Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288808839> ?p ?o ?g. }
- W4288808839 endingPage "109447" @default.
- W4288808839 startingPage "109447" @default.
- W4288808839 abstract "Fine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a specific photo from a given query sketch. However, its widespread applicability is limited because it is difficult for most people to draw a complete sketch, and the drawing process is often time consuming. In this study, we aim to retrieve the target photo from an partial sketch with the least number of strokes possible; the method is referred to as on-the-fly FG-SBIR (Bhunia et al., 2020), in which the retrieval begins after each stroke of the drawing. We consider that a significant correlation exists between these incomplete sketches in the sketch-drawing episodes of each photo. We propose a multi-granularity-association-learning method that further optimizes the embedding space of all incomplete sketches to learn an efficient joint-embedding space. Specifically, based on the integrity of the sketch, a complete sketch episode can be divided into several stages, each of which corresponds to a simple linear-mapping layer. Furthermore, our framework guides the vector space representation of the current sketch to approximate that with its later sketches. In this manner, the retrieval performance of a sketch with fewer strokes can approach that of a sketch with more strokes. We conducted experiments that included more realistic challenges, and our method achieved superior early-retrieval efficiency over the state-of-the-art methods and alternative baselines on two publicly available fine-grained sketch-retrieval datasets." @default.
- W4288808839 created "2022-07-30" @default.
- W4288808839 creator A5026256433 @default.
- W4288808839 creator A5031220156 @default.
- W4288808839 creator A5031693421 @default.
- W4288808839 creator A5037908770 @default.
- W4288808839 creator A5060987351 @default.
- W4288808839 date "2022-10-01" @default.
- W4288808839 modified "2023-10-01" @default.
- W4288808839 title "Multi-granularity Association Learning for On-the-fly Fine-grained Sketch-based Image Retrieval" @default.
- W4288808839 cites W1503798456 @default.
- W4288808839 cites W1895722194 @default.
- W4288808839 cites W2030137299 @default.
- W4288808839 cites W2117539524 @default.
- W4288808839 cites W2124386111 @default.
- W4288808839 cites W2128543433 @default.
- W4288808839 cites W2183341477 @default.
- W4288808839 cites W2467281799 @default.
- W4288808839 cites W2603445054 @default.
- W4288808839 cites W2606271862 @default.
- W4288808839 cites W2776402438 @default.
- W4288808839 cites W2791221471 @default.
- W4288808839 cites W2908869154 @default.
- W4288808839 cites W2922154534 @default.
- W4288808839 cites W2938500406 @default.
- W4288808839 cites W2942422815 @default.
- W4288808839 cites W2945895945 @default.
- W4288808839 cites W2947758276 @default.
- W4288808839 cites W2948085278 @default.
- W4288808839 cites W2962721615 @default.
- W4288808839 cites W2963073614 @default.
- W4288808839 cites W2963255313 @default.
- W4288808839 cites W2964266708 @default.
- W4288808839 cites W2982693525 @default.
- W4288808839 cites W2989207674 @default.
- W4288808839 cites W2994974226 @default.
- W4288808839 cites W3006025420 @default.
- W4288808839 cites W3031875317 @default.
- W4288808839 cites W3034603197 @default.
- W4288808839 cites W3035058753 @default.
- W4288808839 cites W3043547428 @default.
- W4288808839 cites W3092054443 @default.
- W4288808839 cites W3093027278 @default.
- W4288808839 cites W3101029400 @default.
- W4288808839 cites W3108870912 @default.
- W4288808839 cites W3176372702 @default.
- W4288808839 cites W3186006359 @default.
- W4288808839 doi "https://doi.org/10.1016/j.knosys.2022.109447" @default.
- W4288808839 hasPublicationYear "2022" @default.
- W4288808839 type Work @default.
- W4288808839 citedByCount "5" @default.
- W4288808839 countsByYear W42888088392022 @default.
- W4288808839 countsByYear W42888088392023 @default.
- W4288808839 crossrefType "journal-article" @default.
- W4288808839 hasAuthorship W4288808839A5026256433 @default.
- W4288808839 hasAuthorship W4288808839A5031220156 @default.
- W4288808839 hasAuthorship W4288808839A5031693421 @default.
- W4288808839 hasAuthorship W4288808839A5037908770 @default.
- W4288808839 hasAuthorship W4288808839A5060987351 @default.
- W4288808839 hasConcept C111472728 @default.
- W4288808839 hasConcept C111919701 @default.
- W4288808839 hasConcept C11413529 @default.
- W4288808839 hasConcept C115961682 @default.
- W4288808839 hasConcept C138885662 @default.
- W4288808839 hasConcept C142853389 @default.
- W4288808839 hasConcept C154945302 @default.
- W4288808839 hasConcept C1667742 @default.
- W4288808839 hasConcept C177774035 @default.
- W4288808839 hasConcept C23123220 @default.
- W4288808839 hasConcept C2779231336 @default.
- W4288808839 hasConcept C2781020372 @default.
- W4288808839 hasConcept C31972630 @default.
- W4288808839 hasConcept C41008148 @default.
- W4288808839 hasConceptScore W4288808839C111472728 @default.
- W4288808839 hasConceptScore W4288808839C111919701 @default.
- W4288808839 hasConceptScore W4288808839C11413529 @default.
- W4288808839 hasConceptScore W4288808839C115961682 @default.
- W4288808839 hasConceptScore W4288808839C138885662 @default.
- W4288808839 hasConceptScore W4288808839C142853389 @default.
- W4288808839 hasConceptScore W4288808839C154945302 @default.
- W4288808839 hasConceptScore W4288808839C1667742 @default.
- W4288808839 hasConceptScore W4288808839C177774035 @default.
- W4288808839 hasConceptScore W4288808839C23123220 @default.
- W4288808839 hasConceptScore W4288808839C2779231336 @default.
- W4288808839 hasConceptScore W4288808839C2781020372 @default.
- W4288808839 hasConceptScore W4288808839C31972630 @default.
- W4288808839 hasConceptScore W4288808839C41008148 @default.
- W4288808839 hasFunder F4320321543 @default.
- W4288808839 hasFunder F4320323172 @default.
- W4288808839 hasFunder F4320327726 @default.
- W4288808839 hasLocation W42888088391 @default.
- W4288808839 hasOpenAccess W4288808839 @default.
- W4288808839 hasPrimaryLocation W42888088391 @default.
- W4288808839 hasRelatedWork W1926504679 @default.
- W4288808839 hasRelatedWork W2106795979 @default.
- W4288808839 hasRelatedWork W2130228941 @default.
- W4288808839 hasRelatedWork W2161229648 @default.
- W4288808839 hasRelatedWork W2305650600 @default.