Mining Near-duplicate Graph for Cluster-based Reranking of Web Video Search Results

Speaker:	Dr. Hengtao SHEN
		University of Queensland

Title:		"Mining Near-duplicate Graph for Cluster-based
		 Reranking of Web Video Search Results"

Date:		Wednesday, 13 January, 2010

Time:		2:00pm - 3:00pm

Venue:		Room 3412 (via lifts 17/18), HKUST

Abstract:

As the mainstream video content is moving to the Web, finding relevant
videos from the Web has been in an urgent demand. Most available Web video
search engines perform text-based search, which often return some noisy
results on the top of the ranking list. Recently, video search reranking
has been an effective mechanism to improve the initial text-based ranking
list by incorporating visual consistency among the result videos. While
existing methods attempt to rerank all the individual result videos, they
suffer from several drawbacks. In this paper, we propose a new video
reranking paradigm called cluster-based video reranking (CVR). The idea is
to first construct a video near-duplicate graph representing the visual
similarity relationship among videos, followed by identifying the
near-duplicate clusters from the video near-duplicate graph, then rank the
obtained near-duplicate clusters based on cluster properties and
inter-cluster links, and finally for each ranked cluster a representative
video is selected and returned. Comparing to existing methods, the new CVR
ranks clusters and exhibits several advantages, including superior
reranking by utilizing more reliable cluster properties, fast reranking on
a small number of clusters, diverse and representative results.
Particularly, we formulate the near-duplicate cluster identification as a
novel maximal cohesive subgraph mining problem. By leveraging the designed
cluster scoring properties indicating cluster's importance and quality,
random walk is applied over the near-duplicate cluster graph to rank
clusters. An extensive evaluation study proves the novelty and superiority
of our proposals over existing methods.


*********************
Biography:

Heng Tao Shen is a Reader in School of ITEE at The University of
Queensland. He obtained his BSc (with 1st class Honours) and PhD from
Department of Computer Science, National University of Singapore in 2000
and 2004 respectively, then joined The University of Queensland as a
Lecturer in June 2004 and Senior Lecturer in March 2007. His research
interests include Multimedia/Mobile/Web Search, Database Management,
P2P/Cloud Computing, etc. Heng Tao has published and served on program
committees in most prestigious international publication venues of
interests, such as ACM SIGMOD, ACM Multimedia, VLDB, ICDE, etc. He is the
winner of CORE Australasia *Chris Wallace award* 2009 for outstanding
research contribution in the field of computer science.  The prize was
awarded to an academic for research undertaken within a university or
research institution in Australia or New Zealand for a notable
breakthrough or a contribution of particular significance.