Video Summarization using Spatio-Temporal Features by Detecting Representative Content based on Supervised Deep Learning
Date
2021-08
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Pulchowk Campus
Abstract
Video Summarization is the approach to generate the compact version of video
keeping relevant content intact and eliminating redundancy. In this work, a frame-
work has been proposed which makes use of the spatial and temporal features
with self attention from the video sequences to identify the representative con-
tent by generating temporal proposals and supervised learning from the data
manually created by humans or users. Existing Supervised methods don't deal
with the temporal interest and its consistency. For that temporal uniformity is
also necessary which can be addressed by predicting the temporal proposals of
the video segment. The proposed work treats it as temporal action detection
which predicts importance score and location of the segments simultaneously by
developing the anchor based method which generates anchors of varying lengths to
identify interesting proposals. Moreover the extensive quantitative and qualitative
analysis on TVSumm and SumMe datasets augmented with OVP and YouTube
datasets justify the e ectiveness of the method.
Description
Video Summarization is the approach to generate the compact version of video
keeping relevant content intact and eliminating redundancy.
Keywords
Video Summarization,, Self Attention,, Deep Learning
Citation
MASTER OF SCIENCE IN INFORMATION AND COMMUNICATION ENGINEERING