Matches in SemOpenAlex for { <https://semopenalex.org/work/W4353111571> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4353111571 abstract "Video summarization aims to distill the most important information from a source video to produce either an abridged clip or a textual narrative. Traditionally, different methods have been proposed depending on whether the output is a video or text, thus ignoring the correlation between the two semantically related tasks of visual summarization and textual summarization. We propose a new joint video and text summarization task. The goal is to generate both a shortened video clip along with the corresponding textual summary from a long video, collectively referred to as a cross-modal summary. The generated shortened video clip and text narratives should be semantically well aligned. To this end, we first build a large-scale human-annotated dataset -- VideoXum (X refers to different modalities). The dataset is reannotated based on ActivityNet. After we filter out the videos that do not meet the length requirements, 14,001 long videos remain in our new dataset. Each video in our reannotated dataset has human-annotated video summaries and the corresponding narrative summaries. We then design a novel end-to-end model -- VTSUM-BILP to address the challenges of our proposed task. Moreover, we propose a new metric called VT-CLIPScore to help evaluate the semantic consistency of cross-modality summary. The proposed model achieves promising performance on this new task and establishes a benchmark for future research." @default.
- W4353111571 created "2023-03-23" @default.
- W4353111571 creator A5005264558 @default.
- W4353111571 creator A5041358066 @default.
- W4353111571 creator A5055469774 @default.
- W4353111571 creator A5065482772 @default.
- W4353111571 creator A5066409438 @default.
- W4353111571 creator A5067929709 @default.
- W4353111571 creator A5091692262 @default.
- W4353111571 date "2023-03-21" @default.
- W4353111571 modified "2023-09-27" @default.
- W4353111571 title "VideoXum: Cross-modal Visual and Textural Summarization of Videos" @default.
- W4353111571 doi "https://doi.org/10.48550/arxiv.2303.12060" @default.
- W4353111571 hasPublicationYear "2023" @default.
- W4353111571 type Work @default.
- W4353111571 citedByCount "0" @default.
- W4353111571 crossrefType "posted-content" @default.
- W4353111571 hasAuthorship W4353111571A5005264558 @default.
- W4353111571 hasAuthorship W4353111571A5041358066 @default.
- W4353111571 hasAuthorship W4353111571A5055469774 @default.
- W4353111571 hasAuthorship W4353111571A5065482772 @default.
- W4353111571 hasAuthorship W4353111571A5066409438 @default.
- W4353111571 hasAuthorship W4353111571A5067929709 @default.
- W4353111571 hasAuthorship W4353111571A5091692262 @default.
- W4353111571 hasBestOaLocation W43531115711 @default.
- W4353111571 hasConcept C106131492 @default.
- W4353111571 hasConcept C13280743 @default.
- W4353111571 hasConcept C138885662 @default.
- W4353111571 hasConcept C144024400 @default.
- W4353111571 hasConcept C154945302 @default.
- W4353111571 hasConcept C162324750 @default.
- W4353111571 hasConcept C170858558 @default.
- W4353111571 hasConcept C176217482 @default.
- W4353111571 hasConcept C185592680 @default.
- W4353111571 hasConcept C185798385 @default.
- W4353111571 hasConcept C187736073 @default.
- W4353111571 hasConcept C188027245 @default.
- W4353111571 hasConcept C199033989 @default.
- W4353111571 hasConcept C204321447 @default.
- W4353111571 hasConcept C205649164 @default.
- W4353111571 hasConcept C21547014 @default.
- W4353111571 hasConcept C23123220 @default.
- W4353111571 hasConcept C2776436953 @default.
- W4353111571 hasConcept C2779903281 @default.
- W4353111571 hasConcept C2780451532 @default.
- W4353111571 hasConcept C31972630 @default.
- W4353111571 hasConcept C36289849 @default.
- W4353111571 hasConcept C41008148 @default.
- W4353111571 hasConcept C41895202 @default.
- W4353111571 hasConcept C71139939 @default.
- W4353111571 hasConceptScore W4353111571C106131492 @default.
- W4353111571 hasConceptScore W4353111571C13280743 @default.
- W4353111571 hasConceptScore W4353111571C138885662 @default.
- W4353111571 hasConceptScore W4353111571C144024400 @default.
- W4353111571 hasConceptScore W4353111571C154945302 @default.
- W4353111571 hasConceptScore W4353111571C162324750 @default.
- W4353111571 hasConceptScore W4353111571C170858558 @default.
- W4353111571 hasConceptScore W4353111571C176217482 @default.
- W4353111571 hasConceptScore W4353111571C185592680 @default.
- W4353111571 hasConceptScore W4353111571C185798385 @default.
- W4353111571 hasConceptScore W4353111571C187736073 @default.
- W4353111571 hasConceptScore W4353111571C188027245 @default.
- W4353111571 hasConceptScore W4353111571C199033989 @default.
- W4353111571 hasConceptScore W4353111571C204321447 @default.
- W4353111571 hasConceptScore W4353111571C205649164 @default.
- W4353111571 hasConceptScore W4353111571C21547014 @default.
- W4353111571 hasConceptScore W4353111571C23123220 @default.
- W4353111571 hasConceptScore W4353111571C2776436953 @default.
- W4353111571 hasConceptScore W4353111571C2779903281 @default.
- W4353111571 hasConceptScore W4353111571C2780451532 @default.
- W4353111571 hasConceptScore W4353111571C31972630 @default.
- W4353111571 hasConceptScore W4353111571C36289849 @default.
- W4353111571 hasConceptScore W4353111571C41008148 @default.
- W4353111571 hasConceptScore W4353111571C41895202 @default.
- W4353111571 hasConceptScore W4353111571C71139939 @default.
- W4353111571 hasLocation W43531115711 @default.
- W4353111571 hasOpenAccess W4353111571 @default.
- W4353111571 hasPrimaryLocation W43531115711 @default.
- W4353111571 hasRelatedWork W132250100 @default.
- W4353111571 hasRelatedWork W2093597205 @default.
- W4353111571 hasRelatedWork W2389846579 @default.
- W4353111571 hasRelatedWork W2392495745 @default.
- W4353111571 hasRelatedWork W2747680751 @default.
- W4353111571 hasRelatedWork W3163695726 @default.
- W4353111571 hasRelatedWork W4221155488 @default.
- W4353111571 hasRelatedWork W4226118367 @default.
- W4353111571 hasRelatedWork W4306291189 @default.
- W4353111571 hasRelatedWork W4320823199 @default.
- W4353111571 isParatext "false" @default.
- W4353111571 isRetracted "false" @default.
- W4353111571 workType "article" @default.