Video captioning

dc.accession.numberT00866
dc.classification.ddc621.367 LAH
dc.contributor.advisorMandal, Srimanta
dc.contributor.authorLaheri, Vishal Bharatkumar
dc.date.accessioned2020-09-22T19:41:36Z
dc.date.accessioned2025-06-28T10:28:22Z
dc.date.available2023-02-16T19:41:36Z
dc.date.issued2020
dc.degreeM. Tech
dc.description.abstractIn recent years, models for video captioning task has been improved very much. Despite advancement, it is still impeded by hardware constraints. Video captioning models takes a sequence of images and caption as inputs, which makes it one of the most memory consuming and computation required task. In this project work, we exploit the importance of required frames from the video to get the desired performance. We also propose the use of a video summarizing model embedded with the captioning model for dynamically selecting frames, which allows the reduction of required frames without losing Spatio-temporal information of the video.
dc.identifier.citationLaheri, Vishal Bharatkumar (2020). Video captioning. Dhirubhai Ambani Institute of Information and Communication Technology. vi, 25 p. (Acc.No: T00866)
dc.identifier.urihttp://drsr.daiict.ac.in/handle/123456789/944
dc.student.id201811037
dc.subjectDeep Learning
dc.subjectComputer Vision
dc.subjectLSTM
dc.subjectVideo Description
dc.subjectVideo Captioning
dc.titleVideo captioning
dc.typeDissertation

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
201811037.pdf
Size:
4.06 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Plain Text
Description: