Publications by Rita Cucchiara

In this paper we present a new method for head pose real-time estimation in ego-vision scenarios that is a key step in the understanding of social interactions. In order to robustly detect head under changing aspect ratio, scale and orientation we use and extend the Hough-Based Tracker which allows to follow simultaneously each subject in the scene. In an ego-vision scenario where a group interacts in a discussion, each subject's head orientation will be more likely to remain focused for a while on the person who has the floor. In order to encode this behavior we include a stateful Hidden Markov Model technique that enforces the predicted pose with the temporal coherence from a video sequence. We extensively test our approach on several indoor and outdoor ego-vision videos with high illumination variations showing its validity and outperforming other recent related state of the art approaches.

In this paper we propose an approach for Document Layout Analysis based on local correlation features. We identify and extract illustrations in digitized documents by learning the discriminative patterns of textual and pictorial regions. The proposal has been demonstrated to be effective on historical datasets and to outperform the state-of-the-art in presence of challenging documents with a large variety of pictorial elements.

Despite pattern recognition methods for human behavioral analysis has flourished in the last decade, animal behavioral analysis has been almost neglected. Those few approaches are mostly focused on preserving livestock economic value while attention on the welfare of companion animals, like dogs, is now emerging as a social need. In this work, following the analogy with human behavior recognition, we propose a system for recognizing body parts of dogs kept in pens. We decide to adopt both 2D and 3D features in order to obtain a rich description of the dog model. Images are acquired using the Microsoft Kinect to capture the depth map images of the dog. Upon depth maps a Structural Support Vector Machine (SSVM) is employed to identify the body parts using both 3D features and 2D images. The proposal relies on a kernelized discriminative structural classificator specifically tailored for dogs independently from the size and breed. The classification is performed in an online fashion using the LaRank optimization technique to obtaining real time performances. Promising results have emerged during the experimental evaluation carried out at a dog shelter, managed by IZSAM, in Teramo, Italy.

In this paper we address the task of learning how to segment a particular class of objects, by means of a training set of images and their segmentations. In particular we propose a method to overcome the extremely high training time of a previously proposed solution to this problem, Kernelized Structural Support Vector Machines. We employ a one-class SVM working with joint kernels to robustly learn significant support vectors (representative image-mask pairs) and accordingly weight them to build a suitable energy function for the graph cut framework. We report results obtained on two public datasets and a comparison of training times on different training set sizes.

In this paper we propose to extend the well known graph cut segmentation framework by learning superpixel relations and use them to weight superpixel-to-superpixel edges in a superpixel graph. Adjacent superpixel-pairs are analyzed to build an object boundary model, able to discriminate between superpixel-pairs belonging to the same object or placed on the edge between the foreground object and the background. Several superpixel-pair features are investigated and exploited to build a non-linear SVM to learn object boundary appearance. The adoption of this modified graph cut enhances the performance of a previously proposed segmentation method on two publicly available datasets, reaching state-of-the-art results.

In this paper we propose a multimedia solution for the interactive exploration of illuminated manuscripts. We leveraged on the joint exploitation of content-based image retrieval and relevance feedback to provide an effective mechanism to navigate through the manuscript and add custom knowledge in the form of tags. The similarity retrieval between miniature illustrations is based on covariance descriptors, integrating color, spatial and gradient information. The proposed relevance feedback technique, namely Query Remapping Feature Space Warping, accounts for the user’s opinions by accordingly warping the data points. This is obtained by means of a remapping strategy (from the Riemannian space where covariance matrices lie, referring back to Euclidean space) useful to boost the retrieval performance. Experiments are reported to show the quality of the proposal. Moreover, the complete prototype with user interaction, as already showcased at museums and exhibitions, is presented.

Novelty detection is a crucial task in the development of autonomous vision systems. It aims at detecting if samples do not conform with the learnt models. In this paper, we consider the problem of detecting novelty in object recognition problems in which the set of object classes are grouped to form a semantic hierarchy. We follow the idea that, within a semantic hierarchy, novel samples can be defined as samples whose categorization at a specific level contrasts with the categorization at a more general level. This measure indicates if a sample is novel and, in that case, if it is likely to belong to a novel broad category or to a novel sub-category. We present an evaluation of this approach on two hierarchical subsets of the Caltech256 objects dataset and on the SUN scenes dataset, with different classification schemes. We obtain an improvement over Weinshall et al. and show that it is possible to bypass their normalisation heuristic. We demonstrate that this approach achieves good novelty detection rates as far as the conceptual taxonomy is congruent with the visual hierarchy, but tends to fail if this assumption is not satisfied. Copyright 2014 ACM.