WSGaitAction 2014 - Workshop on Human Gait and Action Analysis in the Wild: Challenges and Applications

Human gait analysis and its more general field on human action analysis have progressed for over decades in terms of theory, algorithms and applications, but not without limitation. Significant challenges are imposed to the current work when gait and action analysis is carried out in the wild. Gait and action analysis in the wild connotes more general analysis and is required to tolerate the various factors enforced by the uncontrolled environment and the uncertainties caused by the uncooperative human objects. Tackling these challenges will further boost the relevant applications on security surveillance, monitoring, human-computer interaction and multimedia. This workshop intends to be positioned at the frontier of human gait and action analysis research focusing on the challenges raised by the practical environment i.e. the wild. It will give a comprehensive discussion on the synergy between gait analysis and general action analysis. It will showcase the most excellent and advanced work underway at academic, industry and private research organizations as well as government labs.
Topics of interest include, but are not limited to:
Gait and action information modelling: viewing-angle change, posture variance, body part occlusion, noisy background, speed variance
Gait and action matching from only a few examples
Fusion-based approaches for gait and action analysis
Gait/Action detection: methods for identifying the spatiotemporal location of gait/actions in a video.
Video enhancement for gait biometrics and action analysis
Gender and age recognition through gait and action analysis
Gait biometrics system: gait anti-spoofing, new sensing technologies e.g. 3D, RGB-D, wireless sensor network
Public dataset and performance baseline establishments
Gait and action analysis for person re-identification/multi-camera tracking
Application of gait and action analysis in the wild: visual surveillance, human-centric activity/event detection, content-based video retrieval, human?computer interaction, clinical gait analysis and gait rehabilitation
Authors are invited to submit a full paper according to the guidelines available on the ACCV2014 conference website (at most 12 pages in the Lecture Notes in Computer Science (LNCS) style). Submitted papers will be reviewed by the workshop program committee in a double blind manner. Only electronic submissions will be accepted. In submitting a manuscript to this workshop, the authors acknowledge that no paper substantially similar in content has been submitted to another conference or workshop during the review period. Accepted papers must be registered and presented; otherwise they will not be included in the workshop proceedings. The proceedings will be published by Springer in the Lecture Notes in Computer Science (LNCS) series.
Special announcement from ACCV2014 Organizing Committee on main conference and workshop paper submission
ACCV2014 will continue the "fall back" strategy used successfully in ACCV2012, which can connect some rejected main conference papers to appropriate workshops. The papers rejected by the main conference but connected to a workshop by the author(s) will be automatically passed to the workshop organizers, together with the main conference review comments. The workshop organizers will see the paper and the reviews, based on which they can decide whether the paper can be accepted or not by the workshop.
For this purpose, when potential ACCV2014 authors submit a paper to the main conference, they will be allowed to select a workshop as a “backup” option in case that the if paper is not accepted by the main conference.
Contact
Qiang.Wu-AT-uts.edu.au