Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962958773> ?p ?o ?g. }
- W2962958773 endingPage "3058" @default.
- W2962958773 startingPage "3047" @default.
- W2962958773 abstract "Video captioning, in essential, is a complex natural process, which is affected by various uncertainties stemming from video content, subjective judgment, and so on. In this paper, we build on the recent progress in using encoder-decoder framework for video captioning and address what we find to be a critical deficiency of the existing methods that most of the decoders propagate deterministic hidden states. Such complex uncertainty cannot be modeled efficiently by the deterministic models. In this paper, we propose a generative approach, referred to as multimodal stochastic recurrent neural networks (MS-RNNs), which models the uncertainty observed in the data using latent stochastic variables. Therefore, MS-RNN can improve the performance of video captioning and generate multiple sentences to describe a video considering different random factors. Specifically, a multimodal long short-term memory (LSTM) is first proposed to interact with both visual and textual features to capture a high-level representation. Then, a backward stochastic LSTM is proposed to support uncertainty propagation by introducing latent variables. Experimental results on the challenging data sets, microsoft video description and microsoft research video-to-text, show that our proposed MS-RNN approach outperforms the state-of-the-art video captioning benchmarks." @default.
- W2962958773 created "2019-07-30" @default.
- W2962958773 creator A5036987388 @default.
- W2962958773 creator A5037486611 @default.
- W2962958773 creator A5052993469 @default.
- W2962958773 creator A5066645546 @default.
- W2962958773 creator A5068918243 @default.
- W2962958773 creator A5080516683 @default.
- W2962958773 date "2019-10-01" @default.
- W2962958773 modified "2023-10-14" @default.
- W2962958773 title "From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning" @default.
- W2962958773 cites W1573040851 @default.
- W2962958773 cites W1586939924 @default.
- W2962958773 cites W1601567445 @default.
- W2962958773 cites W179875071 @default.
- W2962958773 cites W1897761818 @default.
- W2962958773 cites W1931639407 @default.
- W2962958773 cites W1956340063 @default.
- W2962958773 cites W2010632104 @default.
- W2962958773 cites W2035434106 @default.
- W2962958773 cites W2064675550 @default.
- W2962958773 cites W2075966418 @default.
- W2962958773 cites W2097117768 @default.
- W2962958773 cites W2110933980 @default.
- W2962958773 cites W2121772968 @default.
- W2962958773 cites W2125707784 @default.
- W2962958773 cites W2133459682 @default.
- W2962958773 cites W2139501017 @default.
- W2962958773 cites W2152175008 @default.
- W2962958773 cites W2194775991 @default.
- W2962958773 cites W2302086703 @default.
- W2962958773 cites W2331050942 @default.
- W2962958773 cites W2341680599 @default.
- W2962958773 cites W2411707397 @default.
- W2962958773 cites W2425121537 @default.
- W2962958773 cites W2513281263 @default.
- W2962958773 cites W2526868004 @default.
- W2962958773 cites W2527145521 @default.
- W2962958773 cites W2598003564 @default.
- W2962958773 cites W2621571501 @default.
- W2962958773 cites W2739107216 @default.
- W2962958773 cites W2751125921 @default.
- W2962958773 cites W2751445731 @default.
- W2962958773 cites W2752930373 @default.
- W2962958773 cites W2764242203 @default.
- W2962958773 cites W2765860780 @default.
- W2962958773 cites W2780838211 @default.
- W2962958773 cites W2781821509 @default.
- W2962958773 cites W2786585376 @default.
- W2962958773 cites W2963576560 @default.
- W2962958773 cites W2963843052 @default.
- W2962958773 cites W2964241990 @default.
- W2962958773 cites W4254816979 @default.
- W2962958773 doi "https://doi.org/10.1109/tnnls.2018.2851077" @default.
- W2962958773 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30130235" @default.
- W2962958773 hasPublicationYear "2019" @default.
- W2962958773 type Work @default.
- W2962958773 sameAs 2962958773 @default.
- W2962958773 citedByCount "161" @default.
- W2962958773 countsByYear W29629587732012 @default.
- W2962958773 countsByYear W29629587732018 @default.
- W2962958773 countsByYear W29629587732019 @default.
- W2962958773 countsByYear W29629587732020 @default.
- W2962958773 countsByYear W29629587732021 @default.
- W2962958773 countsByYear W29629587732022 @default.
- W2962958773 countsByYear W29629587732023 @default.
- W2962958773 crossrefType "journal-article" @default.
- W2962958773 hasAuthorship W2962958773A5036987388 @default.
- W2962958773 hasAuthorship W2962958773A5037486611 @default.
- W2962958773 hasAuthorship W2962958773A5052993469 @default.
- W2962958773 hasAuthorship W2962958773A5066645546 @default.
- W2962958773 hasAuthorship W2962958773A5068918243 @default.
- W2962958773 hasAuthorship W2962958773A5080516683 @default.
- W2962958773 hasBestOaLocation W29629587732 @default.
- W2962958773 hasConcept C111919701 @default.
- W2962958773 hasConcept C115961682 @default.
- W2962958773 hasConcept C118505674 @default.
- W2962958773 hasConcept C119857082 @default.
- W2962958773 hasConcept C147168706 @default.
- W2962958773 hasConcept C154945302 @default.
- W2962958773 hasConcept C157657479 @default.
- W2962958773 hasConcept C167966045 @default.
- W2962958773 hasConcept C17744445 @default.
- W2962958773 hasConcept C199539241 @default.
- W2962958773 hasConcept C2776359362 @default.
- W2962958773 hasConcept C39890363 @default.
- W2962958773 hasConcept C41008148 @default.
- W2962958773 hasConcept C50644808 @default.
- W2962958773 hasConcept C94625758 @default.
- W2962958773 hasConceptScore W2962958773C111919701 @default.
- W2962958773 hasConceptScore W2962958773C115961682 @default.
- W2962958773 hasConceptScore W2962958773C118505674 @default.
- W2962958773 hasConceptScore W2962958773C119857082 @default.
- W2962958773 hasConceptScore W2962958773C147168706 @default.
- W2962958773 hasConceptScore W2962958773C154945302 @default.
- W2962958773 hasConceptScore W2962958773C157657479 @default.
- W2962958773 hasConceptScore W2962958773C167966045 @default.
- W2962958773 hasConceptScore W2962958773C17744445 @default.