Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951159095> ?p ?o ?g. }
- W2951159095 abstract "Automatically generating natural language descriptions of videos plays a fundamental challenge for computer vision community. Most recent progress in this problem has been achieved through employing 2-D and/or 3-D Convolutional Neural Networks (CNN) to encode video content and Recurrent Neural Networks (RNN) to decode a sentence. In this paper, we present Long Short-Term Memory with Transferred Semantic Attributes (LSTM-TSA)---a novel deep architecture that incorporates the transferred semantic attributes learnt from images and videos into the CNN plus RNN framework, by training them in an end-to-end manner. The design of LSTM-TSA is highly inspired by the facts that 1) semantic attributes play a significant contribution to captioning, and 2) images and videos carry complementary semantics and thus can reinforce each other for captioning. To boost video captioning, we propose a novel transfer unit to model the mutually correlated attributes learnt from images and videos. Extensive experiments are conducted on three public datasets, i.e., MSVD, M-VAD and MPII-MD. Our proposed LSTM-TSA achieves to-date the best published performance in sentence generation on MSVD: 52.8% and 74.0% in terms of BLEU@4 and CIDEr-D. Superior results when compared to state-of-the-art methods are also reported on M-VAD and MPII-MD." @default.
- W2951159095 created "2019-06-27" @default.
- W2951159095 creator A5017597537 @default.
- W2951159095 creator A5078141810 @default.
- W2951159095 creator A5085403640 @default.
- W2951159095 creator A5088760097 @default.
- W2951159095 date "2016-11-23" @default.
- W2951159095 modified "2023-10-16" @default.
- W2951159095 title "Video Captioning with Transferred Semantic Attributes" @default.
- W2951159095 cites W1522734439 @default.
- W2951159095 cites W1572567476 @default.
- W2951159095 cites W1573040851 @default.
- W2951159095 cites W1601567445 @default.
- W2951159095 cites W1889081078 @default.
- W2951159095 cites W1893116441 @default.
- W2951159095 cites W1931639407 @default.
- W2951159095 cites W1947481528 @default.
- W2951159095 cites W1956340063 @default.
- W2951159095 cites W2064675550 @default.
- W2951159095 cites W2097117768 @default.
- W2951159095 cites W2101105183 @default.
- W2951159095 cites W2110933980 @default.
- W2951159095 cites W2117539524 @default.
- W2951159095 cites W2123301721 @default.
- W2951159095 cites W2142900973 @default.
- W2951159095 cites W2159243025 @default.
- W2951159095 cites W2164290393 @default.
- W2951159095 cites W2166010828 @default.
- W2951159095 cites W2273041409 @default.
- W2951159095 cites W2294130536 @default.
- W2951159095 cites W2308045930 @default.
- W2951159095 cites W2949380904 @default.
- W2951159095 cites W2949888546 @default.
- W2951159095 cites W2950019618 @default.
- W2951159095 cites W2950307714 @default.
- W2951159095 cites W2952238956 @default.
- W2951159095 cites W2953022248 @default.
- W2951159095 cites W2962835968 @default.
- W2951159095 cites W2963149042 @default.
- W2951159095 cites W2963576560 @default.
- W2951159095 cites W2964018924 @default.
- W2951159095 cites W2964241990 @default.
- W2951159095 cites W2964308564 @default.
- W2951159095 cites W877909479 @default.
- W2951159095 doi "https://doi.org/10.48550/arxiv.1611.07675" @default.
- W2951159095 hasPublicationYear "2016" @default.
- W2951159095 type Work @default.
- W2951159095 sameAs 2951159095 @default.
- W2951159095 citedByCount "11" @default.
- W2951159095 countsByYear W29511590952017 @default.
- W2951159095 countsByYear W29511590952018 @default.
- W2951159095 crossrefType "posted-content" @default.
- W2951159095 hasAuthorship W2951159095A5017597537 @default.
- W2951159095 hasAuthorship W2951159095A5078141810 @default.
- W2951159095 hasAuthorship W2951159095A5085403640 @default.
- W2951159095 hasAuthorship W2951159095A5088760097 @default.
- W2951159095 hasBestOaLocation W29511590951 @default.
- W2951159095 hasConcept C104317684 @default.
- W2951159095 hasConcept C115961682 @default.
- W2951159095 hasConcept C147168706 @default.
- W2951159095 hasConcept C154945302 @default.
- W2951159095 hasConcept C157657479 @default.
- W2951159095 hasConcept C184337299 @default.
- W2951159095 hasConcept C185592680 @default.
- W2951159095 hasConcept C195324797 @default.
- W2951159095 hasConcept C199360897 @default.
- W2951159095 hasConcept C204321447 @default.
- W2951159095 hasConcept C2776187449 @default.
- W2951159095 hasConcept C2777530160 @default.
- W2951159095 hasConcept C28490314 @default.
- W2951159095 hasConcept C41008148 @default.
- W2951159095 hasConcept C50644808 @default.
- W2951159095 hasConcept C55493867 @default.
- W2951159095 hasConcept C66746571 @default.
- W2951159095 hasConcept C81363708 @default.
- W2951159095 hasConceptScore W2951159095C104317684 @default.
- W2951159095 hasConceptScore W2951159095C115961682 @default.
- W2951159095 hasConceptScore W2951159095C147168706 @default.
- W2951159095 hasConceptScore W2951159095C154945302 @default.
- W2951159095 hasConceptScore W2951159095C157657479 @default.
- W2951159095 hasConceptScore W2951159095C184337299 @default.
- W2951159095 hasConceptScore W2951159095C185592680 @default.
- W2951159095 hasConceptScore W2951159095C195324797 @default.
- W2951159095 hasConceptScore W2951159095C199360897 @default.
- W2951159095 hasConceptScore W2951159095C204321447 @default.
- W2951159095 hasConceptScore W2951159095C2776187449 @default.
- W2951159095 hasConceptScore W2951159095C2777530160 @default.
- W2951159095 hasConceptScore W2951159095C28490314 @default.
- W2951159095 hasConceptScore W2951159095C41008148 @default.
- W2951159095 hasConceptScore W2951159095C50644808 @default.
- W2951159095 hasConceptScore W2951159095C55493867 @default.
- W2951159095 hasConceptScore W2951159095C66746571 @default.
- W2951159095 hasConceptScore W2951159095C81363708 @default.
- W2951159095 hasLocation W29511590951 @default.
- W2951159095 hasOpenAccess W2951159095 @default.
- W2951159095 hasPrimaryLocation W29511590951 @default.
- W2951159095 hasRelatedWork W2240668419 @default.
- W2951159095 hasRelatedWork W2556388456 @default.
- W2951159095 hasRelatedWork W2573002734 @default.
- W2951159095 hasRelatedWork W2803206166 @default.