June 2012 Newsletter June 2012 Newsletter


Welcome to the April edition of the IEEE-TCMC (Technical
Committee on Multimedia Computing) monthly mailing. TCMC membership
is officially determined by signing up with the
IEEE Computer Society either with your membership or later through:
TCMC home:
This month's topics include:
IEEE Computer Society: Technical Committee on Multimedia Computing 
Held in conjunction with ICME 2012
Date: 11 July 2012
Time: 11:50 - 13:10
Room: 112
IEEE T-SMC:B special issue
IEEE Trans. on Multimedia Special Issue
Computer Vision for RGB-D Sensors: Kinect and Its Applications
Special issue on IEEE Transactions on Systems, Man and Cybernetics - 
Part B: Cybernectics
Call for Paper:
Depth cameras have been exploited in computer vision for several years, 
but the high price and the poor quality of such devices have limited 
their applicability. With the invention of the low-cost Microsoft Kinect 
sensor, high-resolution depth and visual (RGB) sensing has become 
available for widespread use as an off-the-shelf technology. The 
complementary nature of the depth and visual (RGB) information in the 
Kinect sensor opens up new opportunities to solve fundamental problems 
in computer vision, including object and activity recognition, people 
tracking, 3D mapping and localization, etc. For a long time, researchers 
have been challenged by many problems such as detecting and identifying 
objects/humans in real-world situations. Traditional object segmentation 
and tracking algorithms based on RGB images are not always reliable 
when the environment is cluttered or the illumination conditions 
suddenly change, both of which occur frequently in a real-world setting. 
However, effectively combining depth and RGB data may provide new 
solutions to these problems, where object segmentation based on depth 
information is robust against environmental changes, and the accuracy 
of object tracking/identification can be improved by considering the 
depth, motion and appearance information of an object.
Freely available SDKs and posture trackers for the Kinect modeling 
environments further encourage new solutions to classic problems in 
computer vision. Compared to conventional computer vision systems 
(based on RGB images), systems using the Kinect sensor face a number of 
specific challenges, including characterization of objects based on the 
RGB-Depth images; correlation between per-pixel depth and RGB information 
when one of them is missing or corrupted; and, semantic linkage and 
decision making based on the fused information. Compared to stereo vision 
or ToF techniques exploiting other depth sensors (i.e., Bumblebee camera 
or PMD camera), the algorithms designed for the Kinect sensor need to 
solve additional problems, though the overall depth sensing quality of 
the Kinect sensor is much better than the other two. These particular 
problems embody the intelligent computing of per-pixel depth from a 
noisy and sparse depth point cloud; spatially calibrating and correlating 
the depth image with the RGB images; data mining from the inhomogeneous 
depth map; and, designing the illumination patterns for handling light 
interference effects.
This special issue is specifically dedicated to new algorithms and/or 
new applications based on the Kinect (or similar RGB-D) sensors. 
The key outcomes of the special issue will be a better understanding of: *
(1) the contributions of this new sensor within the computer vision community, 
(2) the possible applications of the Kinect sensor, and (3) the key 
challenges and solutions for research in this domain. Topics of interest 
include, but are not limited to:
* Object detection and recognition
* Segmentation and clustering
* Human pose estimation
* Human activity recognition and gesture recognition
* 3D scene reconstruction
* Human-computer interaction exploiting depth information
* Robotic vision based on Kinect
* Data mining based on RGB-D information
* Intelligent computing for generating dense depth map
* Decision making for fusing sensors
* Adaptive and learning techniques for a Kinect network (multi-Kinect)
* Transmission and visualization of 3D scenes
* 3D integration and understanding in multimedia applications
* Practical issues of deploying Kinect
* Social and ethical issues of Kinect sensing in public and private spaces
* Use of Kinect to acquire ground truth data in context-aware computing
* Industrial applications
Prospective authors should visit http://www.ieeesmc.org/publications/index.html 
for information on paper submission. Manuscripts should be submitted using 
the Manuscript Central system at
http://mc.manuscriptcentral.com/smcb-ieee. Please choose "SI: Vision for 
Kinect" as the manuscript type. Manuscripts will be peer reviewed according 
to the standard IEEE process.
