Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896632102> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2896632102 abstract "How to learn a discriminative fine-grained representation is a key point in many computer vision applications, such as person re-identification, fine-grained classification, fine-grained image retrieval, etc. Most of the previous methods focus on learning metrics or ensemble to derive better global representation, which are usually lack of local information. Based on the considerations above, we propose a novel Attribute-Aware Attention Model ($A^3M$), which can learn local attribute representation and global category representation simultaneously in an end-to-end manner. The proposed model contains two attention models: attribute-guided attention module uses attribute information to help select category features in different regions, at the same time, category-guided attention module selects local features of different attributes with the help of category cues. Through this attribute-category reciprocal process, local and global features benefit from each other. Finally, the resulting feature contains more intrinsic information for image recognition instead of the noisy and irrelevant features. Extensive experiments conducted on Market-1501, CompCars, CUB-200-2011 and CARS196 demonstrate the effectiveness of our $A^3M$. Code is available at https://github.com/iamhankai/attribute-aware-attention." @default.
- W2896632102 created "2018-10-26" @default.
- W2896632102 creator A5016185815 @default.
- W2896632102 creator A5018719202 @default.
- W2896632102 creator A5056485902 @default.
- W2896632102 creator A5089966579 @default.
- W2896632102 date "2018-10-15" @default.
- W2896632102 modified "2023-09-27" @default.
- W2896632102 title "Attribute-Aware Attention Model for Fine-grained Representation Learning" @default.
- W2896632102 cites W1928419358 @default.
- W2896632102 cites W1949591461 @default.
- W2896632102 cites W1958236864 @default.
- W2896632102 cites W1984514441 @default.
- W2896632102 cites W1994488211 @default.
- W2896632102 cites W2104657103 @default.
- W2896632102 cites W2117539524 @default.
- W2896632102 cites W2125889200 @default.
- W2896632102 cites W2135442311 @default.
- W2896632102 cites W2138011018 @default.
- W2896632102 cites W2194775991 @default.
- W2896632102 cites W2202499615 @default.
- W2896632102 cites W2207849498 @default.
- W2896632102 cites W2438305798 @default.
- W2896632102 cites W2479109623 @default.
- W2896632102 cites W2491664569 @default.
- W2896632102 cites W2502225121 @default.
- W2896632102 cites W2541843346 @default.
- W2896632102 cites W2608456260 @default.
- W2896632102 cites W2737725206 @default.
- W2896632102 cites W2764076527 @default.
- W2896632102 cites W2765268259 @default.
- W2896632102 cites W2779066530 @default.
- W2896632102 cites W2963656855 @default.
- W2896632102 cites W2963725249 @default.
- W2896632102 cites W2963954913 @default.
- W2896632102 cites W2964163358 @default.
- W2896632102 cites W3100555577 @default.
- W2896632102 cites W3102668440 @default.
- W2896632102 cites W3143107425 @default.
- W2896632102 cites W56385144 @default.
- W2896632102 doi "https://doi.org/10.1145/3240508.3240550" @default.
- W2896632102 hasPublicationYear "2018" @default.
- W2896632102 type Work @default.
- W2896632102 sameAs 2896632102 @default.
- W2896632102 citedByCount "97" @default.
- W2896632102 countsByYear W28966321022019 @default.
- W2896632102 countsByYear W28966321022020 @default.
- W2896632102 countsByYear W28966321022021 @default.
- W2896632102 countsByYear W28966321022022 @default.
- W2896632102 countsByYear W28966321022023 @default.
- W2896632102 crossrefType "proceedings-article" @default.
- W2896632102 hasAuthorship W2896632102A5016185815 @default.
- W2896632102 hasAuthorship W2896632102A5018719202 @default.
- W2896632102 hasAuthorship W2896632102A5056485902 @default.
- W2896632102 hasAuthorship W2896632102A5089966579 @default.
- W2896632102 hasBestOaLocation W28966321022 @default.
- W2896632102 hasConcept C154945302 @default.
- W2896632102 hasConcept C17744445 @default.
- W2896632102 hasConcept C199539241 @default.
- W2896632102 hasConcept C2776359362 @default.
- W2896632102 hasConcept C41008148 @default.
- W2896632102 hasConcept C59404180 @default.
- W2896632102 hasConcept C94625758 @default.
- W2896632102 hasConceptScore W2896632102C154945302 @default.
- W2896632102 hasConceptScore W2896632102C17744445 @default.
- W2896632102 hasConceptScore W2896632102C199539241 @default.
- W2896632102 hasConceptScore W2896632102C2776359362 @default.
- W2896632102 hasConceptScore W2896632102C41008148 @default.
- W2896632102 hasConceptScore W2896632102C59404180 @default.
- W2896632102 hasConceptScore W2896632102C94625758 @default.
- W2896632102 hasLocation W28966321021 @default.
- W2896632102 hasLocation W28966321022 @default.
- W2896632102 hasOpenAccess W2896632102 @default.
- W2896632102 hasPrimaryLocation W28966321021 @default.
- W2896632102 hasRelatedWork W1549289070 @default.
- W2896632102 hasRelatedWork W1889934247 @default.
- W2896632102 hasRelatedWork W2001353114 @default.
- W2896632102 hasRelatedWork W2104995483 @default.
- W2896632102 hasRelatedWork W2217419988 @default.
- W2896632102 hasRelatedWork W2334684970 @default.
- W2896632102 hasRelatedWork W2938696877 @default.
- W2896632102 hasRelatedWork W2940490924 @default.
- W2896632102 hasRelatedWork W4224259769 @default.
- W2896632102 hasRelatedWork W4285606578 @default.
- W2896632102 isParatext "false" @default.
- W2896632102 isRetracted "false" @default.
- W2896632102 magId "2896632102" @default.
- W2896632102 workType "article" @default.