A morphable model for the synthesis of 3D faces

When monitoring spatial phenomena, which can often be modeled as Gaussian processes (GPs), choosing sensor locations is a fundamental task. There are several common strategies to address this task, for example, geometry or disk models, placing sensors at the points of highest entropy (variance) in the GP model, and A-, D-, or E-optimal design. In this paper, we tackle the combinatorial optimization problem of maximizing the mutual information between the chosen locations and the locations which are not selected. We prove that the problem of finding the configuration that maximizes mutual information is NP-complete. To address this issue, we describe a polynomial-time approximation that is within (1-1/e) of the optimum by exploiting the submodularity of mutual information. We also show how submodularity can be used to obtain online bounds, and design branch and bound search procedures. We then extend our algorithm to exploit lazy evaluations and local structure in the GP, yielding significant speedups. We also extend our approach to find placements which are robust against node failures and uncertainties in the model. These extensions are again associated with rigorous theoretical approximation guarantees, exploiting the submodularity of the objective function. We demonstrate the advantages of our approach towards optimizing mutual information in a very extensive empirical study on two real-world data sets.

/pdf/near-optimal-sensor-placements-in-gaussian-processes-theory-b4fe67xmxz.pdf

Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies

Local binary pattern (LBP) is a nonparametric descriptor, which efficiently summarizes the local structures of images. In recent years, it has aroused increasing interest in many areas of image processing and computer vision and has shown its effectiveness in a number of applications, in particular for facial image analysis, including tasks as diverse as face detection, face recognition, facial expression analysis, and demographic classification. This paper presents a comprehensive survey of LBP methodology, including several more recent variations. As a typical application of the LBP approach, LBP-based facial image analysis is extensively reviewed, while its successful extensions, which deal with various tasks of facial image analysis, are also highlighted.

/pdf/local-binary-patterns-and-its-application-to-facial-image-1kaldi7ot7.pdf

Local Binary Patterns and Its Application to Facial Image Analysis: A Survey

This paper introduces a multilinear principal component analysis (MPCA) framework for tensor object feature extraction. Objects of interest in many computer vision and pattern recognition applications, such as 2D/3D images and video sequences are naturally described as tensors or multilinear arrays. The proposed framework performs feature extraction by determining a multilinear projection that captures most of the original tensorial input variation. The solution is iterative in nature and it proceeds by decomposing the original problem to a series of multiple projection subproblems. As part of this work, methods for subspace dimensionality determination are proposed and analyzed. It is shown that the MPCA framework discussed in this work supplants existing heterogeneous solutions such as the classical principal component analysis (PCA) and its 2D variant (2D PCA). Finally, a tensor object recognition system is proposed with the introduction of a discriminative tensor feature selection mechanism and a novel classification strategy, and applied to the problem of gait recognition. Results presented here indicate MPCA's utility as a feature extraction tool. It is shown that even without a fully optimized design, an MPCA-based gait recognition module achieves highly competitive performance and compares favorably to the state-of-the-art gait recognizers.

/pdf/mpca-multilinear-principal-component-analysis-of-tensor-2delrluhnt.pdf

MPCA: Multilinear Principal Component Analysis of Tensor Objects

We investigate the problem of automatically labelling appearances of characters in TV or film material. This is tremendously challenging due to the huge variation in imaged appearance of each character and the weakness and ambiguity of available annotation. However, we demonstrate that high precision can be achieved by combining multiple sources of information, both visual and textual. The principal novelties that we introduce are: (i) automatic generation of time stamped character annotation by aligning subtitles and transcripts; (ii) strengthening the supervisory information by identifying when characters are speaking; (iii) using complementary cues of face matching and clothing matching to propose common annotations for face tracks. Results are presented on episodes of the TV series “Buffy the Vampire Slayer”.

/pdf/hello-my-name-is-buffy-automatic-naming-of-characters-in-tv-2oaqege0tk.pdf

"Hello! My name is... Buffy" - Automatic Naming of Characters in TV Video

Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision research in general, has witnessed a growing interest in techniques that capitalize on this observation and apply algebraic and statistical tools for extraction and analysis of the underlying manifold. In this chapter, we describe in roughly chronologic order techniques that identify, parameterize, and analyze linear and nonlinear subspaces, from the original Eigenfaces technique to the recently introduced Bayesian method for probabilistic similarity analysis. We also discuss comparative experimental evaluation of some of these techniques as well as practical issues related to the application of subspace methods for varying pose, illumination, and expression.

/pdf/face-recognition-in-subspaces-892arc9jxp.pdf

Face Recognition in Subspaces

We present a discrete spectral framework for the sparse or cardinality-constrained solution of a generalized Rayleigh quotient. This NP-hard combinatorial optimization problem is central to supervised learning tasks such as sparse LDA, feature selection and relevance ranking for classification. We derive a new generalized form of the Inclusion Principle for variational eigenvalue bounds, leading to exact and optimal sparse linear discriminants using branch-and-bound search. An efficient greedy (approximate) technique is also presented. The generalization performance of our sparse LDA algorithms is demonstrated with real-world UCI ML benchmarks and compared to a leading SVM-based gene selection algorithm for cancer classification.

Generalized spectral bounds for sparse LDA

We present a user-centric system for visualization and layout for content-based image retrieval. Image features (visual and/or semantic) are used to display retrievals as thumbnails in a 2-D spatial layout or “configuration” which conveys all pair-wise mutual similarities. A graphical optimization technique is used to provide maximally uncluttered and informative layouts. Moreover, a novel subspace feature weighting technique can be used to modify 2-D layouts in a variety of context-dependent ways. An efficient computational technique for subspace weighting and re-estimation leads to a simple user-modeling framework whereby the system can learn to display query results based on layout examples (or relevance feedback) provided by the user. The resulting retrieval, browsing and visualization can adapt to the user's (time-varying) notions of content, context and preferences in style and interactive navigation. Monte Carlo simulations with machine-generated layouts as well as pilot user studies have demonstrated the ability of this framework to model or “mimic” users, by automatically generating layouts according to their preferences.

/pdf/visualization-and-user-modeling-for-browsing-personal-photo-52fefq4k3e.pdf

Visualization and User-Modeling for Browsing Personal Photo Libraries

Desktop computers are not designed for multi-person face-to-face conversation in a social setting. We describe the design of a novel user interface for multi-user interactive informal storytelling. Our design is guided by principles of experience sharing, the disappearing computer, visual navigation, and implicit query formulation.

Personal digital historian: user interface design

A method for representing an image in an image retrieval database first separates and filters images to extract color and texture features. The color and texture features of each image are partitioned into a plurality of blocks. A joint distribution of the color features and a joint distribution of the texture features are estimated for each block. The estimated joint distributions are stored in the database with each image to enable retrieval of the images by comparing the estimated joint distributions.

Baback Moghaddam

Papers

Face Recognition in Subspaces

Generalized spectral bounds for sparse LDA

Visualization and User-Modeling for Browsing Personal Photo Libraries

Personal digital historian: user interface design

Method for image retrieval with multiple regions of interest