Correlation filters are special classifiers designed for shift-invariant object recognition, which are robust to pattern distortions. The recent literature shows that combining a set of sub-filters trained based on a single or a small group of images obtains the best performance. The idea is equivalent to estimating variable distribution based on the data sampling (bagging), which can be interpreted as finding solutions (variable distribution approximation) directly from sampled data space. However, this methodology fails to account for the variations existed in the data. In this paper, we introduce an intermediate step-solution sampling-after the data sampling step to form a subspace, in which an optimal solution can be estimated. More specifically, we propose a new method, named latent constrained correlation filters (LCCF), by mapping the correlation filters to a given latent subspace, and develop a new learning framework in the latent subspace that embeds distribution-related constraints into the original problem. To solve the optimization problem, we introduce a subspace-based alternating direction method of multipliers, which is proven to converge at the saddle point. Our approach is successfully applied to three different tasks, including eye localization, car detection, and object tracking. Extensive experiments demonstrate that LCCF outperforms the state-of-the-art methods.11.

Flickr allows its users to tag the pictures they like as “favorite”. As a result, many users of the popular photo-sharing platform produce galleries of favorite pictures. This article proposes new approaches, based on Computational Aesthetics, capable to infer the personality traits of Flickr users from the galleries above. In particular, the approaches map low-level features extracted from the pictures into numerical scores corresponding to the Big-Five Traits, both self-assessed and attributed. The experiments were performed over 60,000 pictures tagged as favorite by 300 users (the PsychoFlickr Corpus). The results show that it is possible to predict beyond chance both self-assessed and attributed traits. In line with the state-of-the-art of Personality Computing, these latter are predicted with higher effectiveness (correlation up to 0.68 between actual and predicted traits).

In this paper, we present a new strategy for modeling the motion of local patches for single-object tracking that can be seamlessly applied to most part-based trackers in the literature. The proposed adaptive local movement modeling method is able to model the local movement distribution of the image patches defining the object to track and the reliability of each image patch. Given the output of a base tracking algorithm, a Gaussian mixture model (GMM) is first used to model the distribution of the movement of local patches relative to the center of gravity of the tracked object. Then, the GMM is combined with the chosen base tracker in a boosting framework, which gives an efficient integrated scheme for the tracking task. This provides a robust procedure to detect outliers in the local motion of the patches. The algorithm is highly configurable with the possibility to change the number of local patches used for tracking and to adapt to the variations of the tracked object. The extensive tracking results on standard data sets show that equipping state-of-the-art trackers with our technique remarkably improves their performance.

The kernelized correlation filter (KCF) is one of the state-of-the-art object trackers. However, it does not reasonably model the distribution of correlation response during tracking process, which might cause the drifting problem, especially when targets undergo significant appearance changes due to occlusion, camera shaking, and/or deformation. In this paper, we propose an output constraint transfer (OCT) method that by modeling the distribution of correlation response in a Bayesian optimization framework is able to mitigate the drifting problem. OCT builds upon the reasonable assumption that the correlation response to the target image follows a Gaussian distribution, which we exploit to select training samples and reduce model uncertainty. OCT is rooted in a new theory which transfers data distribution to a constraint of the optimized variable, leading to an efficient framework to calculate correlation filters. Extensive experiments on a commonly used tracking benchmark show that the proposed method significantly improves KCF, and achieves better performance than other state-of-the-art trackers. To encourage further developments, the source code is made available.

Human re-identification is still a challenging task due to the human pose and illumination variations. Nowadays, surveillance cameras with high frame rate are capable of capturing several consecutive frames from each person. Multi-shot images provide richer information of the target person compared to a single-shot image. They, however, produce a high cost of information redundancy which may degrade the performance of re-identification systems. In this paper, we propose a novel framework that combines sparse coding and manifold constraints to extract discriminative information from multi-shot images of one pedestrian for person re-identification across a set of non-overlapped surveillance cameras. The evaluation over two standard multi-shot datasets shows very competitive accuracy of our framework against the state-of-the-art.

