Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952504894> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2952504894 abstract "We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from freely available unlabeled web search results. The explosion of visual data on the web can potentially make visual examples of almost any object easily accessible via web search. Previous unsupervised methods have utilized either large scale sources of texture cues from the web, or shape information from data such as crowdsourced CAD models. We propose a two-stream deep learning framework that combines these cues, with one stream learning visual texture cues from image search data, and the other stream learning rich shape information from 3D CAD models. To perform classification or detection for a novel image, the predictions of the two streams are combined using a late fusion scheme. We present experiments and visualizations for both tasks on the standard benchmark PASCAL VOC 2007 to demonstrate that texture and shape provide complementary information in our model. Our method outperforms previous web image based models, 3D CAD model based approaches, and weakly supervised models." @default.
- W2952504894 created "2019-06-27" @default.
- W2952504894 creator A5068469395 @default.
- W2952504894 creator A5075906727 @default.
- W2952504894 date "2016-09-14" @default.
- W2952504894 modified "2023-09-27" @default.
- W2952504894 title "Combining Texture and Shape Cues for Object Recognition With Minimal Supervision" @default.
- W2952504894 cites W1964763677 @default.
- W2952504894 cites W2081613070 @default.
- W2952504894 cites W2087347434 @default.
- W2952504894 cites W2107250100 @default.
- W2952504894 cites W2108598243 @default.
- W2952504894 cites W2161969291 @default.
- W2952504894 doi "https://doi.org/10.48550/arxiv.1609.04356" @default.
- W2952504894 hasPublicationYear "2016" @default.
- W2952504894 type Work @default.
- W2952504894 sameAs 2952504894 @default.
- W2952504894 citedByCount "0" @default.
- W2952504894 crossrefType "posted-content" @default.
- W2952504894 hasAuthorship W2952504894A5068469395 @default.
- W2952504894 hasAuthorship W2952504894A5075906727 @default.
- W2952504894 hasBestOaLocation W29525048941 @default.
- W2952504894 hasConcept C111370547 @default.
- W2952504894 hasConcept C115961682 @default.
- W2952504894 hasConcept C119857082 @default.
- W2952504894 hasConcept C13280743 @default.
- W2952504894 hasConcept C153180895 @default.
- W2952504894 hasConcept C154945302 @default.
- W2952504894 hasConcept C185798385 @default.
- W2952504894 hasConcept C199360897 @default.
- W2952504894 hasConcept C205649164 @default.
- W2952504894 hasConcept C2781195486 @default.
- W2952504894 hasConcept C31972630 @default.
- W2952504894 hasConcept C36464697 @default.
- W2952504894 hasConcept C41008148 @default.
- W2952504894 hasConcept C75608658 @default.
- W2952504894 hasConceptScore W2952504894C111370547 @default.
- W2952504894 hasConceptScore W2952504894C115961682 @default.
- W2952504894 hasConceptScore W2952504894C119857082 @default.
- W2952504894 hasConceptScore W2952504894C13280743 @default.
- W2952504894 hasConceptScore W2952504894C153180895 @default.
- W2952504894 hasConceptScore W2952504894C154945302 @default.
- W2952504894 hasConceptScore W2952504894C185798385 @default.
- W2952504894 hasConceptScore W2952504894C199360897 @default.
- W2952504894 hasConceptScore W2952504894C205649164 @default.
- W2952504894 hasConceptScore W2952504894C2781195486 @default.
- W2952504894 hasConceptScore W2952504894C31972630 @default.
- W2952504894 hasConceptScore W2952504894C36464697 @default.
- W2952504894 hasConceptScore W2952504894C41008148 @default.
- W2952504894 hasConceptScore W2952504894C75608658 @default.
- W2952504894 hasLocation W29525048941 @default.
- W2952504894 hasOpenAccess W2952504894 @default.
- W2952504894 hasPrimaryLocation W29525048941 @default.
- W2952504894 hasRelatedWork W1967418220 @default.
- W2952504894 hasRelatedWork W2005185696 @default.
- W2952504894 hasRelatedWork W2130228941 @default.
- W2952504894 hasRelatedWork W2161229648 @default.
- W2952504894 hasRelatedWork W2170701234 @default.
- W2952504894 hasRelatedWork W2210334829 @default.
- W2952504894 hasRelatedWork W2235753890 @default.
- W2952504894 hasRelatedWork W2993674027 @default.
- W2952504894 hasRelatedWork W3208409104 @default.
- W2952504894 hasRelatedWork W650836761 @default.
- W2952504894 isParatext "false" @default.
- W2952504894 isRetracted "false" @default.
- W2952504894 magId "2952504894" @default.
- W2952504894 workType "article" @default.