Combining Global and Local Attention with Positional Encoding for Video Summarization (2021)

First Author: Apostolidis E
Attributed to:  Deep Learning from Crawled Spatio-Temporal Representations of Video (DECSTER) funded by EPSRC

Abstract

No abstract provided

Bibliographic Information

Digital Object Identifier: http://dx.doi.org/10.1109/ism52913.2021.00045

Publication URI: https://api.elsevier.com/content/abstract/scopus_id/85125009998

Type: Conference/Paper/Proceeding/Abstract