This paper presents a novel video descriptor based on substantial derivative, an important concept in fluid mechanics, that captures the rate of change of a fluid property as it travels through a velocity field. Unlike standard approaches that only use temporal motion information, our descriptor exploits the spatio-temporal characteristic of substantial derivative. In particular, the spatial and temporal motion patterns are captured by respectively the convective and local accelerations. After estimating the convective and local field from the optic flow, we followed the standard bag-of-word procedure for each motion pattern separately, and we concatenated the two resulting histograms to form the final descriptor. We extensively evaluated the effectiveness of the proposed method on five benchmarks, including three standard datasets (Violence in Movies, Violence In Crowd, and BEHAVE), and two new video-survelliance sequences downloaded from Youtube. Our experiments show how the proposed approach sets the new state-of-the-art on all benchmarks and how the structural information captured by convective acceleration is essential to detect violent episodes in crowded scenarios.

The fact that image data samples lie on a manifold has been successfully exploited in many learning and inference problems. In this paper we leverage the specific structure of data in order to improve recognition accuracies in general recognition tasks. In particular we propose a novel framework that allows to embed manifold priors into sparse representation-based classification (SRC) approaches. We also show that manifold constraints can be transferred from the data to the optimized variables if these are linearly correlated. Using this new insight, we define an efficient alternating direction method of multipliers (ADMM) that can consistently integrate the manifold constraints during the optimization process. This is based on the property that we can recast the problem as the projection over the manifold via a linear embedding method based on the Geodesic distance. The proposed approach is successfully applied on face, digit, action and objects recognition showing a consistently increase on performance when compared to the state of the art.

Re-identification systems aim at recognizing the same individuals in multiple cameras and one of the most relevant problems is that the appearance of same individual varies across cameras due to illumination and viewpoint changes. This paper proposes the use of Cumulative Weighted Brightness Transfer Functions to model this appearance variations. It is multiple frame-based learning approach which leverages consecutive detections of each individual to transfer the appearance, rather than learning brightness transfer function from pairs of images. We tested our approach on standard multi-camera surveillance datasets showing consistent and significant improvements over existing methods on three different datasets without any other additional cost. Our approach is general and can be applied to any appearance-based method.

Abnormal detection in crowd is a challenging vision task due to the scarcity of real-world training examples and the lack of a clear definition of abnormality. To tackle these challenges, we propose a novel measure to capture the commotion of a crowd motion for the task of abnormality detection in crowd. The unsupervised nature of the proposed measure allows to detect abnormality adaptively (i.e. context dependent) with no training cost. The extensive experiments on three different levels (e.g. pixel, frame and video) show the superiority of the proposed approach compared to the state of the arts.

This paper presents a novel video descriptor, referred to as Histogram of Oriented Track lets, for recognizing abnormal situation in crowded scenes. Unlike standard approaches that use optical flow, which estimates motion vectors only from two successive frames, we built our descriptor over long-range motion trajectories which is called track lets in the literature. Following the standard procedure, we divided video sequences in spatio-temporal cuboids within which we collected statistics on the track lets passing through them. In particular, we quantized orientation and magnitude in a 2-dimensional histogram which encodes the motion patterns expected in each cuboid. We classify frames as normal and abnormal by using Latent Dirichlet Allocation and Support Vector Machines. We evaluated the effectiveness of the proposed descriptors on three datasets: UCSD, Violence in Crowds and UMN. The experiments demonstrated (i) very promising results in abnormality detection, (ii) setting new state-of-the-art on two of them, and (iii) outperforming former descriptors based on the optical flow, dense trajectories and the social force model.

In this paper we present a novel strategy for modelling the motion of local patches for single object tracking that can be seamlessly applied to most part-based trackers in the literature. The proposed Adaptive Local Movement Modelling (ALMM) method is able to model the local spatial distribution of the image patches defining the object to track and the reliability of each image patch. Given the output of a base tracking algorithm, a Gaussian Mixture Model (GMM) is first used to model the distribution of the movement of local patches relative to the gravity center of the tracked object. Then, the GMM is combined with the base tracker in a boosting framework, which gives a novel integrated boosting classifier for the tracking task. This provides a robust procedure to detect outliers in the local motion of the patches. The algorithm is highly configurable with the possibility to change the number of local patches used for tracking and to adapt to the variations of the tracked object. Tracking results on standard datasets show that equipping state-of-the-art trackers with our tehcnique remarkably improves their performance.

