Matches in SemOpenAlex for { <https://semopenalex.org/work/W2981036708> ?p ?o ?g. }
- W2981036708 abstract "We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156,416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by adding audio modality for both tasks of zeroshot classification and retrieval, when using multimodal extensions of embedding learning methods. We also propose a novel method to predict the `dominant' modality using a jointly learned modality attention network. We learn the attention in a semi-supervised setting and thus do not require any additional explicit labelling for the modalities. We provide qualitative validation of the modality specific attention, which also successfully generalizes to unseen test classes." @default.
- W2981036708 created "2019-10-25" @default.
- W2981036708 creator A5021354054 @default.
- W2981036708 creator A5034793449 @default.
- W2981036708 creator A5041837701 @default.
- W2981036708 creator A5051876605 @default.
- W2981036708 date "2019-10-19" @default.
- W2981036708 modified "2023-10-08" @default.
- W2981036708 title "Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos." @default.
- W2981036708 cites W1975077471 @default.
- W2981036708 cites W1982795953 @default.
- W2981036708 cites W2099471712 @default.
- W2981036708 cites W2105582566 @default.
- W2981036708 cites W2124033848 @default.
- W2981036708 cites W2128532956 @default.
- W2981036708 cites W2171061940 @default.
- W2981036708 cites W2334493732 @default.
- W2981036708 cites W2400717490 @default.
- W2981036708 cites W2511428026 @default.
- W2981036708 cites W2520613337 @default.
- W2981036708 cites W2593116425 @default.
- W2981036708 cites W2611632661 @default.
- W2981036708 cites W2619697695 @default.
- W2981036708 cites W2740825418 @default.
- W2981036708 cites W2789366140 @default.
- W2981036708 cites W2921950349 @default.
- W2981036708 cites W2949999304 @default.
- W2981036708 cites W2962756039 @default.
- W2981036708 cites W2962772361 @default.
- W2981036708 cites W2962865004 @default.
- W2981036708 cites W2962910554 @default.
- W2981036708 cites W2962960500 @default.
- W2981036708 cites W2963115079 @default.
- W2981036708 cites W2963218389 @default.
- W2981036708 cites W2963499153 @default.
- W2981036708 cites W2963524571 @default.
- W2981036708 cites W2963545832 @default.
- W2981036708 cites W2963680395 @default.
- W2981036708 cites W2963689837 @default.
- W2981036708 cites W2963854535 @default.
- W2981036708 cites W2963887950 @default.
- W2981036708 cites W2963936013 @default.
- W2981036708 cites W2963960318 @default.
- W2981036708 cites W2997685131 @default.
- W2981036708 cites W3123318516 @default.
- W2981036708 cites W652269744 @default.
- W2981036708 cites W93016980 @default.
- W2981036708 hasPublicationYear "2019" @default.
- W2981036708 type Work @default.
- W2981036708 sameAs 2981036708 @default.
- W2981036708 citedByCount "0" @default.
- W2981036708 crossrefType "posted-content" @default.
- W2981036708 hasAuthorship W2981036708A5021354054 @default.
- W2981036708 hasAuthorship W2981036708A5034793449 @default.
- W2981036708 hasAuthorship W2981036708A5041837701 @default.
- W2981036708 hasAuthorship W2981036708A5051876605 @default.
- W2981036708 hasConcept C119857082 @default.
- W2981036708 hasConcept C127413603 @default.
- W2981036708 hasConcept C144024400 @default.
- W2981036708 hasConcept C153180895 @default.
- W2981036708 hasConcept C154945302 @default.
- W2981036708 hasConcept C162324750 @default.
- W2981036708 hasConcept C170154142 @default.
- W2981036708 hasConcept C18555067 @default.
- W2981036708 hasConcept C187736073 @default.
- W2981036708 hasConcept C199360897 @default.
- W2981036708 hasConcept C204321447 @default.
- W2981036708 hasConcept C2779903281 @default.
- W2981036708 hasConcept C2780226545 @default.
- W2981036708 hasConcept C2780451532 @default.
- W2981036708 hasConcept C2780660688 @default.
- W2981036708 hasConcept C2780801425 @default.
- W2981036708 hasConcept C28490314 @default.
- W2981036708 hasConcept C3017588708 @default.
- W2981036708 hasConcept C36289849 @default.
- W2981036708 hasConcept C41008148 @default.
- W2981036708 hasConcept C41608201 @default.
- W2981036708 hasConcept C49774154 @default.
- W2981036708 hasConceptScore W2981036708C119857082 @default.
- W2981036708 hasConceptScore W2981036708C127413603 @default.
- W2981036708 hasConceptScore W2981036708C144024400 @default.
- W2981036708 hasConceptScore W2981036708C153180895 @default.
- W2981036708 hasConceptScore W2981036708C154945302 @default.
- W2981036708 hasConceptScore W2981036708C162324750 @default.
- W2981036708 hasConceptScore W2981036708C170154142 @default.
- W2981036708 hasConceptScore W2981036708C18555067 @default.
- W2981036708 hasConceptScore W2981036708C187736073 @default.
- W2981036708 hasConceptScore W2981036708C199360897 @default.
- W2981036708 hasConceptScore W2981036708C204321447 @default.
- W2981036708 hasConceptScore W2981036708C2779903281 @default.
- W2981036708 hasConceptScore W2981036708C2780226545 @default.
- W2981036708 hasConceptScore W2981036708C2780451532 @default.
- W2981036708 hasConceptScore W2981036708C2780660688 @default.
- W2981036708 hasConceptScore W2981036708C2780801425 @default.
- W2981036708 hasConceptScore W2981036708C28490314 @default.
- W2981036708 hasConceptScore W2981036708C3017588708 @default.
- W2981036708 hasConceptScore W2981036708C36289849 @default.
- W2981036708 hasConceptScore W2981036708C41008148 @default.
- W2981036708 hasConceptScore W2981036708C41608201 @default.
- W2981036708 hasConceptScore W2981036708C49774154 @default.