Abstract
Searching and localizing special moments or important events in any video such as baby’s first steps, game-winning goal, lectures, medical diagnosis techniques and protagonist dialogues can be very useful and productive, but it is a time-consuming job to manually search for the anticipated clip from the plethora of videos. This is where temporal localization concept comes into play with the help of robust deep learning techniques and Intelligent video analytics. Studying patterns, recognizing key objects and spotting anomalies in the videos can be performed swiftly using intelligent video analytics. Increasing the number of meta tags assigned to a video, accuracy of searching within the video as well as from the bucket of videos can potentially improved. The system calculates the screen time of prime characters in a video, auto-generates tags using subtitle and object classifiers and further, localize topics within a video with the help of generated tags.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sigurdsson, G.A., Divvala, S., Farhadi, A., Gupta, A.: Asynchronous temporal fields for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 585–594 (2017)
Sabokrou, M., Fathy, M., Hoseini, M., Klette, R.: Real-time anomaly detection and localization in crowded scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 56–62 (2015)
Alwassel, H., Caba Heilbron, F., Ghanem, B.: Action search: spotting actions in videos and its application to temporal action localization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 251–266 (2018)
Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-talc: weakly-supervised temporal activity localization and classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563–579 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Rahul, R., Pradipkumar, R., Geetha Devasena, M.S. (2021). Temporal Localization of Topics Within Videos. In: Gunjan, V.K., Zurada, J.M. (eds) Modern Approaches in Machine Learning and Cognitive Science: A Walkthrough. Studies in Computational Intelligence, vol 956. Springer, Cham. https://doi.org/10.1007/978-3-030-68291-0_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-68291-0_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68290-3
Online ISBN: 978-3-030-68291-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)