Important Dates:
Submission of full papers 30 September 2012
Notification to authors 30 January 2013
Submission of revised papers 30 March 2013
Final decision on revised papers 30 May 2013
Tentative publication date Fourth quarter 2013
Guest Editors:
Ling Shao, The University of Sheffield, UK
Jungong Han, CWI, The Netherlands
Dong Xu, Nanyang Technological University, Singapore
Jamie Shotton, Microsoft Research Cambridge, UK
IEEE Transactions on Multimedia, Special Issue on  
Socio-Video Semantics
Important Dates 
Manuscript submission:  
Revised manuscript:  
Final acceptance:  
Final manuscript due:  
Tentative publication:  
October1, 2013 
February 1, 2014 
March 15, 2014 
May 1, 2014 
June 1, 2014 
October, 2014
Guest Editors
Dr. Cees G.M. Snoek, Univ. of Amsterdam, the Netherlands, cgmsnoek@uva.nl
Dr. Yu-Gang Jiang, Fudan University, China,  ygj@fudan.edu.cn  
Dr. Rong Yan, Facebook, USA, rongyan@fb.com
Dr. Jiebo Luo, University of Rochester, USA, jluo@cs.rochester.edu
Prof. Alberto Del Bimbo, Univ. degli Studi Firenze, Italy, delbimbo@dsi.unifi.it
All of a sudden video became social. In just five years, individual 
and mostly inactive consumers transformed into active and 
connected prosumers, revolutionaries even, who create, share, and comment 
on massive amounts of video artifacts all over the 
world wide web 2.0. In order to make sense of the massive amounts of video 
content, online social platforms rely on what other 
people say is in the image, which is known to be ambiguous, overly 
personalized, and limited. Hence, the lack of semantics 
currently associated with online video is seriously hampering retrieval, 
repurposing, and usage. In contrast, academic video 
sensemaking approaches rely on an analysis of the multimedia content which 
is important if only to verify what people have said
is factually in the video, or for (professional) archives which cannot be 
shared for crowdsourcing.  For sensemaking, exploiting 
the social multimedia context of video has  largely been ignored in the 
multimedia community. This special issue provides a 
unique opportunity for high-quality multidisciplinary papers connecting 
the social context of online video to video sensemaking. 
Researchers from industry are particularly encouraged to submit 
their work. The issue on socio-video semantics should set the 
scene for a big leap over the semantic gap. Topics of interest 
include (but are not limited to):
*? Socio-video content analysis 
* Cross-modal (social / visual / audio) socio-video content analysis 
* Contextual models for socio-video analysis 
* Novel features for socio-video analysis 
* Complex event recognition in socio-videos 
* Socio-video copy detection 
* Content-aware ads optimization in socio-video sharing sites 
* Efficient learning and mining algorithms for scalable socio-video content analysis 
?* Socio-video browsing and retrieval 
* Socio-video retrieval systems 
* Socio-video summarization 
* Recommender techniques for socio-video browsing 
* Mobile socio-video browsing and retrieval 
* User-centered interface and system design for socio-video browsing and retrieval 
?* Socio-video benchmark construction and open-source software 
* Benchmark database construction for socio-video semantic analysis 
* Ontology construction for socio-video semantic analysis 
* Open-source software libraries for socio-video analysis 
Submissions should follow the official guidelines set out by IEEE 
Transactions on Multimedia, which are located at 
Prospective authors should submit high quality, original 
manuscripts that have not appeared, nor are under consideration, in 
any other journals. Manuscripts should be submitted 
electronically through the online IEEE manuscript submission system at 
http://mc.manuscriptcentral.com/tmm-ieee/. All papers 
will be reviewed by at least three expert reviewers in relevant fields. 
Decision will be made based on the novel scientific and
technical contribution of the submissions and their suitability to the 
interests of this special issue.