FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327571547> ?p ?o ?g. }

• W4327571547 endingPage "49" @default.
• W4327571547 startingPage "40" @default.
• W4327571547 abstract "This paper presents an effective method for strengthening the discriminative ability of high-level deep features by enhancing and aggregating discriminative part-level features for the fine-grained vehicle recognition task. In general, the task of visual recognition concentrates more on the visual differences at the object level. However, for fine-grained object recognition, the visual differences between target objects typically exist in local discriminative areas, so it is more concerned about extracting fine-grained features from these part regions. In this context, we propose solving this issue with a novel feature extraction method from two perspectives: the generation of more feature descriptors of part regions through the learning process of deep networks and the aggregation of part-level discriminative features. This approach is designed to improve the backbone networks to generate finer-level part features through a part-level feature enhancement module and to investigate the intrinsic part-level features of the backbone networks with the help of a feature aggregation module. The enhancement module efficiently finds the finer features highly correlated to the part regions. Then the feature aggregation module builds correlations of similar part features through feature grouping and fusion. Moreover, our proposed method does not require additional parts annotations and achieves comparable performance on two widely-used benchmarks for recognizing fine-grained vehicle types. Experimental results and explainable visualizations demonstrate the effectiveness of the proposed method." @default.
• W4327571547 created "2023-03-17" @default.
• W4327571547 creator A5007987726 @default.
• W4327571547 creator A5013736647 @default.
• W4327571547 creator A5022334521 @default.
• W4327571547 creator A5033316112 @default.
• W4327571547 date "2023-06-01" @default.
• W4327571547 modified "2023-09-26" @default.
• W4327571547 title "An efficient fine-grained vehicle recognition method based on part-level feature optimization" @default.
• W4327571547 cites W1677182931 @default.
• W4327571547 cites W1972702299 @default.
• W4327571547 cites W1979387426 @default.
• W4327571547 cites W2006904655 @default.
• W4327571547 cites W2179713099 @default.
• W4327571547 cites W2405089906 @default.
• W4327571547 cites W2592659495 @default.
• W4327571547 cites W2605117450 @default.
• W4327571547 cites W2734501611 @default.
• W4327571547 cites W2761909754 @default.
• W4327571547 cites W2763070548 @default.
• W4327571547 cites W2917452308 @default.
• W4327571547 cites W2963090248 @default.
• W4327571547 cites W2963725249 @default.
• W4327571547 cites W2976814977 @default.
• W4327571547 cites W3124951096 @default.
• W4327571547 cites W3136015878 @default.
• W4327571547 cites W3138239980 @default.
• W4327571547 cites W3173196825 @default.
• W4327571547 cites W3182672186 @default.
• W4327571547 cites W3187646339 @default.
• W4327571547 cites W4205395965 @default.
• W4327571547 cites W4205622807 @default.
• W4327571547 cites W4211144419 @default.
• W4327571547 cites W4280538209 @default.
• W4327571547 cites W4283361901 @default.
• W4327571547 cites W4285140062 @default.
• W4327571547 doi "https://doi.org/10.1016/j.neucom.2023.03.035" @default.
• W4327571547 hasPublicationYear "2023" @default.
• W4327571547 type Work @default.
• W4327571547 citedByCount "0" @default.
• W4327571547 crossrefType "journal-article" @default.
• W4327571547 hasAuthorship W4327571547A5007987726 @default.
• W4327571547 hasAuthorship W4327571547A5013736647 @default.
• W4327571547 hasAuthorship W4327571547A5022334521 @default.
• W4327571547 hasAuthorship W4327571547A5033316112 @default.
• W4327571547 hasConcept C111919701 @default.
• W4327571547 hasConcept C127413603 @default.
• W4327571547 hasConcept C138885662 @default.
• W4327571547 hasConcept C151730666 @default.
• W4327571547 hasConcept C153180895 @default.
• W4327571547 hasConcept C154945302 @default.
• W4327571547 hasConcept C201995342 @default.
• W4327571547 hasConcept C2776401178 @default.
• W4327571547 hasConcept C2779343474 @default.
• W4327571547 hasConcept C2780451532 @default.
• W4327571547 hasConcept C2781238097 @default.
• W4327571547 hasConcept C41008148 @default.
• W4327571547 hasConcept C41895202 @default.
• W4327571547 hasConcept C52622490 @default.
• W4327571547 hasConcept C59404180 @default.
• W4327571547 hasConcept C86803240 @default.
• W4327571547 hasConcept C97931131 @default.
• W4327571547 hasConcept C98045186 @default.
• W4327571547 hasConceptScore W4327571547C111919701 @default.
• W4327571547 hasConceptScore W4327571547C127413603 @default.
• W4327571547 hasConceptScore W4327571547C138885662 @default.
• W4327571547 hasConceptScore W4327571547C151730666 @default.
• W4327571547 hasConceptScore W4327571547C153180895 @default.
• W4327571547 hasConceptScore W4327571547C154945302 @default.
• W4327571547 hasConceptScore W4327571547C201995342 @default.
• W4327571547 hasConceptScore W4327571547C2776401178 @default.
• W4327571547 hasConceptScore W4327571547C2779343474 @default.
• W4327571547 hasConceptScore W4327571547C2780451532 @default.
• W4327571547 hasConceptScore W4327571547C2781238097 @default.
• W4327571547 hasConceptScore W4327571547C41008148 @default.
• W4327571547 hasConceptScore W4327571547C41895202 @default.
• W4327571547 hasConceptScore W4327571547C52622490 @default.
• W4327571547 hasConceptScore W4327571547C59404180 @default.
• W4327571547 hasConceptScore W4327571547C86803240 @default.
• W4327571547 hasConceptScore W4327571547C97931131 @default.
• W4327571547 hasConceptScore W4327571547C98045186 @default.
• W4327571547 hasFunder F4320336567 @default.
• W4327571547 hasLocation W43275715471 @default.
• W4327571547 hasOpenAccess W4327571547 @default.
• W4327571547 hasPrimaryLocation W43275715471 @default.
• W4327571547 hasRelatedWork W2285052147 @default.
• W4327571547 hasRelatedWork W2507989420 @default.
• W4327571547 hasRelatedWork W2546942002 @default.
• W4327571547 hasRelatedWork W2586441539 @default.
• W4327571547 hasRelatedWork W2743258233 @default.
• W4327571547 hasRelatedWork W2805177060 @default.
• W4327571547 hasRelatedWork W2806866760 @default.
• W4327571547 hasRelatedWork W2905846897 @default.
• W4327571547 hasRelatedWork W2998168123 @default.
• W4327571547 hasRelatedWork W4287995534 @default.
• W4327571547 hasVolume "536" @default.
• W4327571547 isParatext "false" @default.
• W4327571547 isRetracted "false" @default.

• next