Matches in SemOpenAlex for { <https://semopenalex.org/work/W2292919962> ?p ?o ?g. }
- W2292919962 abstract "Textual data such as tags, sentence descriptions are combined with visual cues to reduce the semantic gap for image retrieval applications in today's Multimodal Image Retrieval (MIR) systems. However, all tags are treated as equally important in these systems, which may result in misalignment between visual and textual modalities during MIR training. This will further lead to degenerated retrieval performance at query time. To address this issue, we investigate the problem of tag importance prediction, where the goal is to automatically predict the tag importance and use it in image retrieval. To achieve this, we first propose a method to measure the relative importance of object and scene tags from image sentence descriptions. Using this as the ground truth, we present a tag importance prediction model to jointly exploit visual, semantic and context cues. The Structural Support Vector Machine (SSVM) formulation is adopted to ensure efficient training of the prediction model. Then, the Canonical Correlation Analysis (CCA) is employed to learn the relation between the image visual feature and tag importance to obtain robust retrieval performance. Experimental results on three real-world datasets show a significant performance improvement of the proposed MIR with Tag Importance Prediction (MIR/TIP) system over other MIR systems." @default.
- W2292919962 created "2016-06-24" @default.
- W2292919962 creator A5017846156 @default.
- W2292919962 creator A5040091310 @default.
- W2292919962 creator A5051293560 @default.
- W2292919962 creator A5063253432 @default.
- W2292919962 creator A5074059073 @default.
- W2292919962 date "2016-02-28" @default.
- W2292919962 modified "2023-09-27" @default.
- W2292919962 title "Measuring and Predicting Tag Importance for Image Retrieval" @default.
- W2292919962 cites W1176919 @default.
- W2292919962 cites W1202352811 @default.
- W2292919962 cites W1514027499 @default.
- W2292919962 cites W1521626219 @default.
- W2292919962 cites W1523385540 @default.
- W2292919962 cites W1566135517 @default.
- W2292919962 cites W1861492603 @default.
- W2292919962 cites W1938167356 @default.
- W2292919962 cites W2031248101 @default.
- W2292919962 cites W2059952380 @default.
- W2292919962 cites W2067816745 @default.
- W2292919962 cites W2075115202 @default.
- W2292919962 cites W2096544045 @default.
- W2292919962 cites W2100235303 @default.
- W2292919962 cites W2100379672 @default.
- W2292919962 cites W2102605133 @default.
- W2292919962 cites W2106277773 @default.
- W2292919962 cites W2108598243 @default.
- W2292919962 cites W2109305780 @default.
- W2292919962 cites W2118597426 @default.
- W2292919962 cites W2119775030 @default.
- W2292919962 cites W2123442489 @default.
- W2292919962 cites W2130055251 @default.
- W2292919962 cites W2130660124 @default.
- W2292919962 cites W2136064009 @default.
- W2292919962 cites W2137471889 @default.
- W2292919962 cites W2138118304 @default.
- W2292919962 cites W2141697695 @default.
- W2292919962 cites W2146103513 @default.
- W2292919962 cites W2147069236 @default.
- W2292919962 cites W2157530295 @default.
- W2292919962 cites W2161343988 @default.
- W2292919962 cites W2163740729 @default.
- W2292919962 cites W2165947725 @default.
- W2292919962 cites W2167407098 @default.
- W2292919962 cites W2168356304 @default.
- W2292919962 cites W2184188583 @default.
- W2292919962 cites W2277195237 @default.
- W2292919962 cites W2294130536 @default.
- W2292919962 cites W2429914308 @default.
- W2292919962 cites W2613718673 @default.
- W2292919962 cites W2913081710 @default.
- W2292919962 cites W2950325406 @default.
- W2292919962 cites W2970241052 @default.
- W2292919962 doi "https://doi.org/10.48550/arxiv.1602.08680" @default.
- W2292919962 hasPublicationYear "2016" @default.
- W2292919962 type Work @default.
- W2292919962 sameAs 2292919962 @default.
- W2292919962 citedByCount "0" @default.
- W2292919962 crossrefType "posted-content" @default.
- W2292919962 hasAuthorship W2292919962A5017846156 @default.
- W2292919962 hasAuthorship W2292919962A5040091310 @default.
- W2292919962 hasAuthorship W2292919962A5051293560 @default.
- W2292919962 hasAuthorship W2292919962A5063253432 @default.
- W2292919962 hasAuthorship W2292919962A5074059073 @default.
- W2292919962 hasBestOaLocation W22929199621 @default.
- W2292919962 hasConcept C115961682 @default.
- W2292919962 hasConcept C124101348 @default.
- W2292919962 hasConcept C138885662 @default.
- W2292919962 hasConcept C146849305 @default.
- W2292919962 hasConcept C151730666 @default.
- W2292919962 hasConcept C153180895 @default.
- W2292919962 hasConcept C154945302 @default.
- W2292919962 hasConcept C165696696 @default.
- W2292919962 hasConcept C1667742 @default.
- W2292919962 hasConcept C189391414 @default.
- W2292919962 hasConcept C204321447 @default.
- W2292919962 hasConcept C23123220 @default.
- W2292919962 hasConcept C25343380 @default.
- W2292919962 hasConcept C2776401178 @default.
- W2292919962 hasConcept C2777530160 @default.
- W2292919962 hasConcept C2779343474 @default.
- W2292919962 hasConcept C2781122975 @default.
- W2292919962 hasConcept C38652104 @default.
- W2292919962 hasConcept C41008148 @default.
- W2292919962 hasConcept C41895202 @default.
- W2292919962 hasConcept C86034646 @default.
- W2292919962 hasConcept C86803240 @default.
- W2292919962 hasConceptScore W2292919962C115961682 @default.
- W2292919962 hasConceptScore W2292919962C124101348 @default.
- W2292919962 hasConceptScore W2292919962C138885662 @default.
- W2292919962 hasConceptScore W2292919962C146849305 @default.
- W2292919962 hasConceptScore W2292919962C151730666 @default.
- W2292919962 hasConceptScore W2292919962C153180895 @default.
- W2292919962 hasConceptScore W2292919962C154945302 @default.
- W2292919962 hasConceptScore W2292919962C165696696 @default.
- W2292919962 hasConceptScore W2292919962C1667742 @default.
- W2292919962 hasConceptScore W2292919962C189391414 @default.
- W2292919962 hasConceptScore W2292919962C204321447 @default.
- W2292919962 hasConceptScore W2292919962C23123220 @default.