Probabilistic recognition of human faces from video

By Shaohua Kevin Zhou, Volker Krüger, Ramalingam Chellappa. Proceedings. International Conference on Image Processing, 2002

344 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3a7877effc33e4d9bff0c7251f8772f06982d779

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations (2007, result): “Whereas most of the previous work on matching image sets for object recognition exploits temporal coherence between consecutive images [20], [21], [11], [22], [28], this study does not make any such assumption.”
Face tracking and recognition with visual constraints in real-world videos (2008, background): “For instance, a state-space model was proposed in [5] for classifying videos where state dynamics separates different subjects.”
Face recognition: A literature survey (2003, methodology): “While most face recognition algorithms take still images as probe inputs, a videobased face recognition approach that takes video sequences as inputs has recently been developed [Zhou et al. 2003].”
Face recognition with image sets using manifold density divergence (2005, methodology): “[30] the joint probability distribution of identity and motion is modelled using sequential importance sampling, yielding the recognition decision by marginalization.”
AdaFace: Quality Adaptive Margin for Face Recognition (2022, methodology): “To perform quality aware fusion, probabilistic approaches have been proposed to predict uncertainty in FR representation [5, 21, 30, 33, 51].”
Handbook of Face Recognition, 2nd Edition (2011, background): “we have been able to show [30] that the posterior probability for the correct identity l, p(nt = l|z0:t), is lower-bounded by an increasing curve which converges to 1.”
Visual tracking and recognition using appearance-adaptive models in particle filters (2004, background): “While conventional methods [14] resolve these uncertainties separately, i.e., tracking followed by recognition, we have proposed in [7] a framework to model both uncertainties in a unified way to realize simultaneous tracking and recognition.”