Lightweight dense video captioning with cross-modal attention and knowledge-enhanced unbiased scene graph

Dense video captioning (DVC) aims at generating description for each scene in a video. Despite attractive progress for this task, previous works usually only concentrate on exploiting visual features while neglecting audio information in the video, resulting in inaccurate scene event location. In th...

Descripción completa

Detalles Bibliográficos
Autores principales: Han, Shixing, Liu, Jin, Zhang, Jinyingming, Gong, Peizhu, Zhang, Xiliang, He, Huihua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2023
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9950023/
https://www.ncbi.nlm.nih.gov/pubmed/36855683
http://dx.doi.org/10.1007/s40747-023-00998-5

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9950023/
https://www.ncbi.nlm.nih.gov/pubmed/36855683
http://dx.doi.org/10.1007/s40747-023-00998-5

Ejemplares similares