In recent scene recognition research images or large image regions are often represented as disorganized “bags” of features which can then be analyzed using models originally developed to capture co-variation of word counts in text. However, image feature counts are likely to be constrained in different ways than word counts in text. For example, as a camera pans upwards from a building entrance over its first few floors and then further up into the sky Fig. 1, some feature counts in the image drop while others rise-only to drop again giving way to features found more often at higher elevations. The space of all possible feature count combinations is constrained both by the properties of the larger scene and the size and the location of the window into it. To capture such variation, in this paper we propose the use of the counting grid model. This generative model is based on a grid of feature counts, considerably larger than any of the modeled images, and considerably smaller than the real estate needed to tile the images next to each other tightly. Each modeled image is assumed to have a representative window in the grid in which the feature counts mimic the feature distribution in the image. We provide a learning procedure that jointly maps all images in the training set to the counting grid and estimates the appropriate local counts in it. Experimentally, we demonstrate that the resulting representation captures the space of feature count combinations more accurately than the traditional models, not only when the input images come from a panning camera, but even when modeling images of different scenes from the same category.

We present a statistical behavioural biometric approach for recognizing people by their aesthetic preferences, using colour images. In the enrollment phase, a model is learnt for each user, using a training set of preferred images. In the recognition/authentication phase, such model is tested with an unseen set of pictures preferred by a probe subject. The approach is dubbed “pump and distill”, since the training set of each user is pumped by bagging, producing a set of image ensembles. In the distill step, each ensemble is reduced into a set of surrogates, that is, aggregates of images sharing a similar visual content. Finally, LASSO regression is performed on these surrogates; the resulting regressor, employed as a classifier, takes test images belonging to a single user, predicting his identity. The approach improves the state-of-the-art on recognition and authentication tasks in average, on a dataset of 40000 Flickr images and 200 users. In practice, given a pool of 20 preferred images of a user, the approach recognizes his identity with an accuracy of 92%, and sets an authentication accuracy of 91% in terms of normalized Area Under the Curve of the CMC and ROC curve, respectively.

Are we recognizable by our image preferences? This paper answers affirmatively the question, presenting a soft biometric approach where the preferred images of an individual are used as his personal signature in identification tasks. The approach builds a multi-resolution latent space, formed by multiple Counting Grids, where similar images are mapped nearby. On this space, a set of preferred images of a user produces an ensemble of intensity maps, highlighting in an intuitive way his personal aesthetic preferences. These maps are then used for learning a battery of discriminative classifiers (one for each resolution), which characterizes the user and serves to perform identification. Results are promising: on a dataset of 200 users, and 40K images, using 20 preferred images as biometric template gives 66% of probability of guessing the correct user. This makes the "personal aesthetics" a very hot topic for soft biometrics, while its usage in standard biometric applications seems to be far from being effective, as we show in a simple user study.

Hybrid generative-discriminative models are useful in biomedical applications- generative modeling extracts interpretable features from raw data, highlighting its properties and increasing classification accuracy when used as input for a discriminative classifier. This raises the question: which generative model should be used for a particular application? In this paper we apply a recently proposed generative model called the Counting Grid to expression microarray data and derive the corresponding Fisher kernel. We justify why this model is particularly well-suited for this application and evaluate classification accuracy on four gene expression data sets, including three tumor data sets and a blood sample data set from schizophrenic patients and healthy controls. We report state of the art results on three of the analyzed data sets and closely match the accuracy from previous work on the other.

This paper builds upon the belief that every human being has a built-in image aesthetic evaluation system. This sort of personal aesthetics mostly follows certain aesthetic rules widely studied in image aesthetics (e.g., rules of thirds, colorfulness, etc.), though it likely contains some innate, unique preferences. This paper is a proof of concept of this intuition, presenting personal aesthetics as a novel behavioral biometrical trait. In our scenario, personal aesthetics activate when an individual is presented with a set of photos he may like or dislike. The goal is to distill and encode the uniqueness of his visual preferences into a compact template. To this aim, we extract a pool of low- and high-level state-of-the-art image features from a set of Flickr images preferred by a user, feeding them successively into a LASSO regressor. LASSO highlights the most discriminant cues for the individual, allowing authentication and recognition tasks. The results are surprising given only 1 image as test. We can match the user identity against a gallery of 200 individuals definitely much better than chance. Using 20 images (all preferred by a single user) as a biometrical trait, we reach an AUC of 96%, considering the cumulative matching characteristic curve. Extensive experiments also support the interpretability of our approach, effectively modeling what is the “what we like” that distinguishes us from others.

