Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386122702> ?p ?o ?g. }
- W4386122702 endingPage "109906" @default.
- W4386122702 startingPage "109906" @default.
- W4386122702 abstract "Video captioning aims to briefly describe the content of a video in accurate and fluent natural language, which is a hot research topic in multimedia processing. As a bridge between video and natural language, video captioning is a challenging task that requires a deep understanding of video content and effective utilization of diverse video multimodal information. Existing video captioning methods usually ignore the relative importance between different frames when aggregating frame-level video features and neglect the global semantic correlations between videos and texts in learning visual representations, resulting in the learned representations less effective. To address these problems, we propose a novel framework, namely Global Semantic Enhancement Network (GSEN) to generate high-quality captions for videos. Specifically, a feature aggregation module based on a lightweight attention mechanism is designed to aggregate frame-level video features, which highlights features of informative frames in video representations. In addition, a global semantic enhancement module is proposed to enhance semantic correlations for video and language representations in order to generate semantically more accurate captions. Extensive qualitative and quantitative experiments on two public benchmark datasets MSVD and MSR-VTT demonstrate that the proposed GSEN can achieve superior performance than state-of-the-art methods." @default.
- W4386122702 created "2023-08-25" @default.
- W4386122702 creator A5039507264 @default.
- W4386122702 creator A5065798474 @default.
- W4386122702 creator A5067265615 @default.
- W4386122702 creator A5081934618 @default.
- W4386122702 creator A5083468959 @default.
- W4386122702 creator A5085165965 @default.
- W4386122702 date "2024-01-01" @default.
- W4386122702 modified "2023-10-14" @default.
- W4386122702 title "Global semantic enhancement network for video captioning" @default.
- W4386122702 cites W1573040851 @default.
- W4386122702 cites W1586939924 @default.
- W4386122702 cites W1956340063 @default.
- W4386122702 cites W1969616664 @default.
- W4386122702 cites W2101105183 @default.
- W4386122702 cites W2102605133 @default.
- W4386122702 cites W2110933980 @default.
- W4386122702 cites W2117539524 @default.
- W4386122702 cites W2139501017 @default.
- W4386122702 cites W2142900973 @default.
- W4386122702 cites W2152984213 @default.
- W4386122702 cites W2425121537 @default.
- W4386122702 cites W2523993696 @default.
- W4386122702 cites W2745461083 @default.
- W4386122702 cites W2752191396 @default.
- W4386122702 cites W2883891001 @default.
- W4386122702 cites W2905145027 @default.
- W4386122702 cites W2951390634 @default.
- W4386122702 cites W2962958773 @default.
- W4386122702 cites W2962990649 @default.
- W4386122702 cites W2963524571 @default.
- W4386122702 cites W2963860638 @default.
- W4386122702 cites W2964241990 @default.
- W4386122702 cites W2964350391 @default.
- W4386122702 cites W2979739834 @default.
- W4386122702 cites W2980037812 @default.
- W4386122702 cites W2984862483 @default.
- W4386122702 cites W3003260174 @default.
- W4386122702 cites W3034221024 @default.
- W4386122702 cites W3035372819 @default.
- W4386122702 cites W3035392611 @default.
- W4386122702 cites W3084427242 @default.
- W4386122702 cites W3093309253 @default.
- W4386122702 cites W3099206234 @default.
- W4386122702 cites W3100255860 @default.
- W4386122702 cites W3134875898 @default.
- W4386122702 cites W3176425931 @default.
- W4386122702 cites W3192801752 @default.
- W4386122702 cites W3205021045 @default.
- W4386122702 cites W4220790454 @default.
- W4386122702 cites W4281385024 @default.
- W4386122702 cites W4286751465 @default.
- W4386122702 doi "https://doi.org/10.1016/j.patcog.2023.109906" @default.
- W4386122702 hasPublicationYear "2024" @default.
- W4386122702 type Work @default.
- W4386122702 citedByCount "0" @default.
- W4386122702 crossrefType "journal-article" @default.
- W4386122702 hasAuthorship W4386122702A5039507264 @default.
- W4386122702 hasAuthorship W4386122702A5065798474 @default.
- W4386122702 hasAuthorship W4386122702A5067265615 @default.
- W4386122702 hasAuthorship W4386122702A5081934618 @default.
- W4386122702 hasAuthorship W4386122702A5083468959 @default.
- W4386122702 hasAuthorship W4386122702A5085165965 @default.
- W4386122702 hasConcept C103910844 @default.
- W4386122702 hasConcept C115961682 @default.
- W4386122702 hasConcept C126042441 @default.
- W4386122702 hasConcept C13280743 @default.
- W4386122702 hasConcept C138885662 @default.
- W4386122702 hasConcept C154945302 @default.
- W4386122702 hasConcept C157657479 @default.
- W4386122702 hasConcept C162324750 @default.
- W4386122702 hasConcept C1667742 @default.
- W4386122702 hasConcept C176217482 @default.
- W4386122702 hasConcept C184337299 @default.
- W4386122702 hasConcept C185798385 @default.
- W4386122702 hasConcept C187736073 @default.
- W4386122702 hasConcept C195324797 @default.
- W4386122702 hasConcept C199360897 @default.
- W4386122702 hasConcept C204321447 @default.
- W4386122702 hasConcept C205649164 @default.
- W4386122702 hasConcept C21547014 @default.
- W4386122702 hasConcept C23123220 @default.
- W4386122702 hasConcept C2776401178 @default.
- W4386122702 hasConcept C2780451532 @default.
- W4386122702 hasConcept C41008148 @default.
- W4386122702 hasConcept C41895202 @default.
- W4386122702 hasConcept C49774154 @default.
- W4386122702 hasConcept C76155785 @default.
- W4386122702 hasConcept C86034646 @default.
- W4386122702 hasConceptScore W4386122702C103910844 @default.
- W4386122702 hasConceptScore W4386122702C115961682 @default.
- W4386122702 hasConceptScore W4386122702C126042441 @default.
- W4386122702 hasConceptScore W4386122702C13280743 @default.
- W4386122702 hasConceptScore W4386122702C138885662 @default.
- W4386122702 hasConceptScore W4386122702C154945302 @default.
- W4386122702 hasConceptScore W4386122702C157657479 @default.
- W4386122702 hasConceptScore W4386122702C162324750 @default.