The Second Workshop on Visual Content Identification and Search (VCIDS'11)

VCIDS'11 Technical Program

Technical Program - 11 July 2011 (VCIDS Workshop)

08:30 - 09:00

Conference Registration

Session 1

Room: JH1.03; Chair: Prof. Wenjun (Kevin) Zeng, Univ. of Missouri, USA

09:00 -09:10

Opening Address

09:10 -10:10

Keynote: Prof. Alan Smeaton, Dublin City University, Ireland

Title: Content Identification and Search in Visual Lifelogs

10:10 -10:30

Coffee Break

Session 2

Visual Content Identification and Search I
Room: JH1.03; Chair: Dr. Miroslaw Bober, Mitsubishi Electric R&D Center Europe

10:30 -10:50

Paper #248: P-VCD: A Pivot-Based Approach for Content-Based Video Copy Detection
Juan Manuel Barrios (University of Chile), Benjamin Bustos (University of Chile)

10:50 -11:10

Paper #72: An Efficient, Robust Video Fingerprinting System
Randall Cook (Gracenote, Inc.)

11:10 -11:30

Paper #139: Mobile Augmented Reality for Books on a Shelf
David Chen (Stanford University), Sam Tsai (Stanford University), Cheng-Hsin Hsu (Deutsche Telekom R&D Labs USA), Jatinder Singh (Deutsche Telekom R&D Labs USA), Bernd Girod (Stanford University)

11:30 -11:50

Paper #160: Statistical Modeling of Outliers for Fast Visual Search
Skjalg Lepsoy (Telecom Italia), Gianluca Francini (Telecom Italia), Giovanni Cordara (Telecom Italia), Pedro de Gusmão

11:50 -12:10

Paper #179: Directed Image Search with Local Parallel Feature Axes
Stefan Gumhold (TU Dresden), Marcel Spehr (CGV, TU DRESDEN)

12:10 -12:30

Paper #24: Extracting Multi-Size Local Descriptors by GPU Computing
Naoyuki Ichimura (AIST)

12:30 -13:30

Lunch

Session 3

Visual Content Identification and Search II
Room: JH1.03; Chair: Dr. Ton Kalker, Huawei Technologies, USA

13:30 -13:50

Paper #186: Album-based Object-centric Event Recognition
Shen-Fu Tsai (UIUC), Feng Tang (HP Labs), Thomas Huang (UIUC)

13:50 -14:10

Paper #62: A New ROI Grouping Schema for Automatic Image Annotation
Rami Albatal (LIG), Philippe Mulhem (Laboratoire Informatique de Grenoble (LIG)), Yves Chiaramella (Laboratoire Informatique de Grenoble (LIG))

14:10 -14:30

Paper #76: Detecting Highlights in Sports Videos: Cricket as a Test Case
Hao Tang (HP Labs), Vivek Kwatra (Google Research, USA), Mehmet Emre Sargin (Google), Ullas Gargi (Google)

14:30 -14:50

Paper #61: Credit-title Detection of Video Contents based on Estimation of Superimposed Region using Character Density Distribution
Ryota Mase (NEC), Ryoma Oami (NEC), Toshiyuki Nomura (NEC)

14:50 -15:10

Paper #216: Analyzing the Inner Workings of the Signature Quadratic Form Distance
Christian Beecks (RWTH Aachen University), Thomas Seidl (RWTH Aachen University)

15:10 -15:30

Paper #191: An Efficient Angle-based Shape Matching Approach towards Object Recognition
Zhiyuan Zhang (Shanghai Jiao Tong University), Aixin Zhang (Shanghai Jiao Tong University), Jianhua Li (Shanghai Jiao Tong University), Shenghong Li (Shanghai Jiao Tong University)

15:30 -16:00

Coffee Break

Session 4

Room: JH1.03; Moderator: Prof. Touradj Ebrihimi, EPFL, Switzerland

16:00-18:00

Panel Discussion - "From content moderation to content monetization -- unlocking the potential of visual content identification and search"

Panelists:

Dr. Miroslaw Bober, General Manager, Mitsubishi Electric R&D Center Europe
Randall Cook, Principal Engineer, Gracenote, Inc., USA
Dr. Ton Kalker, Vice President of Technology, Huawei Technologies, Santa Clara, USA
Dr. Alex Loui, Kodak, USA
Prof. Alan Smeaton, Dublin City University, Ireland