Daniel Gatica-Perez

Modeling scenes with local descriptors and latent aspects

We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to three open questions:(l) whether the invariant local features are suitable for scene (rather than object) classification; (2) whether unsupennsed latent space models can be used for feature extraction in the classification task; and (3) whether the latent space formulation can discover visual co-occurrence patterns, motivating novel approaches for image organization and segmentation. Using a 9500-image dataset, our approach is validated on each of these issues. First, we show with extensive experiments on binary and multi-class scene classification tasks, that a bag-of-visterm representation, derived from local invariant descriptors, consistently outperforms state-of-the-art approaches. Second, we show that probabilistic latent semantic analysis (PLSA) generates a compact scene representation, discriminative for accurate classification, and significantly more robust when less training data are available. Third, we have exploited the ability of PLSA to automatically extract visually meaningful aspects, to propose new algorithms for aspect-based image ranking and context-sensitive image segmentation.

Automatic analysis of multimodal group actions in meetings

This paper investigates the recognition of group actions in meetings. A framework is employed in which group actions result from the interactions of the individual participants. The group actions are modeled using different HMM-based approaches, where the observations are provided by a set of audiovisual features monitoring the actions of individuals. Experiments demonstrate the importance of taking interactions into account in modeling the group actions. It is also shown that the visual modality contains useful information, even for predominantly audio-based events, motivating a multimodal approach to meeting analysis.

On image auto-annotation with latent space models

Image auto-annotation, i.e., the association of words to whole images, has attracted considerable attention. In particular, unsupervised, probabilistic latent variable models of text and image features have shown encouraging results, but their performance with respect to other approaches remains unknown. In this paper, we apply and compare two simple latent space models commonly used in text analysis, namely Latent Semantic Analysis (LSA) and Probabilistic LSA (PLSA). Annotation strategies for each model are discussed. Remarkably, we found that, on a 8000-image dataset, a classic LSA model defined on keywords and a very basic image representation performed as well as much more complex, state-of-the-art methods. Furthermore, non-probabilistic methods (LSA and direct image matching) outperformed PLSA on the same dataset.

PLSA-based image auto-annotation: constraining the latent space

We address the problem of unsupervised image auto-annotation with probabilistic latent space models. Unlike most previous works, which build latent space representations assuming equal relevance for the text and visual modalities, we propose a new way of modeling multi-modal co-occurrences, constraining the definition of the latent space to ensure its consistency in semantic terms (words), while retaining the ability to jointly model visual information. The concept is implemented by a linked pair of Probabilistic Latent Semantic Analysis (PLSA) models. On a 16000-image collection, we show with extensive experiments that our approach significantly outperforms previous joint models.

Using particles to track varying numbers of interacting people

In this paper, we present a Bayesian framework for the fully automatic tracking of a variable number of interacting targets using a fixed camera. This framework uses a joint multi-object state-space formulation and a trans-dimensional Markov Chain Monte Carlo (MCMC) particle filter to recursively estimates the multi-object configuration and efficiently search the state-space. We also define a global observation model comprised of color and binary measurements capable of discriminating between different numbers of objects in the scene. We present results which show that our method is capable of tracking varying numbers of people through several challenging real-world tracking situations such as full/partial occlusion and entering/leaving the scene.

A Thousand Words in a Scene

This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of text modeling methods and local invariant features. Our work attempts to elucidate (1) whether a textlike bag-of-visterms (BOV) representation (histogram of quantized local visual features) is suitable for scene (rather than object) classification, (2) whether some analogies between discrete scene representations and text documents exist, and 3) whether unsupervised, latent space models can be used both as feature extractors for the classification task and to discover patterns of visual co-occurrence. Using several data sets, we validate our approach, presenting and discussing experiments on each of these issues. We first show, with extensive experiments on binary and multiclass scene classification tasks using a 9,500-image data set, that the BOV representation consistently outperforms classical scene classification approaches. In other data sets, we show that our approach competes with or outperforms other recent more complex methods. We also show that probabilistic latent semantic analysis (PLSA) generates a compact scene representation, is discriminative for accurate classification, and is more robust than the BOV representation when less labeled training data is available. Finally, through aspect-based image ranking experiments, we show the ability of PLSA to automatically extract visually meaningful scene patterns, making such representation useful for browsing image collections.

