FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089912071> ?p ?o ?g. }

• W3089912071 abstract "Abstract The lack of labeled exemplars makes video classification based on supervised neural networks difficult and challenging. Utilizing external memory that contains task-related knowledge is a beneficial way to learn a category from a handful of samples; however, most existing memory-augmented neural networks still struggle to provide a satisfactory solution for multi-modal external data due to the high dimensionality and massive volume. In light of this, we propose a Memory Transformation Network (MTN) to convert external knowledge, by involving embedded and concentrated memories, so as to leverage it feasibly for video classification with weak supervision. Specifically, we employ a multi-modal deep autoencoder to project external visual and textual information onto a shared space to produce joint embedded memory, which can capture the correlation amongst different modalities to enhance the expressive ability. The curse of dimensionality issue can also be alleviated owing to the inherent dimension reduction ability of the autoencoder. Besides, an attention-based compression mechanism is employed to generate concentrated memory, which records useful information related to a specific task. In this way, the obtained concentrated memory is relatively lightweight to mitigate the time-consuming content-based addressing on large-volume memory. Our model outperforms the state-of-the-arts by 5.44% and 1.81% on average in two metrics over three real-world video datasets, demonstrating its effectiveness and superiority on visual classification with limited labeled exemplars." @default.
• W3089912071 created "2020-10-08" @default.
• W3089912071 creator A5013881064 @default.
• W3089912071 creator A5013911439 @default.
• W3089912071 creator A5034967388 @default.
• W3089912071 creator A5041083459 @default.
• W3089912071 creator A5050171334 @default.
• W3089912071 creator A5063081769 @default.
• W3089912071 date "2020-12-01" @default.
• W3089912071 modified "2023-09-27" @default.
• W3089912071 title "Memory transformation networks for weakly supervised visual classification" @default.
• W3089912071 cites W1533861849 @default.
• W3089912071 cites W1927052826 @default.
• W3089912071 cites W1965555842 @default.
• W3089912071 cites W2044544672 @default.
• W3089912071 cites W2064675550 @default.
• W3089912071 cites W2075606539 @default.
• W3089912071 cites W2095705004 @default.
• W3089912071 cites W2098057602 @default.
• W3089912071 cites W2126579184 @default.
• W3089912071 cites W2150979491 @default.
• W3089912071 cites W2173183968 @default.
• W3089912071 cites W2194775991 @default.
• W3089912071 cites W2250742840 @default.
• W3089912071 cites W24089286 @default.
• W3089912071 cites W2409591106 @default.
• W3089912071 cites W2526041356 @default.
• W3089912071 cites W2561272927 @default.
• W3089912071 cites W2583941031 @default.
• W3089912071 cites W2610163825 @default.
• W3089912071 cites W2741456132 @default.
• W3089912071 cites W2746791238 @default.
• W3089912071 cites W2758851402 @default.
• W3089912071 cites W2761659801 @default.
• W3089912071 cites W2782747298 @default.
• W3089912071 cites W2894873912 @default.
• W3089912071 cites W2909491643 @default.
• W3089912071 cites W2949117887 @default.
• W3089912071 cites W2949335953 @default.
• W3089912071 cites W2949433733 @default.
• W3089912071 cites W2949608135 @default.
• W3089912071 cites W2950527759 @default.
• W3089912071 cites W2950726992 @default.
• W3089912071 cites W2951008357 @default.
• W3089912071 cites W2962934715 @default.
• W3089912071 cites W2963524571 @default.
• W3089912071 cites W2964074409 @default.
• W3089912071 cites W2964308564 @default.
• W3089912071 cites W3015793166 @default.
• W3089912071 cites W2584341106 @default.
• W3089912071 doi "https://doi.org/10.1016/j.knosys.2020.106432" @default.
• W3089912071 hasPublicationYear "2020" @default.
• W3089912071 type Work @default.
• W3089912071 sameAs 3089912071 @default.
• W3089912071 citedByCount "1" @default.
• W3089912071 countsByYear W30899120712022 @default.
• W3089912071 crossrefType "journal-article" @default.
• W3089912071 hasAuthorship W3089912071A5013881064 @default.
• W3089912071 hasAuthorship W3089912071A5013911439 @default.
• W3089912071 hasAuthorship W3089912071A5034967388 @default.
• W3089912071 hasAuthorship W3089912071A5041083459 @default.
• W3089912071 hasAuthorship W3089912071A5050171334 @default.
• W3089912071 hasAuthorship W3089912071A5063081769 @default.
• W3089912071 hasConcept C101738243 @default.
• W3089912071 hasConcept C111030470 @default.
• W3089912071 hasConcept C119857082 @default.
• W3089912071 hasConcept C144024400 @default.
• W3089912071 hasConcept C153083717 @default.
• W3089912071 hasConcept C153180895 @default.
• W3089912071 hasConcept C154945302 @default.
• W3089912071 hasConcept C162324750 @default.
• W3089912071 hasConcept C187736073 @default.
• W3089912071 hasConcept C2779903281 @default.
• W3089912071 hasConcept C2780451532 @default.
• W3089912071 hasConcept C36289849 @default.
• W3089912071 hasConcept C41008148 @default.
• W3089912071 hasConcept C50644808 @default.
• W3089912071 hasConcept C70518039 @default.
• W3089912071 hasConcept C82687282 @default.
• W3089912071 hasConcept C9390403 @default.
• W3089912071 hasConceptScore W3089912071C101738243 @default.
• W3089912071 hasConceptScore W3089912071C111030470 @default.
• W3089912071 hasConceptScore W3089912071C119857082 @default.
• W3089912071 hasConceptScore W3089912071C144024400 @default.
• W3089912071 hasConceptScore W3089912071C153083717 @default.
• W3089912071 hasConceptScore W3089912071C153180895 @default.
• W3089912071 hasConceptScore W3089912071C154945302 @default.
• W3089912071 hasConceptScore W3089912071C162324750 @default.
• W3089912071 hasConceptScore W3089912071C187736073 @default.
• W3089912071 hasConceptScore W3089912071C2779903281 @default.
• W3089912071 hasConceptScore W3089912071C2780451532 @default.
• W3089912071 hasConceptScore W3089912071C36289849 @default.
• W3089912071 hasConceptScore W3089912071C41008148 @default.
• W3089912071 hasConceptScore W3089912071C50644808 @default.
• W3089912071 hasConceptScore W3089912071C70518039 @default.
• W3089912071 hasConceptScore W3089912071C82687282 @default.
• W3089912071 hasConceptScore W3089912071C9390403 @default.
• W3089912071 hasFunder F4320315254 @default.
• W3089912071 hasFunder F4320321001 @default.
• W3089912071 hasFunder F4320335777 @default.

• next