FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224223485> ?p ?o ?g. }

• W4224223485 abstract "Retrieving tracked-vehicles by natural language descriptions plays a critical role in smart city construction. It aims to find the best match for the given texts from a set of tracked vehicles in surveillance videos. Existing works generally solve it by a dual-stream framework, which consists of a text encoder, a visual encoder and a cross-modal loss function. Although some progress has been made, they failed to fully exploit the information at various levels of granularity. To tackle this issue, we propose a novel framework for the natural language-based vehicle retrieval task, OMG, which Observes Multiple Granularities with respect to visual representation, textual representation and objective functions. For the visual representation, target features, context features and motion features are encoded separately. For the textual representation, one global embedding, three local embeddings and a color-type prompt embedding are extracted to represent various granularities of semantic features. Finally, the overall framework is optimized by a cross-modal multi-granularity contrastive loss function. Experiments demonstrate the effectiveness of our method. Our OMG significantly outperforms all previous methods and ranks the 9th on the 6th AI City Challenge Track2. The codes are available at https://github.com/dyhBUPT/OMG." @default.
• W4224223485 created "2022-04-26" @default.
• W4224223485 creator A5005092860 @default.
• W4224223485 creator A5040983509 @default.
• W4224223485 creator A5070830194 @default.
• W4224223485 creator A5076973244 @default.
• W4224223485 creator A5079144156 @default.
• W4224223485 creator A5081329968 @default.
• W4224223485 date "2022-06-01" @default.
• W4224223485 modified "2023-10-02" @default.
• W4224223485 title "OMG: Observe Multiple Granularities for Natural Language-Based Vehicle Retrieval" @default.
• W4224223485 cites W2064675550 @default.
• W4224223485 cites W2157331557 @default.
• W4224223485 cites W2194775991 @default.
• W4224223485 cites W2250539671 @default.
• W4224223485 cites W2251329024 @default.
• W4224223485 cites W2470322391 @default.
• W4224223485 cites W2519904008 @default.
• W4224223485 cites W2808399042 @default.
• W4224223485 cites W2963524571 @default.
• W4224223485 cites W2965843888 @default.
• W4224223485 cites W3105077954 @default.
• W4224223485 cites W3105232955 @default.
• W4224223485 cites W3138516171 @default.
• W4224223485 cites W3145807616 @default.
• W4224223485 cites W3173386860 @default.
• W4224223485 cites W3174110202 @default.
• W4224223485 cites W3174212835 @default.
• W4224223485 cites W3174607348 @default.
• W4224223485 cites W3174657572 @default.
• W4224223485 cites W3176421937 @default.
• W4224223485 cites W3176636394 @default.
• W4224223485 cites W3177014213 @default.
• W4224223485 cites W3177239160 @default.
• W4224223485 cites W3196529233 @default.
• W4224223485 cites W3204670646 @default.
• W4224223485 cites W3207042189 @default.
• W4224223485 cites W4210768491 @default.
• W4224223485 doi "https://doi.org/10.1109/cvprw56347.2022.00352" @default.
• W4224223485 hasPublicationYear "2022" @default.
• W4224223485 type Work @default.
• W4224223485 citedByCount "3" @default.
• W4224223485 countsByYear W42242234852022 @default.
• W4224223485 countsByYear W42242234852023 @default.
• W4224223485 crossrefType "proceedings-article" @default.
• W4224223485 hasAuthorship W4224223485A5005092860 @default.
• W4224223485 hasAuthorship W4224223485A5040983509 @default.
• W4224223485 hasAuthorship W4224223485A5070830194 @default.
• W4224223485 hasAuthorship W4224223485A5076973244 @default.
• W4224223485 hasAuthorship W4224223485A5079144156 @default.
• W4224223485 hasAuthorship W4224223485A5081329968 @default.
• W4224223485 hasBestOaLocation W42242234852 @default.
• W4224223485 hasConcept C111919701 @default.
• W4224223485 hasConcept C118505674 @default.
• W4224223485 hasConcept C151730666 @default.
• W4224223485 hasConcept C154945302 @default.
• W4224223485 hasConcept C165696696 @default.
• W4224223485 hasConcept C177264268 @default.
• W4224223485 hasConcept C17744445 @default.
• W4224223485 hasConcept C177774035 @default.
• W4224223485 hasConcept C185592680 @default.
• W4224223485 hasConcept C188027245 @default.
• W4224223485 hasConcept C195324797 @default.
• W4224223485 hasConcept C199360897 @default.
• W4224223485 hasConcept C199539241 @default.
• W4224223485 hasConcept C204321447 @default.
• W4224223485 hasConcept C23123220 @default.
• W4224223485 hasConcept C2776359362 @default.
• W4224223485 hasConcept C2779343474 @default.
• W4224223485 hasConcept C38652104 @default.
• W4224223485 hasConcept C41008148 @default.
• W4224223485 hasConcept C41608201 @default.
• W4224223485 hasConcept C71139939 @default.
• W4224223485 hasConcept C86803240 @default.
• W4224223485 hasConcept C94625758 @default.
• W4224223485 hasConceptScore W4224223485C111919701 @default.
• W4224223485 hasConceptScore W4224223485C118505674 @default.
• W4224223485 hasConceptScore W4224223485C151730666 @default.
• W4224223485 hasConceptScore W4224223485C154945302 @default.
• W4224223485 hasConceptScore W4224223485C165696696 @default.
• W4224223485 hasConceptScore W4224223485C177264268 @default.
• W4224223485 hasConceptScore W4224223485C17744445 @default.
• W4224223485 hasConceptScore W4224223485C177774035 @default.
• W4224223485 hasConceptScore W4224223485C185592680 @default.
• W4224223485 hasConceptScore W4224223485C188027245 @default.
• W4224223485 hasConceptScore W4224223485C195324797 @default.
• W4224223485 hasConceptScore W4224223485C199360897 @default.
• W4224223485 hasConceptScore W4224223485C199539241 @default.
• W4224223485 hasConceptScore W4224223485C204321447 @default.
• W4224223485 hasConceptScore W4224223485C23123220 @default.
• W4224223485 hasConceptScore W4224223485C2776359362 @default.
• W4224223485 hasConceptScore W4224223485C2779343474 @default.
• W4224223485 hasConceptScore W4224223485C38652104 @default.
• W4224223485 hasConceptScore W4224223485C41008148 @default.
• W4224223485 hasConceptScore W4224223485C41608201 @default.
• W4224223485 hasConceptScore W4224223485C71139939 @default.
• W4224223485 hasConceptScore W4224223485C86803240 @default.
• W4224223485 hasConceptScore W4224223485C94625758 @default.
• W4224223485 hasLocation W42242234851 @default.
• W4224223485 hasLocation W42242234852 @default.

• next