1st ACM International Workshop on

Interactive Multimedia for Consumer Electronics (IMCE 2009)

In association with ACM Multimedia 2009

Beijing, China

23 October, 2009

 
Workshop Program
 
9:00-10:00 Keynote Speech: Multimedia Experience on a Web-Connected CE Device
Dr. Qian Lin, HP Labs
 
Abstract: Consumer electronic devices such as TVs and DVD players used to be stand alone devices that perform a single function. In the last few years, they became increasingly part of an eco-system where they 
are connected to content and application services on the web. Multimedia content and application services, in particular, are a core part of almost all consumer electronics devices. In this talk, we will first discuss 
the overall trend toward the connected devices, and multimedia research opportunities that open up as a result. We will then look into the application area of digital photography, and use Magic Photobook as an 
example of how we can create a cloud-based multimedia service that can support multiple CE devices in the eco-system. We will demonstrate Magic Photobook prototypes, and discuss how various research approaches 
in content analysis, flexible layout, image editing, and UI and interaction have to come together for a compelling solution. Finally, we will share our learning of building up the service in a research environment.
 
Bio: Dr. Qian Lin is director for the Multimedia Interaction and Understanding Lab in HP Labs. The lab focuses on research in multimedia analysis, image processing, and design automation technologies for search and 
organization of multimedia content, web-based multimedia services, and personalized publishing. Dr. Lin and her team contributed a number of key technologies to HP products, including several Real Life Technologies 
for cameras, image processing and compression for imaging pipelines in printers and MFPs, and photo layout and video sharing for retail photo kiosks and Snapfish online services. The Pluribus Interactive camera-projector 
system developed by researchers in her lab was considered to be “one of five top innovations that will reinvent computing” by PC Magazine in 2008. Recently, Dr. Lin’s team launched the Snapfish Lab (www.snapfishlab.com) 
website for beta-testing Labs technologies. Dr. Lin joined Hewlett-Packard Company in 1992. She received her BS from Xi’an Jiaotong University in China, her MSEE from Purdue University, and her PhD in 
Electrical Engineering from Stanford University. Dr. Lin is inventor/co-inventor for 30 issued patents. She is the chair for the Conference on Printing and Imaging in a Web 2.0 World in IS&T/SPIE’s Electronic Imaging 
Symposium in 2010.
 
10:00-10:30 Coffee Break
 
10:30-11:45 Oral Session I: Activity and Gesture
Toward Physical Activity Diary: Motion Recognition Using Simple Acceleration Features with Mobile Phones
Jun Yang
Finger Gesture Recognition through Sweep Sensor
Pong Yuen, W Zou, S Zhang, Kelvin Wong, and Hoson Lam
Utilising Contextual Memory Retrieval Cues and the Ubiquity of the Cell Phone to Assist Individuals Review their Lifelogged Physiological Activities
Aiden Doherty, Kristin Tolle, and Alan Smeaton
 
11:45-12:30 Poster Session
Key Frame Vector and Its Application to Shot Retrieval
Yue Gao, Jinhui Tang, Xudong Xie, and Tat-Seng Chua
A Framework for Robust Feature Selection for Real-time Fashion Style Recommendation
Xiaofei Chao, Mark Huiskes, Tommaso Gritti, and Calina Ciuhu
Spatio-temporal Shape Contexts for Human Action Retrieval
Ling Shao and Yuanjia Du
A New Gaussian Mixture Conditional Random Field Model for Indoor Image Labeling
Xiaofeng WANG and Xiao-Ping Zhang
Scene Classification Using pLSA with Visterm Spatial Location
Sunki Kim
Structured design for Resizable Background Art
Hui Chao, Daniel Tretter, and Xuemei Zhang
Video Shots Retrieval Using Local Invariant Features
Yuanjia Du and Ling Shao
 
12:30-14:00 Lunch Break
 
14:00-15:00 Keynote Speech: Natural Interactivity 
Prof. Alberto Del Bimbo, University of Florence
 
15:00-15:30 Poster Session (Cont.)
 
15:30-16:00 Coffee Break
 
16:00-17:40 Oral Session II: Multimedia Content Analysis
Toward Fully Automated Face Pose Estimation
Tommaso Gritti
Efficient Object Localization with Gaussianized Vector Representation
Xiaodan Zhuang, Xi Zhou, Mark Hasegawa-Johnson, and Thomas Huang
Evolving Virtual Contents with Interactions in Videos
Chia-Hu Chang, Ming-Che Chiang, and Ja-Ling Wu
Upscaling Faces for Recognition Systems Using Trained Filters
Jun Rong, Tommaso Gritti, and Caifeng Shan
 

Call for Papers

With the development of silicon technologies, consumer electronics devices, such as personal computers, HDTV, mobile phones, digital cameras and game consoles, have become ubiquitous for people daily life. These devices

can provide multimedia sources for entertainment, communication, and so on. To interact with these equipments, consumers currently rely on devices such as remote controls, keyboards or control panels, which are often

inconvenient, ambiguous and non-interactive. How to design user interfaces of CE products that enable natural, intuitive and fun interaction is one of the main challenges the CE industry is facing. Many companies and

institutes are working on the advanced user interfaces.