Recently, the Counting Grid (CG) model was developed to represent each input image as a point in a large grid of feature counts. This latent point is a corner of a window of grid points which are all uniformly combined to match the (normalized) feature counts in the image. Being a bag of word model with spatial layout in the latent space, the CG model has superior handling of field of view changes in comparison to other bag of word models, but with the price of being essentially a mixture, mapping each scene to a single window in the grid. In this paper we introduce a family of componential models, dubbed the Componential Counting Grid, whose members represent each input image by multiple latent locations, rather than just one. In this way, we make a substantially more flexible admixture model which captures layers or parts of images and maps them to separate windows in a Counting Grid. We tested the models on scene and place classification where their componential nature helped to extract objects, to capture parallax effects, thus better fitting the data and outperforming Counting Grids and Latent Dirichlet Allocation, especially on sequences taken with wearable cameras.

Modeling user preferences in photographic images is often reduced to analyzing intermediate explicit representations (e.g. textual tags) as means of capturing the objective and subjective properties of image perception, trying to distill the essence of what gives pleasure. We propose an alternative approach that bypasses the necessity to build an explicit conceptual coding of image preferences, operating directly on the raw properties of the images, extracted with heterogeneous feature descriptors. This is achieved through the counting grid model, which fuses together content-based and aesthetics themes into a 2D map in an unsupervised way. We show that certain locations in this map correspond to perceptually intuitive image classes, even without relying on tags or other user-defined information. Moreover, we show that users' individual preferences can be represented as distributions over the map, allowing us to evaluate the affinity between different users' appreciations. We experiment on a large Flickr dataset, clustering users by affinity, and validating these clusters by checking users that belong to the same Flickr photo groups.

One of the main findings of cognitive sciences is that automatic processes of which we are unaware shape, to a significant extent, our perception of the environment. The phenomenon applies not only to the real world, but also to multimedia data we consume every day. Whenever we look at pictures, watch a video or listen to audio recordings, our conscious attention efforts focus on the observable content, but our cognition spontaneously perceives intentions, beliefs, values, attitudes and other constructs that, while being outside of our conscious awareness, still shape our reactions and behavior. So far, multimedia technologies have neglected such a phenomenon to a large extent. This paper argues that taking into account cognitive effects is possible and it can also improve multimedia approaches. As a supporting proof-of-concept, the paper shows not only that there are visual patterns correlated with the personality traits of 300 Flickr users to a statistically significant extent, but also that the personality traits (both self-assessed and attributed by others) of those users can be inferred from the images these latter post as "favourite".

In text analysis documents are represented as disorganized bags of words, models of count features are typically based on mixing a small number of topics \cite{lda,sam}. Recently, it has been observed that for many text corpora documents evolve into one another in a smooth way, with some features dropping and new ones being introduced. The counting grid \cite{cgUai} models this spatial metaphor literally: it is multidimensional grid of word distributions learned in such a way that a document's own distribution of features can be modeled as the sum of the histograms found in a window into the grid. The major drawback of this method is that it is essentially a mixture and all the content much be generated by a single contiguous area on the grid. This may be problematic especially for lower dimensional grids. In this paper, we overcome to this issue with the \emph{Componential Counting Grid} which brings the componential nature of topic models to the basic counting grid. We also introduce a generative kernel based on the document's grid usage and a visualization strategy useful for understanding large text corpora. We evaluate our approach on document classification and multimodal retrieval obtaining state of the art results on standard benchmarks.

