Prof Andrea Cavallaro is one of the organisers of the Video Analytics for Audience Measurement in Retail and Digital Signage (VAAM) workshop in conjunction with the 22nd International Conference on Pattern Recognition, Stockholm, Sweden, 24 August 2014.
The retail and advertisement industries are becoming more pervasive, with the need of measuring engagement of viewers/shoppers with newly launched campaigns. Video analytics may help understanding the effectiveness of the branded message by studying and measuring public opinion and polling, geographical concentration of conversation of viewers. To this aim, computer vision and pattern recognition technologies will play an important role in audience measurement for their capability of understanding from visual cues demographics, gaze, dwell time, affect state and group proxemics, where low spatial-resolution, pose changes, occlusions, illumination changes, large variability of intra-class female age and ethnicity cohorts are critical aspects for recognition. The aim of this workshop is to provide an overview of state of the art methods for audience measurements in retail and Digital Signage, end-users attraction, and stimulate the creation of appropriate benchmark dataset to be used as reference for the development of novel audience measurement algorithms. Papers are invited under the following topics (but not limited to): Dwell time estimation Gender recognition Age and Age group estimation Behaviour analysis People counting in multi-camera network People recurrence in long time window Ethnicity recognition Emotion analysis Free eye gaze estimation Group of related people: detection, tracking and behaviour analysis Path optimization and queue management in the point of sale Annotated Dataset proposal Privacy preserving in audience Measurement Other visual cues for customer profiling