Matches in SemOpenAlex for { <https://semopenalex.org/work/W3098623295> ?p ?o ?g. }
- W3098623295 endingPage "4421" @default.
- W3098623295 startingPage "4410" @default.
- W3098623295 abstract "In this paper, we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While, most SBIR approaches focus on extracting low- and mid-level descriptors for direct feature matching, recent works have shown the benefit of learning coupled feature representations to describe data from two related sources. However, cross-domain representation learning methods are typically cast into non-convex minimization problems that are difficult to optimize, leading to unsatisfactory performance. Inspired by self-paced learning (SPL), a learning methodology designed to overcome convergence issues related to local optima by exploiting the samples in a meaningful order (i.e., easy to hard), we introduce the cross-paced partial curriculum learning (CPPCL) framework. Compared with existing SPL methods which only consider a single modality and cannot deal with prior knowledge, CPPCL is specifically designed to assess the learning pace by jointly handling data from dual sources and modality-specific prior information provided in the form of partial curricula. In addition, thanks to the learned dictionaries, we demonstrate that the proposed CPPCL embeds robust coupled representations for SBIR. Our approach is extensively evaluated on four publicly available datasets (i.e., CUFS, Flickr15K, QueenMary SBIR, and TU-Berlin Extension datasets), showing superior performance over competing SBIR methods." @default.
- W3098623295 created "2020-11-23" @default.
- W3098623295 creator A5027171279 @default.
- W3098623295 creator A5036987388 @default.
- W3098623295 creator A5065059558 @default.
- W3098623295 creator A5066621495 @default.
- W3098623295 creator A5069109233 @default.
- W3098623295 date "2018-09-01" @default.
- W3098623295 modified "2023-10-14" @default.
- W3098623295 title "Cross-Paced Representation Learning With Partial Curricula for Sketch-Based Image Retrieval" @default.
- W3098623295 cites W1479841565 @default.
- W3098623295 cites W1503798456 @default.
- W3098623295 cites W1892078565 @default.
- W3098623295 cites W1895722194 @default.
- W3098623295 cites W1924762813 @default.
- W3098623295 cites W1964073652 @default.
- W3098623295 cites W1972420097 @default.
- W3098623295 cites W1975771248 @default.
- W3098623295 cites W1995137594 @default.
- W3098623295 cites W2030137299 @default.
- W3098623295 cites W2030899956 @default.
- W3098623295 cites W2031489346 @default.
- W3098623295 cites W2066624635 @default.
- W3098623295 cites W2069426496 @default.
- W3098623295 cites W2100556411 @default.
- W3098623295 cites W2102662521 @default.
- W3098623295 cites W2110807182 @default.
- W3098623295 cites W2121058967 @default.
- W3098623295 cites W2124386111 @default.
- W3098623295 cites W2128543433 @default.
- W3098623295 cites W2136995369 @default.
- W3098623295 cites W2149481809 @default.
- W3098623295 cites W2153288431 @default.
- W3098623295 cites W2153404544 @default.
- W3098623295 cites W2156689847 @default.
- W3098623295 cites W2161969291 @default.
- W3098623295 cites W2162915993 @default.
- W3098623295 cites W2166257042 @default.
- W3098623295 cites W2170653751 @default.
- W3098623295 cites W2295088417 @default.
- W3098623295 cites W2296073425 @default.
- W3098623295 cites W2332729875 @default.
- W3098623295 cites W2466618734 @default.
- W3098623295 cites W2471581439 @default.
- W3098623295 cites W2511925527 @default.
- W3098623295 cites W2527420824 @default.
- W3098623295 cites W2536599074 @default.
- W3098623295 cites W2603445054 @default.
- W3098623295 cites W2605938684 @default.
- W3098623295 cites W2608295741 @default.
- W3098623295 doi "https://doi.org/10.1109/tip.2018.2837381" @default.
- W3098623295 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29870357" @default.
- W3098623295 hasPublicationYear "2018" @default.
- W3098623295 type Work @default.
- W3098623295 sameAs 3098623295 @default.
- W3098623295 citedByCount "12" @default.
- W3098623295 countsByYear W30986232952018 @default.
- W3098623295 countsByYear W30986232952019 @default.
- W3098623295 countsByYear W30986232952020 @default.
- W3098623295 countsByYear W30986232952021 @default.
- W3098623295 countsByYear W30986232952022 @default.
- W3098623295 countsByYear W30986232952023 @default.
- W3098623295 crossrefType "journal-article" @default.
- W3098623295 hasAuthorship W3098623295A5027171279 @default.
- W3098623295 hasAuthorship W3098623295A5036987388 @default.
- W3098623295 hasAuthorship W3098623295A5065059558 @default.
- W3098623295 hasAuthorship W3098623295A5066621495 @default.
- W3098623295 hasAuthorship W3098623295A5069109233 @default.
- W3098623295 hasBestOaLocation W30986232952 @default.
- W3098623295 hasConcept C105795698 @default.
- W3098623295 hasConcept C11413529 @default.
- W3098623295 hasConcept C119857082 @default.
- W3098623295 hasConcept C120665830 @default.
- W3098623295 hasConcept C121332964 @default.
- W3098623295 hasConcept C13280743 @default.
- W3098623295 hasConcept C134306372 @default.
- W3098623295 hasConcept C138885662 @default.
- W3098623295 hasConcept C153180895 @default.
- W3098623295 hasConcept C154945302 @default.
- W3098623295 hasConcept C165064840 @default.
- W3098623295 hasConcept C17744445 @default.
- W3098623295 hasConcept C185798385 @default.
- W3098623295 hasConcept C192209626 @default.
- W3098623295 hasConcept C199539241 @default.
- W3098623295 hasConcept C205649164 @default.
- W3098623295 hasConcept C2776359362 @default.
- W3098623295 hasConcept C2776401178 @default.
- W3098623295 hasConcept C2779231336 @default.
- W3098623295 hasConcept C33923547 @default.
- W3098623295 hasConcept C36503486 @default.
- W3098623295 hasConcept C41008148 @default.
- W3098623295 hasConcept C41895202 @default.
- W3098623295 hasConcept C59404180 @default.
- W3098623295 hasConcept C94625758 @default.
- W3098623295 hasConceptScore W3098623295C105795698 @default.
- W3098623295 hasConceptScore W3098623295C11413529 @default.
- W3098623295 hasConceptScore W3098623295C119857082 @default.
- W3098623295 hasConceptScore W3098623295C120665830 @default.