Proceedings ArticleDOI
Aiding face recognition with social context association rule based re-ranking
TLDR
The results show that association rules extracted from social context can be used to augment face recognition and improve the identification performance.Abstract:
Humans are very efficient at recognizing familiar face images even in challenging conditions. One reason for such capabilities is the ability to understand social context between individuals. Sometimes the identity of the person in a photo can be inferred based on the identity of other persons in the same photo, when some social context between them is known. This research presents an algorithm to utilize cooccurrence of individuals as the social context to improve face recognition. Association rule mining is utilized to infer multi-level social context among subjects from a large repository of social transactions. The results are demonstrated on the G-album and on the SN-collection pertaining to 4675 identities prepared by the authors from a social networking website. The results show that association rules extracted from social context can be used to augment face recognition and improve the identification performance.read more
Citations
More filters
Book ChapterDOI
Towards More Natural Social Interactions of Visually Impaired Persons
Sergio Carrato,Gianfranco Fenu,Eric Medvet,Enzo Mumolo,Felice Andrea Pellegrino,Giovanni Ramponi +5 more
TL;DR: A scenario in which a sequence of images is acquired and processed by a wearable device, and the basic tasks of detecting and recognizing people and their facial expression are considered.
Proceedings ArticleDOI
Harnessing social context for improved face recognition
TL;DR: Experimental results on two publicly available datasets show that social context information can improve face recognition and help bridge the gap between humans and machines in face recognition.
Proceedings ArticleDOI
DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification
TL;DR: In this paper , a re-ranking approach that compares two faces using the Earth Mover's Distance on the deep, spatial features of image patches is proposed. But, this approach suffers from poor out-of-distribution generalization to new types of images (e.g., when a query face is masked, cropped or rotated) not included in the training set or the gallery.
Proceedings ArticleDOI
Machine Learning for Social Behavior Understanding
TL;DR: An emerging person recognition approach based on the in-depth analysis of individuals' social behavior in order to enhance the performance of a traditional biometric system is discussed.
Proceedings ArticleDOI
Collaborative filtering motivated automatic photo tagging
TL;DR: A new method for photo tagging task, motivated by collaborative filtering technique, is proposed and a large-scale social network image dataset (SNRR-collection) is collected in this work.
References
More filters
Proceedings Article
Fast algorithms for mining association rules
TL;DR: Two new algorithms for solving thii problem that are fundamentally different from the known algorithms are presented and empirical evaluation shows that these algorithms outperform theknown algorithms by factors ranging from three for small problems to more than an order of magnitude for large problems.
Proceedings ArticleDOI
Rank aggregation methods for the Web
TL;DR: A set of techniques for the rank aggregation problem is developed and compared to that of well-known methods, to design rank aggregation techniques that can be used to combat spam in Web searches.
Proceedings ArticleDOI
Attribute and simile classifiers for face verification
TL;DR: Two novel methods for face verification using binary classifiers trained to recognize the presence or absence of describable aspects of visual appearance and a new data set of real-world images of public figures acquired from the internet.
Proceedings ArticleDOI
Context-based vision system for place and object recognition
TL;DR: A low-dimensional global image representation is presented that provides relevant information for place recognition and categorization, and it is shown how such contextual information introduces strong priors that simplify object recognition.
Proceedings ArticleDOI
Understanding images of groups of people
Andrew C. Gallagher,Tsuhan Chen +1 more
TL;DR: This paper introduced contextual features that encapsulate the group structure locally (for each person in the group), and globally (the overall structure of the group) to accomplish a variety of tasks, such as demographic recognition, calculating scene and camera parameters, and even event recognition.