VSTAR: Visual Semantic Thumbnails and tAgs Revitalization

作者:

Highlights:

• Exploiting image captioning to simultaneously suggest tags and thumbnails.

• Retrieval of semantically relevant trends to be suggested as video tags.

• Providing of user-driven trade-off between tags/thumbnails quality and quantity.

• A proper dataset of YouTube videos has been built and released.

• Results confirmed that the system suggests strongly relevant tags and thumbnail.

摘要

•Exploiting image captioning to simultaneously suggest tags and thumbnails.•Retrieval of semantically relevant trends to be suggested as video tags.•Providing of user-driven trade-off between tags/thumbnails quality and quantity.•A proper dataset of YouTube videos has been built and released.•Results confirmed that the system suggests strongly relevant tags and thumbnail.

论文关键词:Machine learning,Video tagging,Thumbnail enrichment,Google trends,Semantic enrichment

论文评审过程:Received 13 April 2021, Revised 28 August 2021, Accepted 3 December 2021, Available online 1 January 2022, Version of Record 7 January 2022.

论文官网地址:https://doi.org/10.1016/j.eswa.2021.116375