Searching for a Video in World Wide Web has augmented expeditiously as there's been an explosion of growth in video on
social media channels and networks in recent years. At present video search engines use the title, description, and thumbnail of the video
for identifying the right one. In this paper, a novel video searching methodology is proposed using the Video indexing method. Video
indexing is a technique of preparing an index, based on the content of video for the easy access of frames of interest. Videos are stored
along with an index which is created out of video indexing technique. The video searching methodology check the content of index
attached with each video to ensure that video is matching with the searching keyword and its relevance ensured, based on the word count
of searching keyword in video index. The video searching methodology check the content of index attached with each video to ensure that
video is matching with the searching keyword and its relevance ensured, based on the word count of searching keyword in video index.
Video captions are generated by the deep learning network model by combining global local (glocal) attention and context cascading
mechanisms using VIST-Visual Story Telling dataset. Video Index generator uses Wormhole algorithm, that ensure minimum worst-case
time for searching a key with a length of L. Video searching methodology extracts the video clip where the frames of interest lies from the
original huge sized source video. Hence, searcher can get and download a video clip instead of downloading entire video from the video
storage. This reduces the bandwidth requirement and time taken to download the videos.
Published In:IJCSN Journal Volume 8, Issue 2
Date of Publication : April 2019
Pages : 144-147
Figures :01
Tables : --
Jaimon Jacob :
achieved the degrees B.Tech in
Computer Science and Engineering from University of Calicut in
2003, M.Tech in Digital Image processing from Anna University,
Chennai in 2010, MBA in Information Technology from Sikkim
Manipal University in 2012, M.Tech in Computer and Information
Science from Cochin University of Science and Technology in
2014. Currently working as Asst. professor in Computer Science
and Engineering, Department of Computer Science, Govt. Model
Engineering College. Thrikkakara, Ernakulam, Kerala. Four
International Conference papers and Two National Conference
research papers published. Author passionate in research area
"video processing". Associate with professional bodies ISTE,IETE
and IE.
Prof.(Dr.) Sudeep Ilayidom :
achieved the
degrees B.Tech, M.Tech, PhD. Currently Working as Professor,
Division of Computer Engineering ,School of Engineering, Cochin
university of Science and Technology. Ernakulam, Kerala.
Published a Text book on "Data mining and warehousing" by
Cengage Fifty Five research papers published in the related area
Data mining. A well known musician in Malayalam Film Industry.
Passionate ion research area Data Mining, Big Data and related
areas.
Prof.(Dr.) V.P.Devassia :
achieved the degrees
B.Sc. Engineering from MA College of Engineering,
Kothamangalam, in 1983, M.Tech in Industrial Electronics from
Cochin University of Science and Technology, Ph.D in Signal
Processing from Cochin University of Science and Technology in
2001. Worked as Graduate Engineer(T) in Hindustan Paper
Corporation Ltd, Design Engineer, HMT Limited, Principal, Govt.
Model Engineering College, Ernakulam. Author passionate in
research area Signal Processing. associate with professional
bodies ISTE,IETE and IE.
Video Indexing, Video Searching, Visual Story Telling, Wormhole, glocal, VIST
In this paper, an Efficient Video Searching methodology
using Video Indexing is proposed using the Video, Audio,
and Textual information. RNN based speech recognition
model is used for audio to text conversion, OCR technique
is used for Text extraction from preprocessed frames.
Video captions generated for preparing the video index
from video content uses the VIST-Visual Story Telling
dataset for the generation of multi stage cued story. Perfect
and continuous Visual story formation ensured from the
consecutive set of images by the deep learning network
model. The features of Global attention for overall
summarizing and Local attention for image specific
encoding along with context cascading mechanisms
efficiently caption the video given as input. Effective
implementation of this methodology in Video Search
Engine, will initiate incredible changes in data traffic by
minimizing the size of video transport. Also, from the user
point of view, the intended part of video only need be
accessed.
[1] Cisco "Visual Networking Index: Forecast and Trends,
2017-2022", CISCO, February 27, 2019,
https://www.cisco.com/c/en/us/solutions/collateral/service
-provider/visual-networking-index-vni/white-paper-c11-
741490.pdf.
[2] Zheng Cao, and Ming Zhu, "An Efficient Video
Similarity Search Algorithm", IEEE Transactions on
Consumer Electronics, Vol. 56, No. 2, May 2010.
