Creating Storyboard of Social Event from Advertorial Data
Bhavana R M
, Sangameshwari R K
Nonnegative matrix factorization (NMF), temporal relationships, representative photo selection.
Recent analyses have shown that searching about social events becoming obvious part of web search activity. Meanwhile existing sites can at most present social events modified by human beings, in this paper we propose a novel framework to discover social events by itself from search log facts and develop storyboards in which events are ordered consecutively. Since search logs can provide the user’s interests exactly, we use image search log for detecting various events. To perceive occasions from log facts we propose a smooth nonnegative matrix factorization framework, which blends information for query semantics, temporal relationships, search logs and time durability. Furthermore we take into account the time factor as a key element because different events will generate in different time inclinations. Also to give enriched media and visually attractive storyboards, each event is interrelated with illustrative set of photos ordered chronologically. These suitable photos are spontaneously selected from image search information by examining image content qualities. We take popular persons as our test space that takes huge proportion of image look trade.
"Creating Storyboard of Social Event from Advertorial Data", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.3, Issue 7, page no.91 - 95, July-2018, Available :https://ijsdr.org/papers/IJSDR1807014.pdf
Volume 3
Issue 7,
July-2018
Pages : 91 - 95
Paper Reg. ID: IJSDR_180490
Published Paper Id: IJSDR1807014
Downloads: 000346998
Research Area: Engineering
Country: Gulbarga, Karnataka, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
