Kernelized Covariance for Action Recognition

J. Cavazza, A. Zunino, M. San Biagio and V. Murino: "Kernelized Covariance for Action Recognition". ICPR 2016 PDF


The descriptive power of the covariance matrix is limited in capturing linear mutual dependencies between variables only. To solve this issue, we present a rigorous and principled mathematical pipeline to recover the kernel trick for computing the covariance matrix, enhancing it to model more complex, non-linear relationships conveyed by the raw data. Our proposed encoding (Kernelized-COV) generalizes the original covariance representation without compromising the efficiency of the computation. Despite its broad generability, the aforementioned paper applied Kernelized-COV to 3D action recognition from MoCap data.


A Game-Theoretic Probabilistic Approach for Detecting Conversational Groups

S. Vascon, E. Zemene, M. Cristani, H. Hung, M. Pelillo and V. Murino: "A Game-Theoretic Probabilistic Approach for Detecting Conversational Groups". ACCV 2014

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 which models the socio-psychological concept of an F-formation. Essentially, an F-formation defines some constraints on how subjects have to be mutually located and oriented. 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. Specifically, we propose two novel ways of handling the uncertainty in the position and orientation of the head of each individual with respect to the remaining members of the group in terms of tracking errors and the true body orientation. First, we use a novel representation of the affinity between candidate pairs by expressing the distance between distributions over the most plausible oriented region of attention. Additionally, we integrate temporal information over multiple frames while taking into account the social context established in previous frames. 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.

Multi-Link Analysis: Case-Control Brain Network Comparison via Sparse Connectivity Analysis

A. Crimi, L. Giancardo, F. Sanbataro, A. Gozzi, V. Murino, D. Sona


c fig0

Imaging neuroscience is currently pushing towards the analysis of the brain from a connectivity perspective, which is unveiling many insights into brain structure and functionality. Neuroscientists are often required to evaluate experimental effects in case-control on specimens with thousands connections. This software is based on an unsupervised machine-learning algorithm, which can capture the multivariate relationships that characterize two distinct groups of connectomes, thus allowing neuroscientists to immediately visualize only the sub-networks that contain information about differences between case and control group. The method exploits recent machine learning techniques which employ sparsity in order to deal with weighted network composed of hundreds of thousands of connections.


Heterogeneous Auto-Similarities of Characteristics (HASC): Exploiting Relational Information for Classification

M. San Biagio, M. Crocco, M. Cristani, S. Martelli and V. Murino: "Heterogeneous Auto-Similarities of Characteristics (HASC): Exploiting Relational Information for Classification". ICCV 2013

Capturing the essential characteristics of visual objects by considering how their features are inter-related is a recent philosophy of object classification. We embed this principle in a novel image descriptor, dubbed Heterogeneous Auto-Similarities of Characteristics (HASC). HASC is applied to heterogeneous dense features maps, encoding linear relations by covariances and nonlinear associations through information-theoretic measures such as mutual information and entropy. In this way, highly complex structural information can be expressed in a compact, scale invariant and robust manner.



IIT's website uses the following types of cookies: browsing/session, analytics, functional and third party cookies. Users can choose whether or not to accept the use of cookies and access the website. By clicking on "Further Information", the full information notice on the types of cookies will be displayed and you will be able to choose whether or not to accept them whilst browsing on the website
Further Information
Accept and close