loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock
Reinforcement Learning based Video Summarization with Combination of ResNet and Gated Recurrent Unit

Topics: 3D Deep Learning; Camera Networks and Vision; Deep Learning for Image-to-Text Translation and Dialogue; Deep Learning for Visual Understanding ; Document Imaging in Business; Features Extraction; Human and Computer Interaction; Image-Based Modeling and 3D Reconstruction; Machine Learning Technologies for Vision; Medical Image Applications; Multi-task learning; Optical Flow and Motion Analyses; Segmentation and Grouping; Self-taught Learning; Transfer Learning; Understanding from Wearable and Mobile Cameras; Video Surveillance and Event Detection

Authors: Muhammad Atif Afzal and Muhammad Sohail Tahir

Affiliation: National University of Computer and Emerging Sciences, Karachi, Pakistan

Keyword(s): Video Summarization, Reinforcement Learning, Reward Function, ResNet, Gated Recurrent Unit.

Abstract: Video cameras are getting ubiquitous with passage of time. Huge amount of video data is generated daily in this world that needs to be handled efficiently in limited storage and processing power. Video summarization renders the best way to quickly review over lengthy videos along with controlling storage and processing power requirements. Deep reinforcement-deep summarization network (DR-DSN) is a popular method for video summarization but performance of this method is limited and can be enhanced with better representation of video data. Most recently, it has been observed that deep residual networks are quite successful in many computer vision applications including video retrieval and captioning. In this paper, we have investigated deep feature representation for video summarization using deep residual network where ResNet 152 is being used to extract deep videos features. To speed up the model, long short term memory is replaced with gated recurrent unit, thus gave us flexibility to add another RNN layer which resulted in significant improvement in performance. With this combination of ResNet-152 and two layered gated recurrent unit (GRU), we performed experiments on SumMe video dataset and got results not only better than DR-DSN but also better than several state of art video summarization methods. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.16.51.3

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Afzal, M. and Tahir, M. (2021). Reinforcement Learning based Video Summarization with Combination of ResNet and Gated Recurrent Unit. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6; ISSN 2184-4321, SciTePress, pages 261-268. DOI: 10.5220/0010197402610268

@conference{visapp21,
author={Muhammad Atif Afzal. and Muhammad Sohail Tahir.},
title={Reinforcement Learning based Video Summarization with Combination of ResNet and Gated Recurrent Unit},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={261-268},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010197402610268},
isbn={978-989-758-488-6},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - Reinforcement Learning based Video Summarization with Combination of ResNet and Gated Recurrent Unit
SN - 978-989-758-488-6
IS - 2184-4321
AU - Afzal, M.
AU - Tahir, M.
PY - 2021
SP - 261
EP - 268
DO - 10.5220/0010197402610268
PB - SciTePress