Title of Accepted Paper, Poster, Panel, Abstract, Invited Talk  or Keynote


Opening Remark


Keynote Address
Session Chair: Benoit Huet (EURECOM, France)

9:05 – 10:00

Presenter: Shin’Ichi Sato (NII, Japan)

Title: Towards Mining Broadcast Video Archive by Latent Link Analysis

10:00 – 10:30

Coffee break


Session 1
Session Chair: Alexander Hauptmann (CMU, USA)

10 :30 - 10 :50

Commercial Film Detection and Identification Based on a Dual-Stage Temporal Recurrence Hashing Algorithm

Xiaomeng Wu (National Institute of Informatics, Japan), Narongsak Putpuek (Chulalongkorn University, Thailand) and Shin'ichi Satoh (National Institute of Informatics, Japan)

10 :50 - 11:10

A Large-Scale Performance Study of Cluster-Based High-Dimensional Indexing

Gylfi Gudmundsson (INRIA, France), Björn Jónsson (Reykjavík University, Iceland) and Laurent Amsaleg (IRISA-CNRS, France)

11:10 - 11:30

Optimizing Similarity-based Image Joins in a Multimedia Database

Harald Kosch (University of Passau, Germany)


Session 2
Session Chair: Ed Chang (Google Inc., P.R. China)

11:45 – 12:05

Towards Extensible Automatic Image Annotation with the Bag-of-Words Approach

Robert Nagy (University of Erlangen-Nürnberg, Germany) and Klaus Meyer-Wegener (University of Erlangen-Nürnberg, Germany)                               

12:05 - 12:25

(!) Timechange!

Incremental Multi-Classifier Learning Algorithm on Grid’5000 for Large Scale Image Annotation

Yubing Tong (University Joseph Fourier, France)

12:25 - 12:45

Weighting Bag-of-Visual-Words by SVM Kernel Optimization for Video Concept Detection

Feng Wang (East China Normal University, P.R. China) and Bernard Merialdo (EURECOM, France)

12:45 – 14:15

Lunch Break


Session 3
Session Chair: Tat-Seng Chua (NUS, SIngapore)

14:15 – 14:35

(!) Timechange!

An analysis of user behavior in online video streaming

Fan Qiu (Vanderbilt University, USA) and Yi Cui (Vanderbilt University, USA)

14:35 – 14:55

Automatic Image Annotation by Using Relevant Keywords Extracted from Auxiliary Text Documents

Ning Zhou (University of North Carolina at Charlotte, USA), Yi Shen (University of North Carolina at Charlotte, USA) and Jianping Fan (University of North Carolina at Charlotte, USA)

14:55 – 15:15

A Deep Model-based and Data-driven Hybrid Architecture for Image Annotation

Zhiyu Wang (Tsinghua University, P.R. China), Dingyin Xia (College of Computer Science, Zhejiang University, P.R. China) and Ed Chang (Google Inc., P.R. China)

15:15 – 15:35

Concept Detector Refinement Using Social Videos

Xueliang Liu (EURECOM, France) and Benoit Huet (EURECOM, France)

15:35 – 16:00

Coffee break

16:00 – 17:30

Panel: Very Large Scale Multimedia Corpus, Mining and Retrieval

Session Chair: Benoit Huet (EURECOM, France)

Participants: Shin’Ichi Sato (NII, Japan), Apostol Natsev (IBM T. J. Watson Research Center, USA), Ed Chang (Google Inc., P.R. China), Remi Landais (Exalead, France).