Version 1
: Received: 5 December 2018 / Approved: 6 December 2018 / Online: 6 December 2018 (13:19:57 CET)
Version 4
: Received: 1 August 2019 / Approved: 5 August 2019 / Online: 5 August 2019 (03:48:49 CEST)
How to cite:
Shen, Y.; Li, Y. The User-Pleasant Video Skimming by Multi-Modal Keywords Semantics. Preprints2018, 2018120086. https://doi.org/10.20944/preprints201812.0086.v4
Shen, Y.; Li, Y. The User-Pleasant Video Skimming by Multi-Modal Keywords Semantics. Preprints 2018, 2018120086. https://doi.org/10.20944/preprints201812.0086.v4
Shen, Y.; Li, Y. The User-Pleasant Video Skimming by Multi-Modal Keywords Semantics. Preprints2018, 2018120086. https://doi.org/10.20944/preprints201812.0086.v4
APA Style
Shen, Y., & Li, Y. (2019). The User-Pleasant Video Skimming by Multi-Modal Keywords Semantics. Preprints. https://doi.org/10.20944/preprints201812.0086.v4
Chicago/Turabian Style
Shen, Y. and Yingbo Li. 2019 "The User-Pleasant Video Skimming by Multi-Modal Keywords Semantics" Preprints. https://doi.org/10.20944/preprints201812.0086.v4
Abstract
In this paper, we propose a novel approach of video skimming by exploiting the fusion of video temporal information and keyword information representation extracted from multi-model video information including audio, text and visual indices. In addition, we introduce the brand-safe filtering and sentiment analysis in order to only reserve the user-friendly content in the video skim. In the experiment by using the videos from YouTube-8M dataset, we have proved that the semantic conservation in the video skim from the proposed approach highly outperforms the approaches by only partial information of the video in conserving the semantic content of the video.
Keywords
multi-model information fusion; video skim-ming; audio and text classification; keyframe extraction
Subject
Computer Science and Mathematics, Computer Science
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: Yingbo Li
Commenter's Conflict of Interests: Author