Mostrar el registro sencillo del ítem
dc.contributor.author | de Curtò-I Díaz, Joaquim | es_ES |
dc.contributor.author | de Zarzà-I Cubero, Irene | es_ES |
dc.contributor.author | Roig, Gemma | es_ES |
dc.contributor.author | Tavares De Araujo Cesariny Calafate, Carlos Miguel | es_ES |
dc.date.accessioned | 2024-04-30T18:06:39Z | |
dc.date.available | 2024-04-30T18:06:39Z | |
dc.date.issued | 2023-04 | es_ES |
dc.identifier.uri | http://hdl.handle.net/10251/203874 | |
dc.description.abstract | [EN] This manuscript presents a new benchmark for assessing the quality of visual summaries without the need for human annotators. It is based on the Signature Transform, specifically focusing on the RMSE and the MAE Signature and Log-Signature metrics, and builds upon the assumption that uniform random sampling can offer accurate summarization capabilities. We provide a new dataset comprising videos from Youtube and their corresponding automatic audio transcriptions. Firstly, we introduce a preliminary baseline for automatic video summarization, which has at its core a Vision Transformer, an image¿text model pre-trained with Contrastive Language¿Image Pre-training (CLIP), as well as a module of object detection. Following that, we propose an accurate technique grounded in the harmonic components captured by the Signature Transform, which delivers compelling accuracy. The analytical measures are extensively evaluated, and we conclude that they strongly correlate with the notion of a good summary. | es_ES |
dc.description.sponsorship | This work was supported by the HK Innovation and Technology Commission (InnoHK Project CIMDA). We acknowledge the support of Universitat Politècnica de València; R&D project PID2021-122580NB-I00, funded by MCIN/AEI/10.13039/501100011033 and ERDF. We thank the following funding sources from GOETHE-University Frankfurt am Main; DePP Dezentrale Plannung von Platoons im Straßengüterverkehr mit Hilfe einer KI auf Basis einzelner LKW and Center for Data Science & AI . | es_ES |
dc.language | Inglés | es_ES |
dc.publisher | MDPI AG | es_ES |
dc.relation.ispartof | Electronics | es_ES |
dc.rights | Reconocimiento (by) | es_ES |
dc.subject | Video summarization | es_ES |
dc.subject | Large language models | es_ES |
dc.subject | Visual language models | es_ES |
dc.subject | CLIP | es_ES |
dc.subject | Signature transform | es_ES |
dc.subject.classification | ARQUITECTURA Y TECNOLOGIA DE COMPUTADORES | es_ES |
dc.title | Summarization of Videos with the Signature Transform | es_ES |
dc.type | Artículo | es_ES |
dc.identifier.doi | 10.3390/electronics12071735 | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2021-122580NB-I00/ES/SISTEMAS INTELIGENTES DE SENSORIZACION PARA ECOSISTEMAS, ESPACIOS URBANOS Y MOVILIDAD SOSTENIBLE/ | es_ES |
dc.rights.accessRights | Abierto | es_ES |
dc.contributor.affiliation | Universitat Politècnica de València. Escola Tècnica Superior d'Enginyeria Informàtica | es_ES |
dc.description.bibliographicCitation | De Curtò-I Díaz, J.; De Zarzà-I Cubero, I.; Roig, G.; Tavares De Araujo Cesariny Calafate, CM. (2023). Summarization of Videos with the Signature Transform. Electronics. 12(7). https://doi.org/10.3390/electronics12071735 | es_ES |
dc.description.accrualMethod | S | es_ES |
dc.relation.publisherversion | https://doi.org/10.3390/electronics12071735 | es_ES |
dc.type.version | info:eu-repo/semantics/publishedVersion | es_ES |
dc.description.volume | 12 | es_ES |
dc.description.issue | 7 | es_ES |
dc.identifier.eissn | 2079-9292 | es_ES |
dc.relation.pasarela | S\487015 | es_ES |
dc.contributor.funder | AGENCIA ESTATAL DE INVESTIGACION | es_ES |
dc.contributor.funder | European Regional Development Fund | es_ES |
dc.contributor.funder | Universitat Politècnica de València | es_ES |