User interface technologies have been studied in various disciplines for decades. Considering that modern CE products are usually supplied with both microphones and cameras, how to employ both audio and visual information

for interactive multimedia has recently received much attention in both academia and industry. But interactive multimedia is still an under-explored field. Many challenges exist when moving to multimodal interaction: for

example, how to annotate and search huge data acquired by using multiple sensors, especially in the unconstrained end-user environments? how to effectively extract and select representative multimedia features for human behavior

recognition? and how to select the fusion strategy of multimodal data for a given application? To address these challenges, we must adapt the existing approaches or find new solutions suitable for multimedia interaction.

This workshop will bring together researchers from both academia and industry in domains including computer vision, machine learning, audio and speech processing, communications, artificial intelligence and media technology to

share and discuss recent advances in interactive user interfaces and multimedia applications.

Topics related to interactive multimedia for consumer electronics include, but are not limited to,

• Multimedia description and markup
• Multimedia representation and annotation
• Multimedia search and retrieval
• Presence and environment sensing
• Face detection, recognition, and tracking
• Hand detection, tracking, and recognition
• Facial expression recognition
• Emotion/mood recognition
• Gesture/action/activity recognition
• Audio-visual recognition and interaction
• Novel interaction (accelerometer, touch screen, haptics, voice)
• Multimodal data modeling and fusion
• Multimedia content adaptation
• Context-aware services

Workshop Chairs

• Ling Shao, Philips Research, The Netherlands
• Caifeng Shan, Philips Research, The Netherlands
• Jiebo Luo, Kodak Research Laboratories, USA
• Minoru Etoh, NTT DoCoMo Research Laboratories, Japan

PC Members

• Alberto Del Bimbo, University of Firenze, Italy
• Xavier Binefa, University of Barcelona, Spain
• Andrea Cavallaro, Queen Mary University of London, UK
• Wei-Chao Chen, Nokia Research Center, USA
• Berna Erol, Ricoh Innovations, USA
• Yun (Raymond) Fu, BBN Technologies, USA
• Ling Guan, Ryerson University, Canada
• Jungong Han, Eindhoven University of Technology, The Netherlands
• Aki Harma, Philips Research, The Netherlands
• Mark Huiskes, Leiden University, The Netherlands
• Winston Hsu, National Taiwan University, Taiwan
• Alejandro Jaimes, Telefonica I+D, Spain
• Tae-Kyun Kim, Cambridge University, UK
• Rainer Lienhart, University of Augsberg, Germany
• Xuelong Li, University of London, UK
• Qian Lin, HP Labs, USA
• Alexander C. Loui, Kodak Research Labs, USA
• Xiaoming Liu, GE Global Research, USA
• Tao Mei, Microsoft Research Asia, China
• Paul Miller, Queen’s University Belfast, UK
• Anton Nijholt, University of Twente, The Netherlands
• Jean-Marc Odobez, IDIAP Research Institute, Switzerland
• Ryuzo Okada, Toshiba Corporate Research and Development Center, Japan
• Yoichi Sato, University of Tokyo, Japan
• Dacheng Tao, Nanyang Technological University, Singapore
• Qi Tian, Microsoft Research Asia, China
• Ning Xu, Samsung

Important dates

Submission deadline: July 6, 2009

Notification of acceptance: July 20, 2009

Camera-ready due: July 24, 2009

Workshop: October 23, 2009

Paper Submission

• In submitting a manuscript to this workshop, the authors acknowledge that no paper substantially similar in content has been submitted to another conference, workshop, or journal.
• Full papers may be up to 8 pages in length. All papers must follow the standard ACM style guidelines and must be submitted in PDF format using the EDAS system. The review process will be double-blind.

Review and publication

• Each submission will be reviewed by at least three reviewers from PC members and external reviewers for originality, significance, clarity, soundness, relevance and technical contents.
• Accepted papers will be published by ACM in the workshop proceedings together with the ACM Multimedia 2009 proceedings. Extended versions of accepted papers will be invited to submit to an edited book or a

special issue of a top journal.

Registration
Please see details at http://www.acmmm09.org/Registration.aspx.
 
Contact
Any information or inquiries regarding the workshop can be forwarded to: 
<l [dot] shao [at] philips [dot] com> or
<caifeng [dot] shan [at] gmail [dot] com>.