FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2789378830> ?p ?o ?g. }

• W2789378830 abstract "Automatically describing videos with natural language is a fundamental challenge for computer vision and natural language processing. Recently, progress in this problem has been achieved through two steps: 1) employing 2-D and/or 3-D Convolutional Neural Networks (CNNs) (e.g. VGG, ResNet or C3D) to extract spatial and/or temporal features to encode video contents; and 2) applying Recurrent Neural Networks (RNNs) to generate sentences to describe events in videos. Temporal attention-based model has gained much progress by considering the importance of each video frame. However, for a long video, especially for a video which consists of a set of sub-events, we should discover and leverage the importance of each sub-shot instead of each frame. In this paper, we propose a novel approach, namely temporal and spatial LSTM (TS-LSTM), which systematically exploits spatial and temporal dynamics within video sequences. In TS-LSTM, a temporal pooling LSTM (TP-LSTM) is designed to incorporate both spatial and temporal information to extract long-term temporal dynamics within video sub-shots; and a stacked LSTM is introduced to generate a list of words to describe the video. Experimental results obtained in two public video captioning benchmarks indicate that our TS-LSTM outperforms the state-of-the-art methods." @default.
• W2789378830 created "2018-03-29" @default.
• W2789378830 creator A5031091494 @default.
• W2789378830 creator A5066645546 @default.
• W2789378830 creator A5080516683 @default.
• W2789378830 date "2022-02-22" @default.
• W2789378830 modified "2023-09-24" @default.
• W2789378830 title "Exploiting long-term temporal dynamics for video captioning" @default.
• W2789378830 cites W1523493493 @default.
• W2789378830 cites W1573040851 @default.
• W2789378830 cites W1586939924 @default.
• W2789378830 cites W1601567445 @default.
• W2789378830 cites W1606347560 @default.
• W2789378830 cites W1686810756 @default.
• W2789378830 cites W179875071 @default.
• W2789378830 cites W1867429401 @default.
• W2789378830 cites W1897761818 @default.
• W2789378830 cites W1924770834 @default.
• W2789378830 cites W1947481528 @default.
• W2789378830 cites W1956340063 @default.
• W2789378830 cites W2002370809 @default.
• W2789378830 cites W2035434106 @default.
• W2789378830 cites W2064675550 @default.
• W2789378830 cites W2069222105 @default.
• W2789378830 cites W2073301055 @default.
• W2789378830 cites W2097117768 @default.
• W2789378830 cites W2101105183 @default.
• W2789378830 cites W2107878631 @default.
• W2789378830 cites W2110485445 @default.
• W2789378830 cites W2110933980 @default.
• W2789378830 cites W2112796928 @default.
• W2789378830 cites W2117539524 @default.
• W2789378830 cites W2122476475 @default.
• W2789378830 cites W2125707784 @default.
• W2789378830 cites W2133459682 @default.
• W2789378830 cites W2139501017 @default.
• W2789378830 cites W2141130481 @default.
• W2789378830 cites W2159373756 @default.
• W2789378830 cites W2164290393 @default.
• W2789378830 cites W2171928131 @default.
• W2789378830 cites W2194775991 @default.
• W2789378830 cites W2342662179 @default.
• W2789378830 cites W2425121537 @default.
• W2789378830 cites W2507009361 @default.
• W2789378830 cites W2508429489 @default.
• W2789378830 cites W2513281263 @default.
• W2789378830 cites W2527145521 @default.
• W2789378830 cites W2527512904 @default.
• W2789378830 cites W2552161745 @default.
• W2789378830 cites W2556388456 @default.
• W2789378830 cites W2598003564 @default.
• W2789378830 cites W2605373614 @default.
• W2789378830 cites W2613718673 @default.
• W2789378830 cites W2621571501 @default.
• W2789378830 cites W2728700534 @default.
• W2789378830 cites W2739107216 @default.
• W2789378830 cites W2949828251 @default.
• W2789378830 cites W2950553082 @default.
• W2789378830 cites W2951527505 @default.
• W2789378830 cites W2952186347 @default.
• W2789378830 cites W2962762462 @default.
• W2789378830 cites W2963576560 @default.
• W2789378830 cites W2963843052 @default.
• W2789378830 cites W2964241990 @default.
• W2789378830 cites W6908809 @default.
• W2789378830 doi "https://doi.org/10.48550/arxiv.2202.10828" @default.
• W2789378830 hasPublicationYear "2022" @default.
• W2789378830 type Work @default.
• W2789378830 sameAs 2789378830 @default.
• W2789378830 citedByCount "2" @default.
• W2789378830 countsByYear W27893788302021 @default.
• W2789378830 countsByYear W27893788302022 @default.
• W2789378830 crossrefType "posted-content" @default.
• W2789378830 hasAuthorship W2789378830A5031091494 @default.
• W2789378830 hasAuthorship W2789378830A5066645546 @default.
• W2789378830 hasAuthorship W2789378830A5080516683 @default.
• W2789378830 hasBestOaLocation W27893788301 @default.
• W2789378830 hasConcept C115961682 @default.
• W2789378830 hasConcept C126042441 @default.
• W2789378830 hasConcept C147168706 @default.
• W2789378830 hasConcept C153083717 @default.
• W2789378830 hasConcept C153180895 @default.
• W2789378830 hasConcept C154945302 @default.
• W2789378830 hasConcept C157657479 @default.
• W2789378830 hasConcept C165696696 @default.
• W2789378830 hasConcept C28490314 @default.
• W2789378830 hasConcept C38652104 @default.
• W2789378830 hasConcept C41008148 @default.
• W2789378830 hasConcept C50644808 @default.
• W2789378830 hasConcept C70437156 @default.
• W2789378830 hasConcept C76155785 @default.
• W2789378830 hasConcept C81363708 @default.
• W2789378830 hasConceptScore W2789378830C115961682 @default.
• W2789378830 hasConceptScore W2789378830C126042441 @default.
• W2789378830 hasConceptScore W2789378830C147168706 @default.
• W2789378830 hasConceptScore W2789378830C153083717 @default.
• W2789378830 hasConceptScore W2789378830C153180895 @default.
• W2789378830 hasConceptScore W2789378830C154945302 @default.
• W2789378830 hasConceptScore W2789378830C157657479 @default.
• W2789378830 hasConceptScore W2789378830C165696696 @default.

• next