Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042779440> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3042779440 endingPage "1162" @default.
- W3042779440 startingPage "1162" @default.
- W3042779440 abstract "Recent video captioning models aim at describing all events in a long video. However, their event descriptions do not fully exploit the contextual information included in a video because they lack the ability to remember information changes over time. To address this problem, we propose a novel context-aware video captioning model that generates natural language descriptions based on the improved video context understanding. We introduce an external memory, differential neural computer (DNC), to improve video context understanding. DNC naturally learns to use its internal memory for context understanding and also provides contents of its memory as an output for additional connection. By sequentially connecting DNC-based caption models (DNC augmented LSTM) through this memory information, our consecutively connected DNC architecture can understand the context in a video without explicitly searching for event-wise correlation. Our consecutive DNC is sequentially trained with its language model (LSTM) for each video clip to generate context-aware captions with superior quality. In experiments, we demonstrate that our model provides more natural and coherent captions which reflect previous contextual information. Our model also shows superior quantitative performance on video captioning in terms of BLEU (BLEU@4 4.37), METEOR (9.57), and CIDEr-D (28.08)." @default.
- W3042779440 created "2020-07-23" @default.
- W3042779440 creator A5016475473 @default.
- W3042779440 creator A5041622394 @default.
- W3042779440 creator A5057675003 @default.
- W3042779440 date "2020-07-17" @default.
- W3042779440 modified "2023-10-03" @default.
- W3042779440 title "Context Aware Video Caption Generation with Consecutive Differentiable Neural Computer" @default.
- W3042779440 cites W1983364832 @default.
- W3042779440 cites W2064675550 @default.
- W3042779440 cites W2530887700 @default.
- W3042779440 doi "https://doi.org/10.3390/electronics9071162" @default.
- W3042779440 hasPublicationYear "2020" @default.
- W3042779440 type Work @default.
- W3042779440 sameAs 3042779440 @default.
- W3042779440 citedByCount "6" @default.
- W3042779440 countsByYear W30427794402021 @default.
- W3042779440 countsByYear W30427794402022 @default.
- W3042779440 countsByYear W30427794402023 @default.
- W3042779440 crossrefType "journal-article" @default.
- W3042779440 hasAuthorship W3042779440A5016475473 @default.
- W3042779440 hasAuthorship W3042779440A5041622394 @default.
- W3042779440 hasAuthorship W3042779440A5057675003 @default.
- W3042779440 hasBestOaLocation W30427794401 @default.
- W3042779440 hasConcept C115961682 @default.
- W3042779440 hasConcept C121332964 @default.
- W3042779440 hasConcept C137293760 @default.
- W3042779440 hasConcept C151730666 @default.
- W3042779440 hasConcept C154945302 @default.
- W3042779440 hasConcept C157657479 @default.
- W3042779440 hasConcept C165696696 @default.
- W3042779440 hasConcept C195324797 @default.
- W3042779440 hasConcept C204321447 @default.
- W3042779440 hasConcept C2779343474 @default.
- W3042779440 hasConcept C2779662365 @default.
- W3042779440 hasConcept C28490314 @default.
- W3042779440 hasConcept C38652104 @default.
- W3042779440 hasConcept C41008148 @default.
- W3042779440 hasConcept C62520636 @default.
- W3042779440 hasConcept C86803240 @default.
- W3042779440 hasConceptScore W3042779440C115961682 @default.
- W3042779440 hasConceptScore W3042779440C121332964 @default.
- W3042779440 hasConceptScore W3042779440C137293760 @default.
- W3042779440 hasConceptScore W3042779440C151730666 @default.
- W3042779440 hasConceptScore W3042779440C154945302 @default.
- W3042779440 hasConceptScore W3042779440C157657479 @default.
- W3042779440 hasConceptScore W3042779440C165696696 @default.
- W3042779440 hasConceptScore W3042779440C195324797 @default.
- W3042779440 hasConceptScore W3042779440C204321447 @default.
- W3042779440 hasConceptScore W3042779440C2779343474 @default.
- W3042779440 hasConceptScore W3042779440C2779662365 @default.
- W3042779440 hasConceptScore W3042779440C28490314 @default.
- W3042779440 hasConceptScore W3042779440C38652104 @default.
- W3042779440 hasConceptScore W3042779440C41008148 @default.
- W3042779440 hasConceptScore W3042779440C62520636 @default.
- W3042779440 hasConceptScore W3042779440C86803240 @default.
- W3042779440 hasIssue "7" @default.
- W3042779440 hasLocation W30427794401 @default.
- W3042779440 hasLocation W30427794402 @default.
- W3042779440 hasOpenAccess W3042779440 @default.
- W3042779440 hasPrimaryLocation W30427794401 @default.
- W3042779440 hasRelatedWork W1483367581 @default.
- W3042779440 hasRelatedWork W2547835662 @default.
- W3042779440 hasRelatedWork W2783312365 @default.
- W3042779440 hasRelatedWork W2805200595 @default.
- W3042779440 hasRelatedWork W2918969764 @default.
- W3042779440 hasRelatedWork W2972879420 @default.
- W3042779440 hasRelatedWork W3107474891 @default.
- W3042779440 hasRelatedWork W4288112916 @default.
- W3042779440 hasRelatedWork W4312090516 @default.
- W3042779440 hasRelatedWork W4321080401 @default.
- W3042779440 hasVolume "9" @default.
- W3042779440 isParatext "false" @default.
- W3042779440 isRetracted "false" @default.
- W3042779440 magId "3042779440" @default.
- W3042779440 workType "article" @default.