FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035212740> ?p ?o ?g. }

• W3035212740 abstract "Cross-modal matching has been a highlighted research topic in both vision and language areas. Learning appropriate mining strategy to sample and weight informative pairs is crucial for the cross-modal matching performance. However, most existing metric learning methods are developed for unimodal matching, which is unsuitable for cross-modal matching on multimodal data with heterogeneous features. To address this problem, we propose a simple and interpretable universal weighting framework for cross-modal matching, which provides a tool to analyze the interpretability of various loss functions. Furthermore, we introduce a new polynomial loss under the universal weighting framework, which defines a weight function for the positive and negative informative pairs respectively. Experimental results on two image-text matching benchmarks and two video-text matching benchmarks validate the efficacy of the proposed method." @default.
• W3035212740 created "2020-06-19" @default.
• W3035212740 creator A5009074046 @default.
• W3035212740 creator A5037117576 @default.
• W3035212740 creator A5049692788 @default.
• W3035212740 creator A5052993469 @default.
• W3035212740 creator A5060342584 @default.
• W3035212740 creator A5068950059 @default.
• W3035212740 date "2020-06-01" @default.
• W3035212740 modified "2023-09-30" @default.
• W3035212740 title "Universal Weighting Metric Learning for Cross-Modal Matching" @default.
• W3035212740 cites W2131774270 @default.
• W3035212740 cites W2185175083 @default.
• W3035212740 cites W2194775991 @default.
• W3035212740 cites W2289324734 @default.
• W3035212740 cites W2346746376 @default.
• W3035212740 cites W2425121537 @default.
• W3035212740 cites W2546696630 @default.
• W3035212740 cites W2564325886 @default.
• W3035212740 cites W2591669147 @default.
• W3035212740 cites W2745461083 @default.
• W3035212740 cites W2765440071 @default.
• W3035212740 cites W2778100917 @default.
• W3035212740 cites W2795389793 @default.
• W3035212740 cites W2808399042 @default.
• W3035212740 cites W2887712318 @default.
• W3035212740 cites W2907166662 @default.
• W3035212740 cites W2917742317 @default.
• W3035212740 cites W2956018683 @default.
• W3035212740 cites W2962856082 @default.
• W3035212740 cites W2962861647 @default.
• W3035212740 cites W2962958773 @default.
• W3035212740 cites W2963467339 @default.
• W3035212740 cites W2963775347 @default.
• W3035212740 cites W2963916161 @default.
• W3035212740 cites W2964120214 @default.
• W3035212740 cites W2974497444 @default.
• W3035212740 cites W2975761438 @default.
• W3035212740 cites W2981448908 @default.
• W3035212740 cites W2988823324 @default.
• W3035212740 cites W3000633154 @default.
• W3035212740 cites W3003735286 @default.
• W3035212740 cites W3101029400 @default.
• W3035212740 cites W3102887392 @default.
• W3035212740 doi "https://doi.org/10.1109/cvpr42600.2020.01302" @default.
• W3035212740 hasPublicationYear "2020" @default.
• W3035212740 type Work @default.
• W3035212740 sameAs 3035212740 @default.
• W3035212740 citedByCount "53" @default.
• W3035212740 countsByYear W30352127402020 @default.
• W3035212740 countsByYear W30352127402021 @default.
• W3035212740 countsByYear W30352127402022 @default.
• W3035212740 countsByYear W30352127402023 @default.
• W3035212740 crossrefType "proceedings-article" @default.
• W3035212740 hasAuthorship W3035212740A5009074046 @default.
• W3035212740 hasAuthorship W3035212740A5037117576 @default.
• W3035212740 hasAuthorship W3035212740A5049692788 @default.
• W3035212740 hasAuthorship W3035212740A5052993469 @default.
• W3035212740 hasAuthorship W3035212740A5060342584 @default.
• W3035212740 hasAuthorship W3035212740A5068950059 @default.
• W3035212740 hasBestOaLocation W30352127402 @default.
• W3035212740 hasConcept C105795698 @default.
• W3035212740 hasConcept C111472728 @default.
• W3035212740 hasConcept C119857082 @default.
• W3035212740 hasConcept C124101348 @default.
• W3035212740 hasConcept C126838900 @default.
• W3035212740 hasConcept C127413603 @default.
• W3035212740 hasConcept C138885662 @default.
• W3035212740 hasConcept C14036430 @default.
• W3035212740 hasConcept C153180895 @default.
• W3035212740 hasConcept C154945302 @default.
• W3035212740 hasConcept C165064840 @default.
• W3035212740 hasConcept C176217482 @default.
• W3035212740 hasConcept C183115368 @default.
• W3035212740 hasConcept C185592680 @default.
• W3035212740 hasConcept C188027245 @default.
• W3035212740 hasConcept C189430467 @default.
• W3035212740 hasConcept C21547014 @default.
• W3035212740 hasConcept C2780586882 @default.
• W3035212740 hasConcept C2781067378 @default.
• W3035212740 hasConcept C33923547 @default.
• W3035212740 hasConcept C41008148 @default.
• W3035212740 hasConcept C70136482 @default.
• W3035212740 hasConcept C71139939 @default.
• W3035212740 hasConcept C71924100 @default.
• W3035212740 hasConcept C78458016 @default.
• W3035212740 hasConcept C86803240 @default.
• W3035212740 hasConceptScore W3035212740C105795698 @default.
• W3035212740 hasConceptScore W3035212740C111472728 @default.
• W3035212740 hasConceptScore W3035212740C119857082 @default.
• W3035212740 hasConceptScore W3035212740C124101348 @default.
• W3035212740 hasConceptScore W3035212740C126838900 @default.
• W3035212740 hasConceptScore W3035212740C127413603 @default.
• W3035212740 hasConceptScore W3035212740C138885662 @default.
• W3035212740 hasConceptScore W3035212740C14036430 @default.
• W3035212740 hasConceptScore W3035212740C153180895 @default.
• W3035212740 hasConceptScore W3035212740C154945302 @default.
• W3035212740 hasConceptScore W3035212740C165064840 @default.
• W3035212740 hasConceptScore W3035212740C176217482 @default.
• W3035212740 hasConceptScore W3035212740C183115368 @default.

• next