FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2497173630> ?p ?o ?g. }

• W2497173630 endingPage "4024" @default.
• W2497173630 startingPage "4014" @default.
• W2497173630 abstract "How do we retrieve images accurately? Also, how do we rank a group of images precisely and efficiently for specific queries? These problems are critical for researchers and engineers to generate a novel image searching engine. First, it is important to obtain an appropriate description that effectively represent the images. In this paper, multimodal features are considered for describing images. The images unique properties are reflected by visual features, which are correlated to each other. However, semantic gaps always exist between images visual features and semantics. Therefore, we utilize click feature to reduce the semantic gap. The second key issue is learning an appropriate distance metric to combine these multimodal features. This paper develops a novel deep multimodal distance metric learning (Deep-MDML) method. A structured ranking model is adopted to utilize both visual and click features in distance metric learning (DML). Specifically, images and their related ranking results are first collected to form the training set. Multimodal features, including click and visual features, are collected with these images. Next, a group of autoencoders is applied to obtain initially a distance metric in different visual spaces, and an MDML method is used to assign optimal weights for different modalities. Next, we conduct alternating optimization to train the ranking model, which is used for the ranking of new queries with click features. Compared with existing image ranking methods, the proposed method adopts a new ranking model to use multimodal features, including click features and visual features in DML. We operated experiments to analyze the proposed Deep-MDML in two benchmark data sets, and the results validate the effects of the method." @default.
• W2497173630 created "2016-08-23" @default.
• W2497173630 creator A5019708391 @default.
• W2497173630 creator A5037308328 @default.
• W2497173630 creator A5050817770 @default.
• W2497173630 creator A5074103823 @default.
• W2497173630 date "2017-12-01" @default.
• W2497173630 modified "2023-10-16" @default.
• W2497173630 title "Deep Multimodal Distance Metric Learning Using Click Constraints for Image Ranking" @default.
• W2497173630 cites W1920291194 @default.
• W2497173630 cites W1936750108 @default.
• W2497173630 cites W1964810009 @default.
• W2497173630 cites W1969732194 @default.
• W2497173630 cites W1981613567 @default.
• W2497173630 cites W2002370809 @default.
• W2497173630 cites W2008297189 @default.
• W2497173630 cites W2012495032 @default.
• W2497173630 cites W2019972236 @default.
• W2497173630 cites W2024082504 @default.
• W2497173630 cites W2035720976 @default.
• W2497173630 cites W2035849021 @default.
• W2497173630 cites W2047221353 @default.
• W2497173630 cites W2062483254 @default.
• W2497173630 cites W2062553660 @default.
• W2497173630 cites W2063490865 @default.
• W2497173630 cites W2069870183 @default.
• W2497173630 cites W2072750214 @default.
• W2497173630 cites W2076434944 @default.
• W2497173630 cites W2080928936 @default.
• W2497173630 cites W2097117768 @default.
• W2497173630 cites W2102605133 @default.
• W2497173630 cites W2109305780 @default.
• W2497173630 cites W2123099218 @default.
• W2497173630 cites W2124386111 @default.
• W2497173630 cites W2126493897 @default.
• W2497173630 cites W2130660124 @default.
• W2497173630 cites W2133126147 @default.
• W2497173630 cites W2135645798 @default.
• W2497173630 cites W2137675680 @default.
• W2497173630 cites W2137736727 @default.
• W2497173630 cites W2143166796 @default.
• W2497173630 cites W2144679084 @default.
• W2497173630 cites W2147069236 @default.
• W2497173630 cites W2147277317 @default.
• W2497173630 cites W2149427297 @default.
• W2497173630 cites W2150491921 @default.
• W2497173630 cites W2153783077 @default.
• W2497173630 cites W2160555926 @default.
• W2497173630 cites W2161343988 @default.
• W2497173630 cites W2321627895 @default.
• W2497173630 cites W2323770312 @default.
• W2497173630 cites W2397306716 @default.
• W2497173630 cites W2408719493 @default.
• W2497173630 cites W2429914308 @default.
• W2497173630 cites W2460669233 @default.
• W2497173630 cites W2461228296 @default.
• W2497173630 cites W4231109964 @default.
• W2497173630 cites W4254926608 @default.
• W2497173630 doi "https://doi.org/10.1109/tcyb.2016.2591583" @default.
• W2497173630 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/27529881" @default.
• W2497173630 hasPublicationYear "2017" @default.
• W2497173630 type Work @default.
• W2497173630 sameAs 2497173630 @default.
• W2497173630 citedByCount "249" @default.
• W2497173630 countsByYear W24971736302012 @default.
• W2497173630 countsByYear W24971736302017 @default.
• W2497173630 countsByYear W24971736302018 @default.
• W2497173630 countsByYear W24971736302019 @default.
• W2497173630 countsByYear W24971736302020 @default.
• W2497173630 countsByYear W24971736302021 @default.
• W2497173630 countsByYear W24971736302022 @default.
• W2497173630 countsByYear W24971736302023 @default.
• W2497173630 crossrefType "journal-article" @default.
• W2497173630 hasAuthorship W2497173630A5019708391 @default.
• W2497173630 hasAuthorship W2497173630A5037308328 @default.
• W2497173630 hasAuthorship W2497173630A5050817770 @default.
• W2497173630 hasAuthorship W2497173630A5074103823 @default.
• W2497173630 hasConcept C108583219 @default.
• W2497173630 hasConcept C114614502 @default.
• W2497173630 hasConcept C115961682 @default.
• W2497173630 hasConcept C119857082 @default.
• W2497173630 hasConcept C138885662 @default.
• W2497173630 hasConcept C153180895 @default.
• W2497173630 hasConcept C154945302 @default.
• W2497173630 hasConcept C162324750 @default.
• W2497173630 hasConcept C164226766 @default.
• W2497173630 hasConcept C1667742 @default.
• W2497173630 hasConcept C176217482 @default.
• W2497173630 hasConcept C184337299 @default.
• W2497173630 hasConcept C189430467 @default.
• W2497173630 hasConcept C199360897 @default.
• W2497173630 hasConcept C21547014 @default.
• W2497173630 hasConcept C23123220 @default.
• W2497173630 hasConcept C2776401178 @default.
• W2497173630 hasConcept C33923547 @default.
• W2497173630 hasConcept C36464697 @default.
• W2497173630 hasConcept C41008148 @default.
• W2497173630 hasConcept C41895202 @default.

• next