Exploring Global Diversity and Local Context for Video Summarization. (arXiv:2201.11345v1 [cs.CV])

Web: http://arxiv.org/abs/2201.11345

Video summarization aims to automatically generate a diverse and concise
summary which is useful in large-scale video processing. Most of methods tend
to adopt self attention mechanism across video frames, which fails to model the
diversity of video frames. To alleviate this problem, we revisit the pairwise
similarity measurement in self attention mechanism and find that the existing
inner-product affinity leads to discriminative features rather than diversified
features. In light of this phenomenon, we propose global diverse attention by
using …

arxiv cv diversity global video