Matches in SemOpenAlex for { <https://semopenalex.org/work/W3163971663> ?p ?o ?g. }
- W3163971663 endingPage "42" @default.
- W3163971663 startingPage "31" @default.
- W3163971663 abstract "Recent neural models for video captioning usually employ an attention-based encoder-decoder framework. However, current approaches mainly attend to the motion features and object features of the video when generating the caption, but ignore the potential but useful historical information. Besides, exposure bias and vanishing gradients problems always exist in current caption generation models. In this paper, we propose a novel video captioning framework, named Stacked Multimodal Attention Network (SMAN). It adopts additional visual and textual historical information during caption generation as context features, employs a stacked architecture to process different features gradually, and utilizes the Reinforcement Learning method and coarse-to-fine training strategy to further improve the generated results. Both quantitative and qualitative experiments on the benchmark datasets of <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>MSVD</i> and <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>MSR-VTT</i> show the effectiveness and feasibility of our framework. The codes are available on <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/zhengyi123456/SMAN</uri> ." @default.
- W3163971663 created "2021-06-07" @default.
- W3163971663 creator A5035701638 @default.
- W3163971663 creator A5040613149 @default.
- W3163971663 creator A5067518097 @default.
- W3163971663 creator A5070073283 @default.
- W3163971663 creator A5075964389 @default.
- W3163971663 date "2022-01-01" @default.
- W3163971663 modified "2023-10-17" @default.
- W3163971663 title "Stacked Multimodal Attention Network for Context-Aware Video Captioning" @default.
- W3163971663 cites W1586939924 @default.
- W3163971663 cites W1601567445 @default.
- W3163971663 cites W1895577753 @default.
- W3163971663 cites W1956340063 @default.
- W3163971663 cites W2064675550 @default.
- W3163971663 cites W2101105183 @default.
- W3163971663 cites W2117539524 @default.
- W3163971663 cites W2119717200 @default.
- W3163971663 cites W2425121537 @default.
- W3163971663 cites W2506483933 @default.
- W3163971663 cites W2507365558 @default.
- W3163971663 cites W2523993696 @default.
- W3163971663 cites W2527349934 @default.
- W3163971663 cites W2549139847 @default.
- W3163971663 cites W2552161745 @default.
- W3163971663 cites W2556388456 @default.
- W3163971663 cites W2621571501 @default.
- W3163971663 cites W2739107216 @default.
- W3163971663 cites W2745461083 @default.
- W3163971663 cites W2765658575 @default.
- W3163971663 cites W2807834696 @default.
- W3163971663 cites W2808071176 @default.
- W3163971663 cites W2887585070 @default.
- W3163971663 cites W2895845501 @default.
- W3163971663 cites W2901988662 @default.
- W3163971663 cites W2904698318 @default.
- W3163971663 cites W2905145027 @default.
- W3163971663 cites W2962681491 @default.
- W3163971663 cites W2962907269 @default.
- W3163971663 cites W2962934715 @default.
- W3163971663 cites W2962990649 @default.
- W3163971663 cites W2963084599 @default.
- W3163971663 cites W2963552819 @default.
- W3163971663 cites W2963971014 @default.
- W3163971663 cites W2964241990 @default.
- W3163971663 cites W2964896648 @default.
- W3163971663 cites W2965359408 @default.
- W3163971663 cites W2970768710 @default.
- W3163971663 cites W2981411942 @default.
- W3163971663 cites W2984862483 @default.
- W3163971663 cites W2986670728 @default.
- W3163971663 cites W3034221024 @default.
- W3163971663 cites W3034593503 @default.
- W3163971663 cites W3035365026 @default.
- W3163971663 cites W3035392611 @default.
- W3163971663 doi "https://doi.org/10.1109/tcsvt.2021.3058626" @default.
- W3163971663 hasPublicationYear "2022" @default.
- W3163971663 type Work @default.
- W3163971663 sameAs 3163971663 @default.
- W3163971663 citedByCount "13" @default.
- W3163971663 countsByYear W31639716632022 @default.
- W3163971663 countsByYear W31639716632023 @default.
- W3163971663 crossrefType "journal-article" @default.
- W3163971663 hasAuthorship W3163971663A5035701638 @default.
- W3163971663 hasAuthorship W3163971663A5040613149 @default.
- W3163971663 hasAuthorship W3163971663A5067518097 @default.
- W3163971663 hasAuthorship W3163971663A5070073283 @default.
- W3163971663 hasAuthorship W3163971663A5075964389 @default.
- W3163971663 hasConcept C111919701 @default.
- W3163971663 hasConcept C115961682 @default.
- W3163971663 hasConcept C118505674 @default.
- W3163971663 hasConcept C13280743 @default.
- W3163971663 hasConcept C151730666 @default.
- W3163971663 hasConcept C154945302 @default.
- W3163971663 hasConcept C157657479 @default.
- W3163971663 hasConcept C185798385 @default.
- W3163971663 hasConcept C199360897 @default.
- W3163971663 hasConcept C204321447 @default.
- W3163971663 hasConcept C205649164 @default.
- W3163971663 hasConcept C23123220 @default.
- W3163971663 hasConcept C2779343474 @default.
- W3163971663 hasConcept C36464697 @default.
- W3163971663 hasConcept C41008148 @default.
- W3163971663 hasConcept C50644808 @default.
- W3163971663 hasConcept C86803240 @default.
- W3163971663 hasConcept C98045186 @default.
- W3163971663 hasConceptScore W3163971663C111919701 @default.
- W3163971663 hasConceptScore W3163971663C115961682 @default.
- W3163971663 hasConceptScore W3163971663C118505674 @default.
- W3163971663 hasConceptScore W3163971663C13280743 @default.
- W3163971663 hasConceptScore W3163971663C151730666 @default.
- W3163971663 hasConceptScore W3163971663C154945302 @default.
- W3163971663 hasConceptScore W3163971663C157657479 @default.
- W3163971663 hasConceptScore W3163971663C185798385 @default.
- W3163971663 hasConceptScore W3163971663C199360897 @default.
- W3163971663 hasConceptScore W3163971663C204321447 @default.
- W3163971663 hasConceptScore W3163971663C205649164 @default.
- W3163971663 hasConceptScore W3163971663C23123220 @default.