasRelatedWork W2415131061 @default.