Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128093669> ?p ?o ?g. }
- W3128093669 abstract "Dense video captioning aims to localize and describe important events in untrimmed videos. Existing methods mainly tackle this task by exploiting only visual features, while completely neglecting the audio track. Only a few prior works have utilized both modalities, yet they show poor results or demonstrate the importance on a dataset with a specific domain. In this paper, we introduce Bi-modal Transformer which generalizes the Transformer architecture for a bi-modal input. We show the effectiveness of the proposed model with audio and visual modalities on the dense video captioning task, yet the module is capable of digesting any two modalities in a sequence-to-sequence task. We also show that the pre-trained bi-modal encoder as a part of the bi-modal transformer can be used as a feature extractor for a simple proposal generation module. The performance is demonstrated on a challenging ActivityNet Captions dataset where our model achieves outstanding performance. The code is available: this http URL" @default.
- W3128093669 created "2021-02-15" @default.
- W3128093669 creator A5008909874 @default.
- W3128093669 creator A5088180438 @default.
- W3128093669 date "2020-01-01" @default.
- W3128093669 modified "2023-09-26" @default.
- W3128093669 title "A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer." @default.
- W3128093669 cites W1522301498 @default.
- W3128093669 cites W1601567445 @default.
- W3128093669 cites W2110933980 @default.
- W3128093669 cites W2194775991 @default.
- W3128093669 cites W2554906389 @default.
- W3128093669 cites W2556388456 @default.
- W3128093669 cites W2558834163 @default.
- W3128093669 cites W2570343428 @default.
- W3128093669 cites W2584992898 @default.
- W3128093669 cites W2593116425 @default.
- W3128093669 cites W2607644813 @default.
- W3128093669 cites W2766375149 @default.
- W3128093669 cites W2784025607 @default.
- W3128093669 cites W2796239628 @default.
- W3128093669 cites W2797263747 @default.
- W3128093669 cites W2891955747 @default.
- W3128093669 cites W2914699769 @default.
- W3128093669 cites W2948859046 @default.
- W3128093669 cites W2950019618 @default.
- W3128093669 cites W2950307714 @default.
- W3128093669 cites W2963084599 @default.
- W3128093669 cites W2963504927 @default.
- W3128093669 cites W2963576560 @default.
- W3128093669 cites W2963717374 @default.
- W3128093669 cites W2964241990 @default.
- W3128093669 cites W2970971581 @default.
- W3128093669 cites W2973802306 @default.
- W3128093669 hasPublicationYear "2020" @default.
- W3128093669 type Work @default.
- W3128093669 sameAs 3128093669 @default.
- W3128093669 citedByCount "5" @default.
- W3128093669 countsByYear W31280936692020 @default.
- W3128093669 countsByYear W31280936692021 @default.
- W3128093669 crossrefType "proceedings-article" @default.
- W3128093669 hasAuthorship W3128093669A5008909874 @default.
- W3128093669 hasAuthorship W3128093669A5088180438 @default.
- W3128093669 hasConcept C111919701 @default.
- W3128093669 hasConcept C115961682 @default.
- W3128093669 hasConcept C118505674 @default.
- W3128093669 hasConcept C119599485 @default.
- W3128093669 hasConcept C127413603 @default.
- W3128093669 hasConcept C144024400 @default.
- W3128093669 hasConcept C154945302 @default.
- W3128093669 hasConcept C157657479 @default.
- W3128093669 hasConcept C165801399 @default.
- W3128093669 hasConcept C185592680 @default.
- W3128093669 hasConcept C188027245 @default.
- W3128093669 hasConcept C2779903281 @default.
- W3128093669 hasConcept C28490314 @default.
- W3128093669 hasConcept C36289849 @default.
- W3128093669 hasConcept C41008148 @default.
- W3128093669 hasConcept C66322947 @default.
- W3128093669 hasConcept C71139939 @default.
- W3128093669 hasConceptScore W3128093669C111919701 @default.
- W3128093669 hasConceptScore W3128093669C115961682 @default.
- W3128093669 hasConceptScore W3128093669C118505674 @default.
- W3128093669 hasConceptScore W3128093669C119599485 @default.
- W3128093669 hasConceptScore W3128093669C127413603 @default.
- W3128093669 hasConceptScore W3128093669C144024400 @default.
- W3128093669 hasConceptScore W3128093669C154945302 @default.
- W3128093669 hasConceptScore W3128093669C157657479 @default.
- W3128093669 hasConceptScore W3128093669C165801399 @default.
- W3128093669 hasConceptScore W3128093669C185592680 @default.
- W3128093669 hasConceptScore W3128093669C188027245 @default.
- W3128093669 hasConceptScore W3128093669C2779903281 @default.
- W3128093669 hasConceptScore W3128093669C28490314 @default.
- W3128093669 hasConceptScore W3128093669C36289849 @default.
- W3128093669 hasConceptScore W3128093669C41008148 @default.
- W3128093669 hasConceptScore W3128093669C66322947 @default.
- W3128093669 hasConceptScore W3128093669C71139939 @default.
- W3128093669 hasLocation W31280936691 @default.
- W3128093669 hasOpenAccess W3128093669 @default.
- W3128093669 hasPrimaryLocation W31280936691 @default.
- W3128093669 hasRelatedWork W2527349934 @default.
- W3128093669 hasRelatedWork W2785892019 @default.
- W3128093669 hasRelatedWork W2936900244 @default.
- W3128093669 hasRelatedWork W2945961616 @default.
- W3128093669 hasRelatedWork W2950579554 @default.
- W3128093669 hasRelatedWork W2950864153 @default.
- W3128093669 hasRelatedWork W2985144848 @default.
- W3128093669 hasRelatedWork W3012386959 @default.
- W3128093669 hasRelatedWork W3025796084 @default.
- W3128093669 hasRelatedWork W3095909497 @default.
- W3128093669 hasRelatedWork W3125480685 @default.
- W3128093669 hasRelatedWork W3162251280 @default.
- W3128093669 hasRelatedWork W3185518018 @default.
- W3128093669 hasRelatedWork W3185739472 @default.
- W3128093669 hasRelatedWork W3187583865 @default.
- W3128093669 hasRelatedWork W3194973321 @default.
- W3128093669 hasRelatedWork W3197980617 @default.
- W3128093669 hasRelatedWork W3202567960 @default.
- W3128093669 hasRelatedWork W3205716523 @default.
- W3128093669 hasRelatedWork W3206857696 @default.