Matches in SemOpenAlex for { <https://semopenalex.org/work/W2119939615> ?p ?o ?g. }
- W2119939615 abstract "Visual reranking has been widely deployed to refine the quality of conventional content-based image retrieval engines. The current trend lies in employing a crowd of retrieved results stemming from multiple feature modalities to boost the overall performance of visual reranking. However, a major challenge pertaining to current reranking methods is how to take full advantage of the complementary property of distinct feature modalities. Given a query image and one feature modality, a regular visual reranking framework treats the top-ranked images as pseudo positive instances which are inevitably noisy, difficult to reveal this complementary property, and thus lead to inferior ranking performance. This paper proposes a novel image reranking approach by introducing a Co-Regularized Multi-Graph Learning (Co-RMGL) framework, in which the intra-graph and inter-graph constraints are simultaneously imposed to encode affinities in a single graph and consistency across different graphs. Moreover, weakly supervised learning driven by image attributes is performed to denoise the pseudo-labeled instances, thereby highlighting the unique strength of individual feature modality. Meanwhile, such learning can yield a few anchors in graphs that vitally enable the alignment and fusion of multiple graphs. As a result, an edge weight matrix learned from the fused graph automatically gives the ordering to the initially retrieved results. We evaluate our approach on four benchmark image retrieval datasets, demonstrating a significant performance gain over the state-of-the-arts." @default.
- W2119939615 created "2016-06-24" @default.
- W2119939615 creator A5015874725 @default.
- W2119939615 creator A5016080094 @default.
- W2119939615 creator A5056569344 @default.
- W2119939615 creator A5071037763 @default.
- W2119939615 creator A5074103823 @default.
- W2119939615 date "2013-12-01" @default.
- W2119939615 modified "2023-10-18" @default.
- W2119939615 title "Visual Reranking through Weakly Supervised Multi-graph Learning" @default.
- W2119939615 cites W1566135517 @default.
- W2119939615 cites W1969926026 @default.
- W2119939615 cites W1988421392 @default.
- W2119939615 cites W1989060270 @default.
- W2119939615 cites W2023991840 @default.
- W2119939615 cites W2035821475 @default.
- W2119939615 cites W2052916917 @default.
- W2119939615 cites W2053186076 @default.
- W2119939615 cites W2076188996 @default.
- W2119939615 cites W2084435358 @default.
- W2119939615 cites W2098411764 @default.
- W2119939615 cites W2099528205 @default.
- W2119939615 cites W2100556411 @default.
- W2119939615 cites W2128017662 @default.
- W2119939615 cites W2137675680 @default.
- W2119939615 cites W2141362318 @default.
- W2119939615 cites W2148809531 @default.
- W2119939615 cites W2151509460 @default.
- W2119939615 cites W2158427031 @default.
- W2119939615 cites W2161149720 @default.
- W2119939615 cites W2162915993 @default.
- W2119939615 cites W2294130536 @default.
- W2119939615 cites W2536626143 @default.
- W2119939615 cites W3143107425 @default.
- W2119939615 doi "https://doi.org/10.1109/iccv.2013.323" @default.
- W2119939615 hasPublicationYear "2013" @default.
- W2119939615 type Work @default.
- W2119939615 sameAs 2119939615 @default.
- W2119939615 citedByCount "70" @default.
- W2119939615 countsByYear W21199396152014 @default.
- W2119939615 countsByYear W21199396152015 @default.
- W2119939615 countsByYear W21199396152016 @default.
- W2119939615 countsByYear W21199396152017 @default.
- W2119939615 countsByYear W21199396152018 @default.
- W2119939615 countsByYear W21199396152019 @default.
- W2119939615 countsByYear W21199396152020 @default.
- W2119939615 countsByYear W21199396152021 @default.
- W2119939615 countsByYear W21199396152022 @default.
- W2119939615 countsByYear W21199396152023 @default.
- W2119939615 crossrefType "proceedings-article" @default.
- W2119939615 hasAuthorship W2119939615A5015874725 @default.
- W2119939615 hasAuthorship W2119939615A5016080094 @default.
- W2119939615 hasAuthorship W2119939615A5056569344 @default.
- W2119939615 hasAuthorship W2119939615A5071037763 @default.
- W2119939615 hasAuthorship W2119939615A5074103823 @default.
- W2119939615 hasConcept C119857082 @default.
- W2119939615 hasConcept C132525143 @default.
- W2119939615 hasConcept C13280743 @default.
- W2119939615 hasConcept C138885662 @default.
- W2119939615 hasConcept C153180895 @default.
- W2119939615 hasConcept C154945302 @default.
- W2119939615 hasConcept C185798385 @default.
- W2119939615 hasConcept C189430467 @default.
- W2119939615 hasConcept C205649164 @default.
- W2119939615 hasConcept C2776401178 @default.
- W2119939615 hasConcept C2776436953 @default.
- W2119939615 hasConcept C41008148 @default.
- W2119939615 hasConcept C41895202 @default.
- W2119939615 hasConcept C80444323 @default.
- W2119939615 hasConcept C86037889 @default.
- W2119939615 hasConceptScore W2119939615C119857082 @default.
- W2119939615 hasConceptScore W2119939615C132525143 @default.
- W2119939615 hasConceptScore W2119939615C13280743 @default.
- W2119939615 hasConceptScore W2119939615C138885662 @default.
- W2119939615 hasConceptScore W2119939615C153180895 @default.
- W2119939615 hasConceptScore W2119939615C154945302 @default.
- W2119939615 hasConceptScore W2119939615C185798385 @default.
- W2119939615 hasConceptScore W2119939615C189430467 @default.
- W2119939615 hasConceptScore W2119939615C205649164 @default.
- W2119939615 hasConceptScore W2119939615C2776401178 @default.
- W2119939615 hasConceptScore W2119939615C2776436953 @default.
- W2119939615 hasConceptScore W2119939615C41008148 @default.
- W2119939615 hasConceptScore W2119939615C41895202 @default.
- W2119939615 hasConceptScore W2119939615C80444323 @default.
- W2119939615 hasConceptScore W2119939615C86037889 @default.
- W2119939615 hasLocation W21199396151 @default.
- W2119939615 hasOpenAccess W2119939615 @default.
- W2119939615 hasPrimaryLocation W21199396151 @default.
- W2119939615 hasRelatedWork W1786507113 @default.
- W2119939615 hasRelatedWork W1998850041 @default.
- W2119939615 hasRelatedWork W2039826537 @default.
- W2119939615 hasRelatedWork W2048843004 @default.
- W2119939615 hasRelatedWork W2097116485 @default.
- W2119939615 hasRelatedWork W2104465941 @default.
- W2119939615 hasRelatedWork W2293317945 @default.
- W2119939615 hasRelatedWork W2884983377 @default.
- W2119939615 hasRelatedWork W2954428433 @default.
- W2119939615 hasRelatedWork W2587195495 @default.
- W2119939615 isParatext "false" @default.
- W2119939615 isRetracted "false" @default.