Face Recognition with Image Sets Using Manifold Density Divergence

Arandjelović, Ognjen; Shakhnarovich, Gregory; Fisher, John W.; Cipolla, Roberto; Darrell, Trevor

doi:10.1109/cvpr.2005.151

Cited by 231 publications

(207 citation statements)

References 24 publications

Supporting

Mentioning

203

Contrasting

Order By: Relevance

“…Generally speaking, research on face recognition focuses much on exploring the distribution [5] or structure of the data sets [6][7][8] and designing the between-set distance [9,2], while in the literature of person reidentification, more attention has been paid to feature representation [3,10,4]. Such a phenomenon to some extent is due to the differences between these two categories: usually human bodies have greater appearance variations and occlusions than faces, causing difficulties for feature representation.…”

Section: Related Workmentioning

confidence: 99%

Set Based Discriminative Ranking for Recognition

Minoh

Lao

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract.Recently both face recognition and body-based person reidentification have been extended from single-image based scenarios to video-based or even more generally image-set based problems. Set-based recognition brings new research and application opportunities while at the same time raises great modeling and optimization challenges. How to make the best use of the available multiple samples for each individual while at the same time not be disturbed by the great within-set variations is considered by us to be the major issue. Due to the difficulty of designing a global optimal learning model, most existing solutions are still based on unsupervised matching, which can be further categorized into three groups: a) set-based signature generation, b) direct set-to-set matching, and c) between-set distance finding. The first two count on good feature representation while the third explores data set structure and set-based distance measurement. The main shortage of them is the lack of learning-based discrimination ability. In this paper, we propose a set-based discriminative ranking model (SBDR), which iterates between set-to-set distance finding and discriminative feature space projection to achieve simultaneous optimization of these two. Extensive experiments on widely-used face recognition and person re-identification datasets not only demonstrate the superiority of our approach, but also shed some light on its properties and application domain.

show abstract

Section: Related Workmentioning

confidence: 99%

Set Based Discriminative Ranking for Recognition

Minoh

Lao

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

show abstract

“…By taking into account temporal coherence, face dynamics (such as non-rigid facial expressions and rigid head movements) within the video sequence are modeled and exploited to enforce recognition. The third class [110,93,10,59,106] also uses all face images, but does not assume temporal coherence between consecutive images; the problem was treated as an image-set matching problem. The distributions of face images in each set are modeled and compared for recognition, and the existing work can be further divided into statistical model-based and mutual subspace-based methods (see Section 3.3 for details).…”

Section: Face Recognition In Videomentioning

confidence: 99%

“…Method Key-frame based Approaches [90], [40], [47], [114], [100], [17], [115], [31], [78], [85], [98], [101], [118] Temporal Model based Approaches [74], [73], [72], [75], [18], [24], [67], [69], [68], [122], [120], [123], [121], [64], [65], [66], [79], [55], [2], [43], [50], [49] Image-Set Matching based Approaches Statistical model-based [93], [4], [96], [7], [10], [6], [9] Mutual subspace-based [110], [90], [35], [82], [108], [56], [57], [5]<...>…”

Section: Categorymentioning

confidence: 99%

“…These approaches have been discussed in Section 3.1. Parametric model-based approaches tend to represent each image set by a parametric distribution and then measure the similarity between two distributions [93,7,10]. This is based on the assumption that images are drawn from some distributions on the underlying face pattern manifold, and normally statistical learning algorithms are adopted to model the distribution.…”

Section: Image-set Matching Based Approachesmentioning

confidence: 99%

“…To deal with nonlinear variations in face appearance due to illumination and pose changes, Arandjelovic et al [10] model the face appearance distribution as Gaussian Mixture Models (GMMs) on low-dimensional manifolds. The KL divergence was adopted to measure the similarity between the estimated distributions.…”

Section: Statistical Model-based Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Face Recognition and Retrieval in Video

Shan¹

2010

Video Search and Mining

View full text Add to dashboard Cite

Abstract. Automatic face recognition has long been established as one of the most active research areas in computer vision. Face recognition in unconstrained environments remains challenging for most practical applications. In contrast to traditional still-image based approaches, recently the research focus has shifted towards videobased approaches. Video data provides rich and redundant information, which can be exploited to resolve the inherent ambiguities of image-based recognition like sensitivity to low resolution, pose variations and occlusion, leading to more accurate and robust recognition. Face recognition has also been considered in the content-based video retrieval setup, for example, character-based video search. In this chapter, we review existing research on face recognition and retrieval in video. The relevant techniques are comprehensively surveyed and discussed.

show abstract

Computing the matrix geometric mean: Riemannian versus Euclidean conditioning, implementation techniques, and a Riemannian BFGS method

Yuan

Huang

Absil

et al. 2020

Numerical Linear Algebra App

View full text Add to dashboard Cite

Summary This paper addresses the problem of computing the Riemannian center of mass of a collection of symmetric positive definite matrices. We show in detail that the condition number of the Riemannian Hessian of the underlying optimization problem is never very ill conditioned in practice, which explains why the Riemannian steepest descent approach has been observed to perform well. We also show theoretically and empirically that this property is not shared by the Euclidean Hessian. We then present a limited‐memory Riemannian BFGS method to handle this computational task. We also provide methods to produce efficient numerical representations of geometric objects that are required for Riemannian optimization methods on the manifold of symmetric positive definite matrices. Through empirical results and a computational complexity analysis, we demonstrate the robust behavior of the limited‐memory Riemannian BFGS method and the efficiency of our implementation when compared to state‐of‐the‐art algorithms.

show abstract

Face Recognition with Image Sets Using Manifold Density Divergence

Abstract: Abstract

Cited by 231 publications

References 24 publications

Set Based Discriminative Ranking for Recognition

Set Based Discriminative Ranking for Recognition

Face Recognition and Retrieval in Video

Computing the matrix geometric mean: Riemannian versus Euclidean conditioning, implementation techniques, and a Riemannian BFGS method

Contact Info

Product

Resources

About