HIS 2016 - Workshop on Human Identification for Surveillance (HIS): Methods & Applications

Human (re)identification is a critical process for tracking, understanding a person’s activity and security authentication in a large space monitored by a camera network. Great progress has been made in this area, focusing on heterogeneous cues (face, body (2D appearance and 3D volume), other unimodal biometrics such as finger and palm, gait, behavioral cues in general) which do not require user’s collaboration. However, this problem is far from being completely solved, particularly in real-world applications under uncontrolled environments, where a large number of factors hinder the identification performance, including lighting variations, different types of occlusion, large pose and view change.
The mission of the workshop is to explore the cutting edge research in non-collaborative (re)identification, with a particular emphasis on the fusion of different modalities. For example, the face recognition and the re-identification communities, even though they share many objectives, they rarely have interacted to hybridize novel recognition applications, where both the biometric patterns (face and body) can be jointly exploited. This holds true also for the communities of gait recognition and body re-identification, thermal body recognition, visual body recognition and other biometrics cues such as Iris Recognition at a distance. The HIS workshop, in this sense, will be highly interdisciplinary, encouraging papers (even preliminary), where the modality fusion plays a primary role.
In addition, the HIS greatly relies on the development of feature and similarity learning strategy. Therefore, the HIS workshop also aims to explore recent progress in feature and similarity learning (distance metric learning) for identification. It has been observed in recent years that the (re-)identification performance can be largely improved when a robust feature representation or an appropriate distance/similarity function has been learned. In this aspect, this workshop will help the community to better understand the challenges and opportunities of feature and similarity learning techniques and their applications to (re-)identification for the next few years.
Topics
Topics of interest include, but are not limited to: 1. Face, Finger, Iris, Palm Recognition
2. Person Re-identification
3. People Detection, Tracking, and Gait analysis
4. Novel biometrics sensing methods and Soft Biometrics
5. Feature Learning for Biometrics Recognition
6. Similarity Learning (/Distance Metric Learning) for Biometrics Recognition
7. Human identification with multiple cues and multi-modality fusion
8. Large scale search and matching for identification
9. Transfer Learning for visual surveillance
10. Performance modeling, prediction and evaluation of identification/biometrics systems
11. Security improvement assessment for multi-identification/biometrics systems