Hidden Markov Models (HMMs) are among the most important and widely used techniques to deal with sequential or temporal data. Their application in computer vision ranges from action/gesture recognition to videosurveillance through shape analysis. Although HMMs are often embedded in complex frameworks, this paper focuses on theoretical aspects of HMM learning. We propose a regularized algorithm for learning HMMs in the spectral framework, whose computations have no local minima. Compared with recently proposed spectral algorithms for HMMs, our method is guaranteed to produce probability values which are always physically meaningful and which, on synthetic mathematical models, give very good approximations to true probability values. Furthermore, we place no restriction on the number of symbols and the number of states. On various pattern recognition data sets, our algorithm consistently outperforms classical HMMs, both in accuracy and computational speed. This and the fact that HMMs are used in vision as building blocks for more powerful classification approaches, such as generative embedding approaches or more complex generative models, strongly support spectral HMMs (SHMMs) as a new basic tool for pattern recognition.

Models that captures the common structure of an object class have appeared few years ago in the literature (Jojic and Caspi in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 212–219, 2004 ; Winn and Jojic in Proceedings of International Conference on Computer Vision (ICCV), pp. 756–763, 2005 ); they are often referred as “stel models.” Their main characteristic is to segment objects in clear, often semantic, parts as a consequence of the modeling constraint which forces the regions belonging to a single segment to have a tight distribution over local measurements, such as color or texture. This self-similarity within a region in a single image is typical of many meaningful image parts, even when across different images of similar objects, the corresponding parts may not have similar local measurements. Moreover, the segmentation itself is expected to be consistent within a class, although still flexible. These models have been applied mostly to segmentation scenarios. In this paper, we extent those ideas (1) proposing to capture correlations that exist in structural elements of an image class due to global effects, (2) exploiting the segmentations to capture feature co-occurrences and (3) allowing the use of multiple, eventually sparse, observation of different nature. In this way we obtain richer models more suitable to recognition tasks. We accomplish these requirements using a novel approach we dubbed stel component analysis . Experimental results show the flexibility of the model as it can deal successfully with image/video segmentation and object recognition where, in particular, it can be used as an alternative of, or in conjunction with, bag-of-features and related classifiers, where stel inference provides a meaningful spatial partition of features.

A score function induced by a generative model of the data can provide a feature vector of a fixed dimension for each data sample. Data samples themselves may be of differing lengths (e.g., speech segments or other sequential data), but as a score function is based on the properties of the data generation process, it produces a fixed-length vector in a highly informative space, typically referred to as "score space." Discriminative classifiers have been shown to achieve higher performances in appropriately chosen score spaces with respect to what is achievable by either the corresponding generative likelihood-based classifiers or the discriminative classifiers using standard feature extractors. In this paper, we present a novel score space that exploits the free energy associated with a generative model. The resulting free energy score space (FESS) takes into account the latent structure of the data at various levels and can be shown to lead to classification performance that at least matches the performance of the free energy classifier based on the same generative model and the same factorization of the posterior. We also show that in several typical computer vision and computational biology applications the classifiers optimized in FESS outperform the corresponding pure generative approaches, as well as a number of previous approaches combining discriminating and generative models.

In recent years a particular class of probabilistic graphical models-called topic models-has proven to represent an useful and interpretable tool for understanding and mining microarray data. In this context, such models have been almost only applied in the clustering scenario, whereas the classification task has been disregarded by researchers. In this paper, we thoroughly investigate the use of topic models for classification of microarray data, starting from ideas proposed in other fields (e.g., computer vision). A classification scheme is proposed, based on highly interpretable features extracted from topic models, resulting in a hybrid generative-discriminative approach; an extensive experimental evaluation, involving 10 different literature benchmarks, confirms the suitability of the topic models for classifying expression microarray data.

In recent object/scene recognition research images or large image regions are often represented as disorganized ”bags” of image features. This representation allows direct application of models of word counts in text. However, the image feature counts are likely to be constrained in different ways than word counts in text. As a camera pans upwards from a building entrance over its first few floors and then above the penthouse to the backdrop formed by the mountains, and then further up into the sky, some feature counts in the image drop while others rise-only to drop again giving way to features found more often at higher elevations (Fig. 1). The space of all possible feature count combinations is constrained by the properties of the larger scene as well as the size and the location of the window into it. Accordingly, our model is based on a grid of feature counts, considerably larger than any of the modeled images, and considerably smaller than the real estate needed to tile the images next to each other tightly. Each modeled image is assumed to have a representative window in the grid in which the sum of feature counts mimics the distribution in the image. We provide learning procedures that jointly map all images in the training set to the counting grid and estimate the appropriate local counts in it. Experimentally, we demonstrate that the resulting representation captures the space of feature count combinations more accurately than the traditional models, such as latent Dirichlet allocation, even when modeling images of different scenes from the same category.

