Segmenting semantically meaningful whole objects from images is a challenging problem, and it becomes especially so without higher level common sense reasoning. In this paper, we present an interactive segmentation framework that integrates image appearance and boundary constraints in a principled way to address this problem. In particular, we assume that small sets of pixels, which are referred to as seed pixels, are labeled as the object and background. The seed pixels are used to estimate the labels of the unlabeled pixels using Dirichlet process multiple-view learning, which leverages 1) multiple-view learning that integrates appearance and boundary constraints and 2) Dirichlet process mixture-based nonlinear classification that simultaneously models image features and discriminates between the object and background classes. With the proposed learning and inference algorithms, our segmentation framework is experimentally shown to produce both quantitatively and qualitatively promising results on a standard dataset of images. In particular, our proposed framework is able to segment whole objects from images given insufficient seeds.

In this paper, we study the problem of social relational inference using visual concepts which serve as indicators of actors' social interactions. While social network analysis from videos has started to gain attention in the recent years, the existing work either uses proximity or co-occurrence statistics, or exploit a holistic model of the scene content where the relations are assumed to stay constant throughout the video. This work permits changing relations and argues that there exists a relationship between the visual concepts and the social relations among actors, which is a fundamentally new concept in computer vision. Specifically, we leverage the existing large-scale concept detectors to generate concept score vectors to represent the video content, and we further map them to grouping cues that are used to detect the social structure. In our framework, a probabilistic graphical model with temporal smoothing provides a means to analyze social relations among actors and detect communities. Experiments on Youtube videos and theatrical movies validate the proposed framework.

We study the problem of event detection from realistic videos with repetitive sequential human activities. Despite the large body of work on event detection and recognition, very few have addressed low-quality videos captured from realistic environments. Our framework is based on solving the shortest path on a temporal-event graph constructed from the video content. Graph vertices correspond to detected event primitives, and edge weights are set according to generic knowledge of the event patterns and the discrepancy between event primitives based on a greedy matching of their visual features. Experimental results on videos collected from a retail environment validate the usefulness of the proposed approach.

Visual compliance has emerged as a new paradigm to ensure that employees comply with processes and policies in a business context. In this paper, we focus on videos from retail stores and formulate a binary integer program for detecting checkout events, which enables enforcing visual compliance in such an environment. The proposed integer program maximizes the essential quantities that characterize true events of interest, subject to an array of constraints. In particular, the binary decision variables correspond to the presence of a set of hypothesized visual events. In the objective function, the binary variables are weighted by quality measures derived from infinite Gaussian mixture modeling of the video content, such that maximizing the overall quality measure is expected to uncover the meaningful visual events. Our framework is tested and validated on videos recorded at checkout lanes, and leads to better performance than previous methods.

In this paper, we introduce a new type of coverage for wireless sensor networks, called Directed Coverage (D-coverage). Basically, D-coverage is the coverage provided by a sensor network monitoring an area between two boundaries, through which the intruder attempts to penetrates the area. We also study how to measure the quality of D-coverage. Our first evaluation approach is a projection-based simple approach, while our second approach is a more comprehensive Markov chain based approach. Our evaluation approaches can accurately evaluate the quality and provide good guidelines for sensor network deployment and run-time repair.

In this paper, we propose to use hypergraphs as the model for images and pose image segmentation as a machine learning problem in which some pixels (called seeds) are labeled as the objects and background. Using the seed pixels, our method predicts the labels for all unlabeled pixels. We present the relations of the proposed method to other hypergraph based learning techniques. We give an adaptive procedure for constructing image hypergraphs and achieve promising results on a real image dataset.

Regression or least squares fitting is an important problem in statistics, data mining and many other applications. In recent years, basis functions derived from the underlying geometry of data, primarily Laplacian eigenfunctions, have attracted much interest. In this paper, we present a new framework based on adaptive Laplacian eigenfunctions and show the benefit of using a time-varying basis in regression analysis.