SummaryNet: two-stream convolutional networks for automatic video summarisation

Simple item page
dc.contributor.authorJappie, Ziyad
dc.date.accessioned2020-11-16T22:45:16Z
dc.date.available2020-11-16T22:45:16Z
dc.date.issued2020
dc.descriptionA dissertation submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in fulfilment of the requirements for the degree of Master of Science, 2020en_ZA
dc.description.abstractVideo summarisation is the task of automatically summarising a video sequence, to extract “important” parts of the video so as to give an overview of what has occurred. The benefit of solving this problem is that it can be applied to a myriad of fields such as the entertainment industry, sports, e-learning and many more. There is a distinct inherent difficulty with video summarisation due to its subjectivity - there is no one defined correct answer. As such, it is particularly difficult to define and measure tangible performance. This is in addition to the other difficulties associated with general video processing. We present a novel two-stream network framework for automatic video summarisation, which we call SummaryNet. The SummaryNet employs a deep two-stream network to model pertinent spatio-temporal features by leveraging RGB as well as optical flow information. We use the Two-Stream Inflated 3D ConvNet (I3D) network to extract high-level, semantic feature representations as inputs to our SummaryNet model. Experimental results on common benchmark datasets show that the considered method achieves comparable or better results than the state-of-the-art video summarisation methodsen_ZA
dc.description.librarianCK2020en_ZA
dc.facultyFaculty of Scienceen_ZA
dc.format.extentOnline resource (ix, 90 leaves)
dc.identifier.citationJappie, Ziyad (2020) SummaryNet: two-stream convolutional networks for automatic video summarisation, University of the Witwatersrand, Johannesburg, https://hdl.handle.net/10539/30207
dc.identifier.urihttps://hdl.handle.net/10539/30207
dc.language.isoenen_ZA
dc.schoolSchool of Computer Science and Applied Mathematicsen_ZA
dc.subject.lcshComputer vision
dc.subject.lcshPattern perception
dc.subject.lcshImage processing
dc.titleSummaryNet: two-stream convolutional networks for automatic video summarisationen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
ZIYAD JAPPIE 557803.pdf
Size:
10.57 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
ETD Collection