Vladimir Pavlovic

Visual interpretation of hand gestures for human-computer interaction: a review

In a process for preparing phosphoric acid by contact of sulphuric acid and phosphate rock with filtration of the gypsum slurry and recycle of the rest for contact with fresh rock, a fraction of the recycle slurry is treated with sulphuric acid to convert at least some of the gypsum to calcium sulphate hemihydrate and the slurry comprising hemihydrate is returned to contact the mixture of phosphate rock, phosphoric acid and recycle gypsum slurry. The process gives an easily filtered gypsum slurry with low phosphate losses in the gypsum filter cake.

A New Baseline for Image Annotation

Automatically assigning keywords to images is of great interest as it allows one to index, retrieve, and understand large collections of image data. Many techniques have been proposed for image annotation in the last decade that give reasonable performance on standard datasets. However, most of these works fail to compare their methods with simple baseline techniques to justify the need for complex models and subsequent training. In this work, we introduce a new baseline technique for image annotation that treats annotation as a retrieval problem. The proposed technique utilizes low-level image features and a simple combination of basic distances to find nearest neighbors of a given image. The keywords are then assigned using a greedy label transfer mechanism. The proposed baseline outperforms the current state-of-the-art methods on two standard and one large Web dataset. We believe that such a baseline measure will provide a strong platform to compare and better understand future annotation techniques.

Face tracking and recognition with visual constraints in real-world videos

We address the problem of tracking and recognizing faces in real-world, noisy videos. We track faces using a tracker that adaptively builds a target model reflecting changes in appearance, typical of a video setting. However, adaptive appearance trackers often suffer from drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, our tracker introduces visual constraints using a combination of generative and discriminative models in a particle filtering framework. The generative term conforms the particles to the space of generic face poses while the discriminative one ensures rejection of poorly aligned targets. This leads to a tracker that significantly improves robustness against abrupt appearance changes and occlusions, critical for the subsequent recognition phase. Identity of the tracked subject is established by fusing pose-discriminant and person-discriminant features over the duration of a video sequence. This leads to a robust video-based face recognizer with state-of-the-art recognition performance. We test the quality of tracking and face recognition on real-world noisy videos from YouTube as well as the standard Honda/UCSD database. Our approach produces successful face tracking results on over 80% of all videos without video or person-specific parameter tuning. The good tracking performance induces similarly high recognition rates: 100% on Honda/UCSD and over 70% on the YouTube set containing 35 celebrities in 1500 sequences.

Toward multimodal human-computer interface

Recent advances in various signal processing technologies, coupled with an explosion in the available computing power, have given rise to a number of novel human-computer interaction (HCI) modalities: speech, vision-based gesture recognition, eye tracking, electroencephalograph, etc. Successful embodiment of these modalities into an interface has the potential of easing the HCI bottleneck that has become noticeable with the advances in computing and communication. It has also become increasingly evident that the difficulties encountered in the analysis and interpretation of individual sensing modalities may be overcome by integrating them into a multimodal human-computer interface. We examine several promising directions toward achieving multimodal HCI. We consider some of the emerging novel input modalities for HCI and the fundamental issues in integrating them at various levels, from early signal level to intermediate feature level to late decision level. We discuss the different computational approaches that may be applied at the different levels of modality integration. We also briefly review several demonstrated multimodal HCI systems and applications. Despite all the recent developments, it is clear that further research is needed for interpreting and fitting multiple sensing modalities in the context of HCI. This research can benefit from many disparate fields of study that increase our understanding of the different human communication modalities and their potential role in HCI.

A dynamic Bayesian network approach to figure tracking using learned dynamic models

The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. However most work on tracking and synthesizing figure motion has employed either simple, generic dynamic models or highly specific hand-tailored ones. Recently, a broad class of learning and inference algorithms for time-series models have been successfully cast in the framework of dynamic Bayesian networks (DBNs). This paper describes a novel DBN-based switching linear dynamic system (SLDS) model and presents its application to figure motion analysis. A key feature of our approach is an approximate Viterbi inference technique for overcoming the intractability of exact inference in mixed-state DBNs. We present experimental results for learning figure dynamics from video data and show promising initial results for tracking, interpolation, synthesis, and classification using learned models.

RankGene: identification of diagnostic genes based on expression data

RankGene is a program for analyzing gene expression data and computing diagnostic genes based on their predictive power in distinguishing between different types of samples. The program integrates into one system a variety of popular ranking criteria, ranging from the traditional t-statistic to one-dimensional support vector machines. This flexibility makes RankGene a useful tool in gene expression analysis and feature selection.

Baselines for Image Annotation

Automatically assigning keywords to images is of great interest as it allows one to retrieve, index, organize and understand large collections of image data. Many techniques have been proposed for image annotation in the last decade that give reasonable performance on standard datasets. However, most of these works fail to compare their methods with simple baseline techniques to justify the need for complex models and subsequent training. In this work, we introduce a new and simple baseline technique for image annotation that treats annotation as a retrieval problem. The proposed technique utilizes global low-level image features and a simple combination of basic distance measures to find nearest neighbors of a given image. The keywords are then assigned using a greedy label transfer mechanism. The proposed baseline method outperforms the current state-of-the-art methods on two standard and one large Web dataset. We believe that such a baseline measure will provide a strong platform to compare and better understand future annotation techniques.

Impact of dynamic model learning on classification of human motion

The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. However, most work on tracking and analysis of figure motion has employed either generic or highly specific hand-tailored dynamic models superficially coupled with hidden Markov models (HMMs) of motion regimes. Recently, an alternative class of learned dynamic models known as switching linear dynamic systems (SLDSs) has been cast in the framework of dynamic Bayesian networks (DBNs) and applied to analysis and tracking of the human figure. In this paper we further study the impact of learned SLDS models on analysis and tracking of human motion and contrast them to the more common HMM models. We develop a novel approximate structured variational inference algorithm for SLDS, a globally convergent DBN inference scheme, and compare it with standard SLDS inference techniques. Experimental results on learning and analysis of figure dynamics from video data indicate the significant potential of the SLDS approach.

A graphical model framework for coupling MRFs and deformable models

This paper proposes a new framework for image segmentation based on the integration of MRFs and deformable models using graphical models. We first construct a graphical model to represent the relationship of the observed image pixels, the true region labels and the underlying object contour. We then formulate the problem of image segmentation as the one of joint regioncontour inference and learning in the graphical model. The graphical model representation allows us to use an approximate structured variational inference technique to solve this otherwise intractable joint inference problem. Using this technique, the MAP solution to the original model is obtained by finding the MAP solutions of two simpler models, an extended MRF model and a probabilistic deformable model, iteratively and incrementally. In the extended MRF model, the true region labels are estimated using the BP algorithm in a band area around the estimated contour from the probabilistic deformable model, and the result in turn guides the probabilistic deformable model to an improved estimation of the contour. Experimental results show that our new hybrid method outperforms both the MRF-based and the deformable model-based methods.

A hybrid face recognition method using Markov random fields

We propose a hybrid face recognition method that combines holistic and feature analysis-based approaches using a Markov random field (MRF) model. The face images are divided into small patches, and the MRF model is used to represent the relationship between the image patches and the patch IDs. The MRF model is first learned from the training image patches, given a test image. The most probable patch IDs is then inferred using the belief propagation (BP) algorithm. Finally, the ID of the test image is determined by a voting scheme from the estimated patch IDs. Experimental results on several face datasets indicate the significant potential of our method.