In this paper, we present an appearance-based method for person re-identification. It consists in the extraction of features that model three complementary aspects of the human appearance: the overall chromatic content, the spatial arrangement of colors into stable regions, and the presence of recurrent local motifs with high entropy. All this information is derived from different body parts, and weighted opportunely by exploiting symmetry and asymmetry perceptual principles. In this way, robustness against very low resolution, occlusions and pose, viewpoint and illumination changes is achieved. The approach applies to situations where the number of candidates varies continuously, considering single images or bunch of frames for each individual. It has been tested on several public benchmark datasets (ViPER, iLIDS, ETHZ), gaining new state-of-the-art performances.

Most approaches to learn classifiers for structured objects (e.g., images) use generative models in a classical Bayesian framework. However, state-of-the-art classifiers for vectorial data (e.g., support vector machines) are learned discriminatively. A generative embedding is a mapping from the object space into a fixed dimensional score space, induced by a generative model, usually learned from data. The fixed dimensionality of these generative score spaces makes them adequate for discriminative learning of classifiers, thus bringing together the best of the discriminative and generative paradigms. In particular, it was recently shown that this hybrid approach outperforms a classifier obtained directly for the generative model upon which the score space was built. Using a generative embedding involves two steps: (i) defining and learning the generative model and using it to build the embedding; (ii) discriminatively learning a (maybe kernel) classifier on the adopted score space. The literature on generative embeddings is essentially focused on step (i), usually using some standard off-the-shelf tool for step (ii). In this paper, we adopt a different approach, by focusing also on the discriminative learning step. In particular, we combine two very recent and top performing tools in each of the steps: (i) the free energy score space; (ii) non-extensive information theoretic kernels. In this paper, we apply this methodology in scene recognition. Experimental results on two benchmark datasets shows that our approach yields state-of-the-art performance.

In this paper, we propose a novel appearance-based method for person re-identification, that condenses a set of frames of the same individual into a highly informative signature, called Histogram Plus Epitome, HPE. It incorporates complementary global and local statistical descriptions of the human appearance, focusing on the overall chromatic content, via histograms representation, and on the presence of recurrent local patches, via epitome estimation. The matching of HPEs provides optimal performances against low resolution, occlusions, pose and illumination variations, defining novel state-of-the-art results on all the datasets considered.

Following the trend of “segmentation for recognition”, we present 2LDA, a novel generative model to automatically segment an image in 2 segments, background and foreground, while inferring a latent Dirichlet allocation (LDA) topic distribution on both segments. The idea is to merge two separate modules, LDA and the segmentation module, explicitly considering (and exchanging) the uncertainty between them. The resulting model adds spatial relationships to LDA, which in turn helps in using the topics to segment an image. The experimental results show that, unlike LDA, our model can be used to recognize objects, and also outperforms the state of the art algorithms.

In order to study the properties of total visual input in humans, a single subject wore a camera for two weeks capturing, on average, an image every 20 seconds (www.research.microsoft.com/~jojic/aihs). The resulting new dataset contains a mix of indoor and outdoor scenes as well as numerous foreground objects. Our first analysis goal is to create a visual summary of the subject’s two weeks of life using unsupervised algorithms that would automatically discover recurrent scenes, familiar faces or common actions. Direct application of existing algorithms, such as panoramic stitching (e.g. Photosynth) or appearance-based clustering models (e.g. the epitome), is impractical due to either the large dataset size or the dramatic variation in the lighting conditions. As a remedy to these problems, we introduce a novel image representation, the “stel epitome,” and an associated efficient learning algorithm. In our model, each image or image patch is characterized by a hidden mapping T, which, as in previous epitome models, defines a mapping between the image-coordinates and the coordinates in the large all-I-have-seen" epitome matrix. The limited epitome real-estate forces the mappings of different images to overlap, with this overlap indicating image similarity. However, in our model the image similarity does not depend on direct pixel-to-pixel intensity/color/feature comparisons as in previous epitome models, but on spatial configuration of scene or object parts, as the model is based on the palette-invariant stel models. As a result, stel epitomes capture structure that is invariant to non-structural changes, such as illumination, that tend to uniformly affect pixels belonging to a single scene or object part."

