Search

Recent trends in activity recognition have shown that structured learning methods are useful in modeling spatio-temporal relationships, often termed as context in continuous videos. However, learning an efficient set of relationships or an ideal structure for representation of context in these videos still remains a challenging problem. While a continuous video consists of several activities, the contextual relationships between these activities are relatively sparse. We propose a method which aims to discover these sparse relationships using an L1-regularization based automatic structure discovery of a graphical model representing the video. We propose a 2-layered graphical model, where the lower level models feature information and the higher level models spatiotemporal context. The features are modeled using space-time interest points, while the relationships between activities are modeled using an undirected graphical model. Sparsity is imposed on the edges of the graph so as to model a sparse set of relationships. Experiments have been conducted on complex activity recognition datasets to demonstrate the superior performance of our approach in classification of continuous activities.

We present a work that explores the feasibility of automated face recognition technologies for analyzing identities in works of portraiture, and in the process provide additional evidence to settle some long-standing questions in art history. Works of portrait art bear the mark of visual interpretation of the artist. Moreover, the number of samples available to model these effects is often limited. From a set of portraiture of the Renaissance and Baroque periods, where the identities of subjects are known, we derive appropriate features that are based on domain knowledge of artistic renderings, and learn and validate statistical models for the distribution of the match and non-match scores, which we refer to as portrait feature space (PFS). Thereafter, we use this PFS on a number of cases that have been "open questions" to art historians. They are usually in the form of validating two portraits as belonging to the same person. Using statistical hypothesis tests on the PFS, we provide quantitative measures of similarity for each of these questions. It is, to the best of our knowledge, the first study that applies automated face recognition technologies to the analysis of portraits of multiple subjects in various forms - paintings, death masks, sculptures.

Renaissance portraits were depictions of some important royals of those times. Analysis of faces in these portraits can provide valuable dynastical information in addition to enriching personal details of the depicted sitter. Such studies can offer insights to the art-history community in understanding and linking personal histories. In particular, face recognition technologies can be useful for identifying subjects when there is ambiguity. However, portraits are subject to several complexities such as aesthetic sensibilities of the artist or social standing of the sitter. Thus, for robust automated face recognition, it becomes important to model the characteristics of the artist. In this paper, we focus on modeling the styles of artists by considering case studies involving Renaissance art-works. After a careful examination of artistic trends, we arrive at relevant features for analysis. From a set of instances known to match/not match, we learn distributions of match and non-match scores which we collectively refer to as the portrait feature space (PFS). Thereafter, using statistical permutation tests we learn which of the chosen features were emphasized in various works involving (a) same artist depicting same sitter, (b) same sitter but by different artists and (c) same artist but depicting different sitters. Finally, we show that the knowledge of these specific choices can provide valuable information regarding the sitter and/or artist.