Abstract
We propose visual memes, or frequently reposted short video segments, for
tracking large-scale video remix in social media. Video remixing is a
prevalent phenomenon on social media platforms, it is part of "venacular
creativity" where users create "curated selections based on what they liked
or thought was important". Social influence are often characterized from
text-based online interactions such as quoting or reweeting, our tool allows
such metric to be developed for visual media. Visual memes are extracted by
novel and highly scalable detection algorithms that we develop, with over
96% precision and 80% recall.  We monitor real-world events on YouTube, and
we model interactions using a graph model over memes. This allows us to
define several measures of influence.  These abstractions, using more than
two million video shots from several large-scale event datasets, enable us
to quantify and efficiently extract several important observations: over
half of the videos contain re-mixed content, which appears rapidly; video
view counts, particularly high ones, are poorly correlated with the virality
of content; the influence of traditional news media versus citizen
journalists varies from event to event; iconic single images of an event are
easily extracted; and content that will have long lifespan can be predicted
within a day after it first appears.  We hypothesize that such tools for
tracking multi-modal interactions will be a necessity for modeling the
multimedia social web.

Bio
Lexing Xie is Lecturer in the Research School of Computer Science at the
Australian National University. She received B.S. from Tsinghua University,
Beijing, China, and M.S. and Ph.D. degrees from Columbia University, all in
Electrical Engineering. She was with IBM T.J. Watson Research Center in New
York from 2005 to 2010.  Her research interests are in multimedia signal
processing, data mining, and applied machine learning. Her recent projects
include multimedia analysis, social media tracking, visual semantics,
large-scale image and video search, geo-spatial data mining and urban event
modeling. Lexing's research has received five best student paper and best
paper awards in ACM MM 2002 and 2005, IEEE ICIP 2004, ACM/IEEE JCDL 2007 and
IEEE SOLI 2011. She was the 2005 IBM Research Josef Raviv Memorial Postdoc
fellow in Computer Science and Engineering. She was adjunct assistant
professor at Columbia University 2007-2009, she regularly serves on the
program and organizing committees of major multimedia conferences.
http://cecs.anu.edu.au/~xlx