As a useful concept in the study of the low level image class structure, we introduce the notion of a structure element - `stel.' The notion is related to the notions of a pixel, superpixel, segment or a part, but instead of referring to an element or a region of a single image, stel is a probabilistic element of an entire image class. Stels often define clear object or scene parts as a consequence of the modeling constraint which forces the regions belonging to a single stel to have a tight distribution over local measurements, such as color or texture. This self-similarity within a region in a single image is typical of most meaningful image parts, even when in different images of similar objects the corresponding parts may not have similar local measurements. The stel itself is expected to be consistent within a class, yet flexible, which we accomplish using a novel approach we dubbed stel component analysis. Experimental results show how stel component analysis can assist in image/video segmentation and object recognition where, in particular, it can be used as an alternative of, or in conjunction with, bag-of-features and related classifiers, where stel inference provides a meaningful spatial partition of features.

Hybrid, generative-discriminative, techniques have proven to be valuable approaches in tackling difficult object or scene recognition problems. In general, a generative model over the available data for each image class is first learned providing a relatively comprehensive statistical multi-level representation. In this way, new meaningful image features become available, which encode the degree of fitness of the data with respect to the model at different representation levels. Such features are then fed into a discriminative classifier which can exploit the intrinsic data separability. In this paper, we propose the use of variational free energy terms as feature vectors, so that the degree of fitness of the data and the uncertainty over the generative process are explicitly included in the data description. The proposed method is automatically superior to a pure generative classification, and we also experimentally validate it on a wide selection of generative models applied to challenging benchmarks in hard computer vision tasks such as scene, object, and shape recognition. In several instances, the proposed approach outperforms the current state-of-the-art techniques as for classification results, while also showing to be computationally inexpensive.

Score functions induced by generative models extract fixed-dimension feature vectors from different-length data observations by subsuming the process of data generation, projecting them in highly informative spaces called score spaces. In this way, standard discriminative classifiers are proved to achieve higher performances than a solely generative or discriminative approach. In this paper, we present a novel score space that exploits the free energy associated to a generative model through a score function. This function aims at capturing both the uncertainty of the model learning and ``local compliance of data observations with respect to the generative process. Theoretical justifications and convincing comparative classification results on various generative models prove the goodness of the proposed strategy.

Image categorization is undoubtedly one of the most challenging open problems faced in computer vision, far from being solved by employing pure visual cues. Recently, additional textual ldquotagsrdquo can be associated to images, enriching their semantic interpretation beyond the pure visual aspect, and helping to bridge the so-called semantic gap. One of the latest class of tags consists in geo-location data, containing information about the geographical site where an image has been captured. Such data motivate, if not require, novel strategies to categorize images, and pose new problems to focus on. In this paper, we present a statistical method for geo-located image categorization, in which categories are formed by clustering geographically proximal images with similar visual appearance. The proposed strategy permits also to deal with the geo-recognition problem, i.e., to infer the geographical area depicted by images with no available location information. The method lies in the wide literature on statistical latent representations, in particular, the probabilistic latent semantic analysis (pLSA) paradigm has been extended, introducing a latent aspect which characterizes peculiar visual features of different geographical zones. Experiments on categorization and georecognition have been carried out employing a well-known geographical image repository: results are actually very promising, opening new interesting challenges and applications in this research field.

In the last few years, there has been a certain attention to the problem of human-human communication, trying to devise artificial systems able to mediate a conversational setting between two or more people. In this paper, we designed an automatic system based on a generative structure able to classify hard dialog acts. The generative model is composed by integrating a hierarchical Gaussian mixture model and the Influence Model, originating a brand new method able to deal with such difficult scenarios. The method has been tested on a set of conversational settings involving dialogues between adults and children and adults, in flat and arguing discussions, proving very accurate classification results.