A standing conversational group (also known as F-formation) occurs when two or more people sustain a social interaction, such as chatting at a cocktail party. Detecting such interactions in images or videos is of fundamental importance in many contexts, like surveillance, social signal processing, social robotics or activity classification. This paper presents an approach to this problem by modeling the socio-psychological concept of an F-formation and the biological constraints of social attention. Essentially, an F-formation defines some constraints on how subjects have to be mutually located and oriented while the biological constraints defines the plausible zone in which persons can interact. We develop a game-theoretic framework embedding these constraints, which is supported by a statistical modeling of the uncertainty associated with the position and orientation of people. First, we use a novel representation of the affinity between pairs of people expressed as a distance between distributions over the most plausible oriented region of attention.Additionally, we integrate temporal information over multiple frames to smooth noisy head orientation and pose estimates, solve ambiguous situations and establish a more precise social context. We do this in a principled way by using recent notions from multi-payoff evolutionary game theory. Experiments on several benchmark datasets consistently show the superiority of the proposed approach over state of the art and its robustness under severe noise conditions.Author has been partially supported by the European Commission under contract number FP7-ICT-600877 (SPENCER) and is affiliated with the Delft Data Science consortium.

No abstract

Abstract. Clustering algorithms are largely adopted in security applications as a vehicle to detect malicious activities, although few attention has been paid on preventing deliberate attacks from subverting the clustering process itself. Recent work has introduced a methodology for the security analysis of data clustering in adversarial settings, aimed to identify potential attacks against clustering algorithms and to evaluate their impact. The authors have shown that single-linkage hierarchical clustering can be severely affected by the presence of a very small fraction of carefully-crafted poisoning attacks into the input data, highlighting that the clustering algorithm may be itself the weakest link in a security system. In this paper, we extend this analysis to the case of complete-linkage hierarchical clustering by devising an ad hoc poisoning attack. We verify its effectiveness on artificial data and on application examples related to the clustering of malware and handwritten digits.

Following recent technological advances there is a growing interest in building non-intrusive methods that help us communicate with computing devices. In this regard, accurate information from eye is a promising input medium between a user and computing devices. In this paper we propose a method that captures the degree of eye closeness. Although many methods exist for detection of eyelid openness, they are inherently unable to satisfactorily perform in real world applications. Detailed eye state estimation is more important, in extracting meaningful information, than estimating whether eyes are open or closed. However, learning reliable eye state estimator requires accurate annotations which is cost prohibitive. In this work, we leverage synthetic face images which can be generated via computer graphics rendering techniques and automatically annotated with different levels of eye openness. These synthesized training data images, however, have a domain shift from real-world data. To alleviate this issue, we propose a weakly-supervised method which utilizes the accurate annotation from the synthetic data set, to learn accurate degree of eye openness, and the weakly labeled (open or closed) real world eye data set to control the domain shift. We introduce a data set of 1.3M synthetic face images with detail eye openness and eye gaze information, and 21k real-world images with open/closed annotation. The dataset will be released online upon acceptance. Extensive experiments validate the effectiveness of the proposed approach.

No abstract