Alberto Del Bimbo

Semantic annotation of sports videos

Taking into consideration the unique qualities of sports videos, we propose a system that semantically annotates them at different layers of semantic significance, using different elements of visual content. We decompose each shot into its visual and graphic content elements and, by combining several different low-level visual primitives, capture the semantic content at a higher level of significance.

Content-based retrieval of 3D models

In the past few years, there has been an increasing availability of technologies for the acquisition of digital 3D models of real objects and the consequent use of these models in a variety of applications, in medicine, engineering, and cultural heritage. In this framework, content-based retrieval of 3D objects is becoming an important subject of research, and finding adequate descriptors to capture global or local characteristics of the shape has become one of the main investigation goals. In this article, we present a comparative analysis of a few different solutions for description and retrieval by similarity of 3D models that are representative of the principal classes of approaches proposed. We have developed an experimental analysis by comparing these methods according to their robustness to deformations, the ability to capture an objects structural complexity, and the resolution at which models are considered.

Person Re-Identification by Iterative Re-Weighted Sparse Ranking

In this paper we introduce a method for person re-identification based on discriminative, sparse basis expansions of targets in terms of a labeled gallery of known individuals. We propose an iterative extension to sparse discriminative classifiers capable of ranking many candidate targets. The approach makes use of soft- and hard- re-weighting to redistribute energy among the most relevant contributing elements and to ensure that the best candidates are ranked at each iteration. Our approach also leverages a novel visual descriptor which we show to be discriminative while remaining robust to pose and illumination variations. An extensive comparative evaluation is given demonstrating that our approach achieves state-of-the-art performance on single- and multi-shot person re-identification scenarios on the VIPeR, i-LIDS, ETHZ, and CAVIAR4REID datasets. The combination of our descriptor and iterative sparse basis expansion improves state-of-the-art rank-1 performance by six percentage points on VIPeR and by 20 on CAVIAR4REID compared to other methods with a single gallery image per person. With multiple gallery and probe images per person our approach improves by 17 percentage points the state-of-the-art on i-LIDS and by 72 on CAVIAR4REID at rank-1. The approach is also quite efficient, capable of single-shot person re-identification over galleries containing hundreds of individuals at about 30 re-identifications per second.

Event detection and recognition for semantic annotation of video

Research on methods for detection and recognition of events and actions in videos is receiving an increasing attention from the scientific community, because of its relevance for many applications, from semantic video indexing to intelligent video surveillance systems and advanced human-computer interaction interfaces. Event detection and recognition requires to consider the temporal aspect of video, either at the low-level with appropriate features, or at a higher-level with models and classifiers than can represent time. In this paper we survey the field of event recognition, from interest point detectors and descriptors, to event modelling techniques and knowledge management technologies. We provide an overview of the methods, categorising them according to video production methods and video domains, and according to types of events and actions that are typical of these domains.

Copy-move forgery detection and localization by means of robust clustering with J-Linkage

Understanding if a digital image is authentic or not, is a key purpose of image forensics. There are several different tampering attacks but, surely, one of the most common and immediate one is copy-move. A recent and effective approach for detecting copy-move forgeries is to use local visual features such as SIFT. In this kind of methods, SIFT matching is often followed by a clustering procedure to group keypoints that are spatially close. Often, this procedure could be unsatisfactory, in particular in those cases in which the copied patch contains pixels that are spatially very distant among them, and when the pasted area is near to the original source. In such cases, a better estimation of the cloned area is necessary in order to obtain an accurate forgery localization. In this paper a novel approach is presented for copy-move forgery detection and localization based on the JLinkage algorithm, which performs a robust clustering in the space of the geometric transformation. Experimental results, carried out on different datasets, show that the proposed method outperforms other similar state-of-the-art techniques both in terms of copy-move forgery detection reliability and of precision in the manipulated patch localization.

3-D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold

Recognizing human actions in 3-D video sequences is an important open problem that is currently at the heart of many research domains including surveillance, natural interfaces and rehabilitation. However, the design and development of models for action recognition that are both accurate and efficient is a challenging task due to the variability of the human pose, clothing and appearance. In this paper, we propose a new framework to extract a compact representation of a human action captured through a depth sensor, and enable accurate action recognition. The proposed solution develops on fitting a human skeleton model to acquired data so as to represent the 3-D coordinates of the joints and their change over time as a trajectory in a suitable action space. Thanks to such a 3-D joint-based framework, the proposed solution is capable to capture both the shape and the dynamics of the human body, simultaneously. The action recognition problem is then formulated as the problem of computing the similarity between the shape of trajectories in a Riemannian manifold. Classification using k-nearest neighbors is finally performed on this manifold taking advantage of Riemannian geometry in the open curve shape space. Experiments are carried out on four representative benchmarks to demonstrate the potential of the proposed solution in terms of accuracy/latency for a low-latency action recognition. Comparative results with state-of-the-art methods are reported.

Recognizing Actions from Depth Cameras as Weakly Aligned Multi-part Bag-of-Poses

Recently released depth cameras provide effective estimation of 3D positions of skeletal joints in temporal sequences of depth maps. In this work, we propose an efficient yet effective method to recognize human actions based on the positions of joints. First, the body skeleton is decomposed in a set of kinematic chains, and the position of each joint is expressed in a locally defined reference system which makes the coordinates invariant to body translations and rotations. A multi-part bag-of-poses approach is then defined, which permits the separate alignment of body parts through a nearest-neighbor classification. Experiments conducted on the Florence 3D Action dataset and the MSR Daily Activity dataset show promising results.

Multi-scale and real-time non-parametric approach for anomaly detection and localization

In this paper we propose an approach for anomaly detection and localization, in video surveillance applications, based on spatio-temporal features that capture scene dynamic statistics together with appearance. Real-time anomaly detection is performed with an unsupervised approach using a non-parametric modeling, evaluating directly multi-scale local descriptor statistics. A method to update scene statistics is also proposed, to deal with the scene changes that typically occur in a real-world setting. The proposed approach has been tested on publicly available datasets, to evaluate anomaly detection and localization, and outperforms other state-of-the-art real-time approaches.

A Set of Selected SIFT Features for 3D Facial Expression Recognition

In this paper, the problem of person-independent facial expression recognition is addressed on 3D shapes. To this end, an original approach is proposed that computes SIFT descriptors on a set of facial landmarks of depth images, and then selects the subset of most relevant features. Using SVM classification of the selected features, an average recognition rate of 77.5% on the BU-3DFE database has been obtained. Comparative evaluation on a common experimental setup, shows that our solution is able to obtain state of the art results.

Content-Based Retrieval of 3-D Objects Using Spin Image Signatures

Retrieval by content of 3D models is becoming more and more important due to the advancements in 3D hardware and software technologies for acquisition, authoring and display of 3D objects, their ever-increasing availability at affordable costs, and the establishments of open standards for 3D data interchange. In this paper, we present a new method, referred to as spin image signatures, that develops on the original spin images approach, with adaptations to support effective retrieval by content. According to the method proposed, a set of spin images is derived for each model, to obtain a view-independent description of its 3D shape and a signature is evaluated for each spin image in the set. Clustering is hence performed on the set of spin image signatures to obtain a compact representation. Experimental results are presented, showing the effectiveness of the spin image signatures method for retrieval, also in comparison with other methods, and its sensitivity to model deformations