FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209983272> ?p ?o ?g. }

• W3209983272 endingPage "5188" @default.
• W3209983272 startingPage "5181" @default.
• W3209983272 abstract "Audio and vision are two main modalities in video data. Multimodal learning, especially for audiovisual learning, has drawn considerable attention recently, which can boost the performance of various computer vision tasks. However, in video summarization, most existing approaches just exploit the visual information while neglecting the audio information. In this brief, we argue that the audio modality can assist vision modality to better understand the video content and structure and further benefit the summarization process. Motivated by this, we propose to jointly exploit the audio and visual information for the video summarization task and develop an audiovisual recurrent network (AVRN) to achieve this. Specifically, the proposed AVRN can be separated into three parts: 1) the two-stream long-short term memory (LSTM) is used to encode the audio and visual feature sequentially by capturing their temporal dependency; 2) the audiovisual fusion LSTM is used to fuse the two modalities by exploring the latent consistency between them; and 3) the self-attention video encoder is adopted to capture the global dependency in the video. Finally, the fused audiovisual information and the integrated temporal and global dependencies are jointly used to predict the video summary. Practically, the experimental results on the two benchmarks, i.e., SumMe and TVsum, have demonstrated the effectiveness of each part and the superiority of AVRN compared with those approaches just exploiting visual information for video summarization." @default.
• W3209983272 created "2021-11-08" @default.
• W3209983272 creator A5014425465 @default.
• W3209983272 creator A5068918243 @default.
• W3209983272 creator A5091227928 @default.
• W3209983272 date "2023-08-01" @default.
• W3209983272 modified "2023-10-01" @default.
• W3209983272 title "AudioVisual Video Summarization" @default.
• W3209983272 cites W1904325426 @default.
• W3209983272 cites W1966872876 @default.
• W3209983272 cites W1987366351 @default.
• W3209983272 cites W2007033327 @default.
• W3209983272 cites W2028613966 @default.
• W3209983272 cites W2028788183 @default.
• W3209983272 cites W2032342062 @default.
• W3209983272 cites W2064675550 @default.
• W3209983272 cites W2072551889 @default.
• W3209983272 cites W2097117768 @default.
• W3209983272 cites W2105174364 @default.
• W3209983272 cites W2120645068 @default.
• W3209983272 cites W2126532873 @default.
• W3209983272 cites W2134577448 @default.
• W3209983272 cites W2514143532 @default.
• W3209983272 cites W2526050071 @default.
• W3209983272 cites W2529272619 @default.
• W3209983272 cites W2532883456 @default.
• W3209983272 cites W2605100742 @default.
• W3209983272 cites W2607326921 @default.
• W3209983272 cites W2725751619 @default.
• W3209983272 cites W2737677090 @default.
• W3209983272 cites W2740101263 @default.
• W3209983272 cites W2766630207 @default.
• W3209983272 cites W2781922022 @default.
• W3209983272 cites W2788303226 @default.
• W3209983272 cites W2798970487 @default.
• W3209983272 cites W2883872876 @default.
• W3209983272 cites W2895758197 @default.
• W3209983272 cites W2904820498 @default.
• W3209983272 cites W2963220254 @default.
• W3209983272 cites W2963971014 @default.
• W3209983272 cites W2964167369 @default.
• W3209983272 cites W2967219836 @default.
• W3209983272 cites W2981642654 @default.
• W3209983272 cites W2982084422 @default.
• W3209983272 cites W2993980108 @default.
• W3209983272 cites W2997573100 @default.
• W3209983272 cites W2999428529 @default.
• W3209983272 cites W2999606372 @default.
• W3209983272 cites W3010790568 @default.
• W3209983272 cites W3027431227 @default.
• W3209983272 cites W3035392611 @default.
• W3209983272 cites W3083405884 @default.
• W3209983272 cites W3095374178 @default.
• W3209983272 cites W3099156605 @default.
• W3209983272 cites W3106313084 @default.
• W3209983272 cites W3107128832 @default.
• W3209983272 cites W3116298410 @default.
• W3209983272 cites W3125189040 @default.
• W3209983272 cites W3180463990 @default.
• W3209983272 doi "https://doi.org/10.1109/tnnls.2021.3119969" @default.
• W3209983272 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34695009" @default.
• W3209983272 hasPublicationYear "2023" @default.
• W3209983272 type Work @default.
• W3209983272 sameAs 3209983272 @default.
• W3209983272 citedByCount "5" @default.
• W3209983272 countsByYear W32099832722022 @default.
• W3209983272 countsByYear W32099832722023 @default.
• W3209983272 crossrefType "journal-article" @default.
• W3209983272 hasAuthorship W3209983272A5014425465 @default.
• W3209983272 hasAuthorship W3209983272A5068918243 @default.
• W3209983272 hasAuthorship W3209983272A5091227928 @default.
• W3209983272 hasBestOaLocation W32099832721 @default.
• W3209983272 hasConcept C111919701 @default.
• W3209983272 hasConcept C118505674 @default.
• W3209983272 hasConcept C138885662 @default.
• W3209983272 hasConcept C144024400 @default.
• W3209983272 hasConcept C154945302 @default.
• W3209983272 hasConcept C165696696 @default.
• W3209983272 hasConcept C170858558 @default.
• W3209983272 hasConcept C19768560 @default.
• W3209983272 hasConcept C2776401178 @default.
• W3209983272 hasConcept C2779903281 @default.
• W3209983272 hasConcept C2780226545 @default.
• W3209983272 hasConcept C36289849 @default.
• W3209983272 hasConcept C38652104 @default.
• W3209983272 hasConcept C41008148 @default.
• W3209983272 hasConcept C41895202 @default.
• W3209983272 hasConcept C49774154 @default.
• W3209983272 hasConcept C98045186 @default.
• W3209983272 hasConceptScore W3209983272C111919701 @default.
• W3209983272 hasConceptScore W3209983272C118505674 @default.
• W3209983272 hasConceptScore W3209983272C138885662 @default.
• W3209983272 hasConceptScore W3209983272C144024400 @default.
• W3209983272 hasConceptScore W3209983272C154945302 @default.
• W3209983272 hasConceptScore W3209983272C165696696 @default.
• W3209983272 hasConceptScore W3209983272C170858558 @default.
• W3209983272 hasConceptScore W3209983272C19768560 @default.
• W3209983272 hasConceptScore W3209983272C2776401178 @default.

• next