Face Recognition from Long-Term Observations

By Gregory Shakhnarovich, John W. Fisher III, Trevor Darrell. European Conference on Computer Vision, 2002

315 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/31cc777d48b61d1186bae221f1f7a3321441a741

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Statistics and Probability

Citations in the corpus

Meta-Recognition: The Theory and Practice of Recognition Score Analysis (2011, unknown): “Ç”
From sample similarity to ensemble similarity: probabilistic distance measures in reproducing kernel Hilbert space (2006, methodology): “7 shows a misclassification example in [37], where the fourth probe person is misclassified as the ninth gallery person, while one of our approaches (the KL divergence in the RKHS induced by the matrix RBF kernel) corrected this error.”
Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification (2015, background): “Another type of SPD matrix is the resulting matrix of Gaussian distribution, which is exploited by a few works (Shakhnarovich et al., 2002; Arandjelović et al., 2005; Huang et al., 2015b; Wang et al., 2015) to capture the entire probabilistic model of object variations for more robust image set…”
Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations (2007, unknown): “Relevant previous approaches to set matching for set classification can be broadly partitioned into parametric model-based [17], [34] and nonparametric sample-based methods [12], [14].”
Grassmann discriminant analysis: a unifying view on subspace-based learning (2008, background): “Copyright 2008 by the author(s)/owner(s). the similarity between image vectors (Shakhnarovich et al., 2002; Kondor & Jebara, 2003; Zhou & Chellappa, 2006).”
Multi-manifold deep metric learning for image set classification (2015, methodology): “…set classiﬁcation has been an important problem in computer vision in recent years [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 15, 16, 18, 22, 24, 26, 27, 28, 29, 34, 35, 36, 37, 38, 39, 40], especially when more and more data are easily accessible and multiple images of the same object are easily…”
Face recognition in unconstrained videos with matched background similarity (2011, background): “Thus, recognition becomes a problem of determining the similarity between vector sets, which can be modeled as distributions [12], subspaces [24, 26], or more general manifolds [7, 11, 19].”
Manifold-Manifold Distance with application to face recognition based on image set (2008, unknown): “Representative parametric methods include [1], [19].”
Probabilistic Face Embeddings (2019, background): “In the field of face template/video matching, there exists abundant literature on modeling the faces as probabilistic distributions [29, 1], subspace [3] or manifolds [1, 11] in the feature space.”
Face recognition with image sets using manifold density divergence (2005, methodology): “We believe that this restriction explains the variable results attributed to these methods [24, 27], since it does not capture non-linear variation in appearance due to illumination and pose changes.”
Covariance discriminative learning: A natural and efficient approach to image set classification (2012, methodology): “Parametric modeling methods seek to represent each image set with some parametric distribution function, e.g., single Gaussian [22] or Gaussian mixture models (GMM) [1], and then measure the similarity between two distributions in terms of the Kullback-Leibler Divergence (KLD).”
Video-based face recognition using probabilistic appearance manifolds (2003, background): “We conclude with remarks and future work in Section 5.”
Manifold Discriminant Analysis (2009, methodology): “Typical model-based methods [1], [21], tend to represent image set by parametric distribution function, and then measure the similarity between two distributions.”