FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971370469> ?p ?o ?g. }

• W2971370469 endingPage "896" @default.
• W2971370469 startingPage "883" @default.
• W2971370469 abstract "In multi-task learning, multiple interrelated tasks are jointly learned to achieve better performance. In many cases, if we can identify which tasks are related, we can also clearly identify which tasks are unrelated. In the past, most researchers emphasized exploiting correlations among interrelated tasks while completely ignoring the unrelated tasks that may provide valuable prior knowledge for multi-task learning. In this paper, a new approach is developed to hierarchically learn a tree of multi-task metrics by leveraging prior knowledge about both the related tasks and unrelated tasks. First, a visual tree is constructed to hierarchically organize large numbers of image categories in a coarse-to-fine fashion. Over the visual tree, a multi-task metric classifier is learned for each node by exploiting both the related and unrelated tasks, where the learning tasks for training the classifiers for the sibling child nodes under the same parent node are treated as the interrelated tasks, and the others are treated as the unrelated tasks. In addition, the node-specific metric for the parent node is propagated to its sibling child nodes to control inter-level error propagation. Our experimental results demonstrate that our hierarchical metric learning algorithm achieves better results than other state-of-the-art algorithms." @default.
• W2971370469 created "2019-09-12" @default.
• W2971370469 creator A5004311849 @default.
• W2971370469 creator A5039820086 @default.
• W2971370469 creator A5062655544 @default.
• W2971370469 creator A5063145868 @default.
• W2971370469 date "2020-01-01" @default.
• W2971370469 modified "2023-10-15" @default.
• W2971370469 title "Exploiting Related and Unrelated Tasks for Hierarchical Metric Learning and Image Classification" @default.
• W2971370469 cites W1851597118 @default.
• W2971370469 cites W1963882359 @default.
• W2971370469 cites W1964134198 @default.
• W2971370469 cites W1967732418 @default.
• W2971370469 cites W1979936637 @default.
• W2971370469 cites W1987083125 @default.
• W2971370469 cites W2014764728 @default.
• W2971370469 cites W2056450786 @default.
• W2971370469 cites W2061851712 @default.
• W2971370469 cites W2065180801 @default.
• W2971370469 cites W2081580037 @default.
• W2971370469 cites W2084401272 @default.
• W2971370469 cites W2089150756 @default.
• W2971370469 cites W2095979710 @default.
• W2971370469 cites W2097117768 @default.
• W2971370469 cites W2108598243 @default.
• W2971370469 cites W2116339064 @default.
• W2971370469 cites W2118696714 @default.
• W2971370469 cites W2123378748 @default.
• W2971370469 cites W2128017662 @default.
• W2971370469 cites W2137165876 @default.
• W2971370469 cites W2155893237 @default.
• W2971370469 cites W2165232124 @default.
• W2971370469 cites W2167372553 @default.
• W2971370469 cites W2169495281 @default.
• W2971370469 cites W2189540548 @default.
• W2971370469 cites W2194775991 @default.
• W2971370469 cites W2267727210 @default.
• W2971370469 cites W2321627895 @default.
• W2971370469 cites W2322020277 @default.
• W2971370469 cites W2417510252 @default.
• W2971370469 cites W2461228296 @default.
• W2971370469 cites W2583115687 @default.
• W2971370469 cites W2587977587 @default.
• W2971370469 cites W2603646780 @default.
• W2971370469 cites W2612647668 @default.
• W2971370469 cites W2734621611 @default.
• W2971370469 cites W2736435690 @default.
• W2971370469 cites W2740889030 @default.
• W2971370469 cites W2762381996 @default.
• W2971370469 cites W2963094609 @default.
• W2971370469 cites W2963495494 @default.
• W2971370469 cites W2964176323 @default.
• W2971370469 cites W2964189431 @default.
• W2971370469 cites W3103818906 @default.
• W2971370469 doi "https://doi.org/10.1109/tip.2019.2938321" @default.
• W2971370469 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31502971" @default.
• W2971370469 hasPublicationYear "2020" @default.
• W2971370469 type Work @default.
• W2971370469 sameAs 2971370469 @default.
• W2971370469 citedByCount "9" @default.
• W2971370469 countsByYear W29713704692021 @default.
• W2971370469 countsByYear W29713704692022 @default.
• W2971370469 countsByYear W29713704692023 @default.
• W2971370469 crossrefType "journal-article" @default.
• W2971370469 hasAuthorship W2971370469A5004311849 @default.
• W2971370469 hasAuthorship W2971370469A5039820086 @default.
• W2971370469 hasAuthorship W2971370469A5062655544 @default.
• W2971370469 hasAuthorship W2971370469A5063145868 @default.
• W2971370469 hasConcept C113174947 @default.
• W2971370469 hasConcept C119857082 @default.
• W2971370469 hasConcept C127413603 @default.
• W2971370469 hasConcept C134306372 @default.
• W2971370469 hasConcept C154945302 @default.
• W2971370469 hasConcept C162324750 @default.
• W2971370469 hasConcept C175154964 @default.
• W2971370469 hasConcept C176217482 @default.
• W2971370469 hasConcept C187736073 @default.
• W2971370469 hasConcept C21547014 @default.
• W2971370469 hasConcept C2780451532 @default.
• W2971370469 hasConcept C33923547 @default.
• W2971370469 hasConcept C41008148 @default.
• W2971370469 hasConcept C62611344 @default.
• W2971370469 hasConcept C66938386 @default.
• W2971370469 hasConcept C95623464 @default.
• W2971370469 hasConceptScore W2971370469C113174947 @default.
• W2971370469 hasConceptScore W2971370469C119857082 @default.
• W2971370469 hasConceptScore W2971370469C127413603 @default.
• W2971370469 hasConceptScore W2971370469C134306372 @default.
• W2971370469 hasConceptScore W2971370469C154945302 @default.
• W2971370469 hasConceptScore W2971370469C162324750 @default.
• W2971370469 hasConceptScore W2971370469C175154964 @default.
• W2971370469 hasConceptScore W2971370469C176217482 @default.
• W2971370469 hasConceptScore W2971370469C187736073 @default.
• W2971370469 hasConceptScore W2971370469C21547014 @default.
• W2971370469 hasConceptScore W2971370469C2780451532 @default.
• W2971370469 hasConceptScore W2971370469C33923547 @default.
• W2971370469 hasConceptScore W2971370469C41008148 @default.
• W2971370469 hasConceptScore W2971370469C62611344 @default.

• next