Modeling Semantic Aspects for Cross-Media Image Indexing

To go beyond the query-by-example paradigm in image retrieval, there is a need for semantic indexing of large image collections for intuitive text-based image search. Different models have been proposed to learn the dependencies between the visual content of an image set and the associated text captions, then allowing for the automatic creation of semantic indexes for unannotated images. The task, however, remains unsolved. In this paper, we present three alternatives to learn a probabilistic latent semantic analysis (PLSA) model for annotated images and evaluate their respective performance for automatic image indexing. Under the PLSA assumptions, an image is modeled as a mixture of latent aspects that generates both image features and text captions, and we investigate three ways to learn the mixture of aspects. We also propose a more discriminative image representation than the traditional Blob histogram, concatenating quantized local color information and quantized local texture descriptors. The first learning procedure of a PLSA model for annotated images is a standard expectation-maximization (EM) algorithm, which implicitly assumes that the visual and the textual modalities can be treated equivalently. The other two models are based on an asymmetric PLSA learning, allowing to constrain the definition of the latent space on the visual or on the textual modality. We demonstrate that the textual modality is more appropriate to learn a semantically meaningful latent space, which translates into improved annotation performance. A comparison of our learning algorithms with respect to recent methods on a standard data set is presented, and a detailed evaluation of the performance shows the validity of our framework.

Modeling Dominance in Group Conversations Using Nonverbal Activity Cues

Dominance - a behavioral expression of power - is a fundamental mechanism of social interaction, expressed and perceived in conversations through spoken words and audiovisual nonverbal cues. The automatic modeling of dominance patterns from sensor data represents a relevant problem in social computing. In this paper, we present a systematic study on dominance modeling in group meetings from fully automatic nonverbal activity cues, in a multi-camera, multi-microphone setting. We investigate efficient audio and visual activity cues for the characterization of dominant behavior, analyzing single and joint modalities. Unsupervised and supervised approaches for dominance modeling are also investigated. Activity cues and models are objectively evaluated on a set of dominance-related classification tasks, derived from an analysis of the variability of human judgment of perceived dominance in group discussions. Our investigation highlights the power of relatively simple yet efficient approaches and the challenges of audiovisual integration. This constitutes the most detailed study on automatic dominance modeling in meetings to date.

Modeling individual and group actions in meetings with layered HMMs

We address the problem of recognizing sequences of human interaction patterns in meetings, with the goal of structuring them in semantic terms. The investigated patterns are inherently group-based (defined by the individual activities of meeting participants, and their interplay), and multimodal (as captured by cameras and microphones). By defining a proper set of individual actions, group actions can be modeled as a two-layer process, one that models basic individual activities from low-level audio-visual (AV) features,and another one that models the interactions. We propose a two-layer hidden Markov model (HMM) framework that implements such concept in a principled manner, and that has advantages over previous works. First, by decomposing the problem hierarchically, learning is performed on low-dimensional observation spaces, which results in simpler models. Second, our framework is easier to interpret, as both individual and group actions have a clear meaning, and thus easier to improve. Third, different HMMs can be used in each layer, to better reflect the nature of each subproblem. Our framework is general and extensible, and we illustrate it with a set of eight group actions, using a public 5-hour meeting corpus. Experiments and comparison with a single-layer HMM baseline system show its validity.

Evaluating Multi-Object Tracking

Multiple object tracking (MOT) is an active and challenging research topic. Many different approaches to the MOT problem exist, yet there is little agreement amongst the community on how to evaluate or compare these methods, and the amount of literature addressing this problem is limited. The goal of this paper is to address this issue by providing a comprehensive approach to the empirical evaluation of tracking performance. To that end, we explore the tracking characteristics important to measure in a real-life application, focusing on configuration (the number and location of objects in a scene) and identification (the consistent labeling of objects over time), and define a set of measures and a protocol to objectively evaluate these characteristics.