[3] Qiu Chen , Koji Kotani , Feifei Lee and Tadahiro Ohmi,
"A fast search algorithm for large video database using
HOG based features", David C., Wyld et al. (Eds) : ITCS,
JSE, SIP, ARIA, NLP-2016, pp. 35-41, 2016.
[4] H.Aradhye, G. Toderici, and J. Yagnik. "Video2text:
Learning to annotate video content".ICDM Workshop on
Internet Multimedia Mining, Google, Inc,USA,2009.
[5] N. Krishnamoorthy, G. Malkarnenkar, R. J. Mooney, K.
Saenko, and S. Guadarrama,. "Generating Naturallanguage
video descriptions using text-mined
knowledge". In Proceedings of the Workshop on Vision
and Natural Language Processing, pp 10-19,July 2013.
[6] J. Donahue, L. A. Hendricks, S. Guadarrama, M.
Rohrbach, S. Venugopalan, K. Saenko, and T. Darrell,
"Long-term recurrent convolutional networks for visual
recognition and description", arXiv:1411.4389v4 [cs.CV],
May 2016
[7] O. Vinyals, A. Toshev, S. Bengio, and D. Erhan, "Show
and tell: A Neural Image Caption Generator",
arXiv:1411.4555v2 [cs.CV], April 2015.
[8] S. Venugopalan, H. Xu, J. Donahue, M. Rohrbach, R.
Mooney, and K. Saenko. "Translating videos to natural
language using deep recurrent neural networks",
arXiv:1412.4729v3 [cs.CV], April, 2015.
[9] J. Liu, Q.Yu, O. Javed, S.Ali, Amir Tamrakar,
A.Divakaran , H. Cheng, H. Sawhney, "Video event
recognition using concept attributes", IEEE Workshop on
Applications of Computer Vision (WACV), March 2013
[10] Masoud Mazloom, Amirhossein Habibian and Cees G. M.
Snoek ISLA,. "Querying for Video Events by Semantic
Signatures from Few Examples". Proceedings of the 21st
ACM International Conference on multimedia, pp 609-
612 October, 2013.
[11] Subhashini Venugopalan, Marcus Rohrbach Jeff Donahue
Raymond Mooney Trevor Darrell Kate Saenko,
"Sequence to Sequence - Video to Text", Proceedings of
the 2015, IEEE International Conference on Computer
Vision (ICCV),Pages 4534-4542 December, 2015.
[12] N.Gayathri, K.Mahesh, "A Systematic study on Video
Indexing", International Journal of Pure and Applied
Mathematics Volume 118 No. 8 2018, 425-428
[13] M.Ravinder, T.Venugopal, Sultanpur, Medak, "Content-
Based Video Indexing and Retrieval using Key frames
Texture, Edge and Motion Features", International
Journal of Current Engineering and Technology, Vol.6,
No.2,April,2016.
[14] Natsuda Laokulrat, Sang Phan, Noriki Nishida, Raphael
Shu Yo Ehara , Naoaki Okazaki, Yusuke Miyao and
Hideki Nakayama, "Generating Video Description using
Sequence-to-sequence Model with Temporal Attention",
Proceedings of International Conference on
Computational Linguistics: Technical Papers, pages 44-
52, Osaka, Japan, December, 2016.
[15] Anubhav Kumar , Raj Kumar Goel , "An Efficient
Algorithm for Text Localization and Extraction in
Complex Video Text Images", IEEE International
Conference on Information Management in the
Knowledge Economy,2013.
[16] T. K. Huang, F.Ferraro,"Visual storytelling". Annual
Conference of the North American Chapter of the
Association for Computational Linguistics,
arXiv:1604.03968v1 [cs.CL], 2016.
[17] T.Kim, Min-OhHeo, SeonilSon Kyoung-WhaPark
,Byoung-Tak Zhang "GLAC-Net: GLobal Attention
Cascading Networks for Multi-Image Cued Story
Generation", arXiv:1805.10973v3, Feb 2019.
[18] Xingbo Wu, Fan Ni , Song Jiang, "Wormhole: A Fast
Ordered Index for In-memory Data Management",
arXiv:1805.02200v2 [cs.DB], May 2018.
