Attribute and simile classifiers for face verification

By Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, Shree K. Nayar. 2009

1,717 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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 Signal Processing

Citations in the corpus

Grounded Compositional Semantics for Finding and Describing Images with Sentences (2014, background): “, 2012), there is also work on attribute classification and other mid-level elements (Kumar et al., 2009), some of which we hope to capture with our approach as well.”
Generative Adversarial Text to Image Synthesis (2016, background): “Traditionally this type of detailed visual information about an object has been captured in attribute representations distinguishing characteristics the object category encoded into a vector (Farhadi et al., 2009; Kumar et al., 2009; Parikh & Grauman, 2011; Lampert et al., 2014), in particular to en”
Deep Learning Face Attributes in the Wild (2014, background): “[15] predicted face attributes by extracting hand-crafted features from ten face parts.”
Autoencoding beyond pixels using a learned similarity metric (2015, methodology): “To imitate the original experiment, we use Labeled faces in the wild (LFW) images (Huang et al., 2007) with attributes (Kumar et al., 2009).”
Attribute2Image: Conditional Image Generation from Visual Attributes (2015, methodology): “[24] that describes different aspects of facial appearance such as age, gender, or facial expression, etc.”
Machine Learning Models that Remember Too Much (2017, methodology): “For the gender classification task, we use additional attribute labels [42].”
Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition (2016, methodology): “To test this approach, we randomly selected 20 frontal images from the PubFig [21] face dataset, and tested whether each could be permuted to evade detection by fooling the first classifier in the cascade.”
Faceless Person Recognition: Privacy Implications in Social Media (2016, background): “Various other cues have been explored, for example: attributes classification [40, 41], social context [42, 43], relative camera positions [44], space-time priors [45], and photo-album priors [46].”
Concept Bottleneck Models (2020, background): “Earlier versions of concept bottleneck models were overtaken in predictive accuracy by end-to-end neural networks (e.g., Kumar et al. (2009) for face recognition and Lampert et al. (2009) for animal identification), leading to a perceived tradeoff between accuracy and interpretability in terms of…”
PANDA: Pose Aligned Networks for Deep Attribute Modeling (2013, methodology): “We also used the publicly available gender scores of [16] to compute the average precision of their system on the test subset.”
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (2015, neutral): “Note also that [23] and [32] are contemporaneous, as their arxiv papers appeared after ours [2].”
Learning Face Representation from Scratch (2014, methodology): “In 2009, based on the name list of LFW [11] collected another good dataset named as PubFig.”
Label-Embedding for Image Classification (2015, neutral): “Attributes have been used for image description [19], [18], [9], caption generation [27], [41], face recognition [29], [51], [10], image retrieval [28], [56], [15], action recognition [32], [69], novelty detection [62] and object classiﬁcation [30], [18], [64], [65], [34], [54], [38].”
Web-scale training for face identification (2014, background): “1Using the biased [14, 19] background to improve performance is not in the scope of this work.”
Surpassing Human-Level Face Verification Performance on LFW with GaussianFace (2014, methodology): “), and the parameters of the models in (Li et al. 2013; Berg and Belhumeur 2012; Kumar et al. 2009; Simonyan et al. 2013) (for example, the number of Gaussians, the number of classifiers, etc.”
Deeply learned face representations are sparse, selective, and robust (2014, background): “There have been works on ﬁrst learning attribute classiﬁers and using attribute predictions for face recognition [18, 8].”
Multi-Task CNN Model for Attribute Prediction (2015, neutral): “Typically, discriminative learning approaches are used to learn semantic attributes (attributes that have names)[13], [27], [30].”
Person Recognition in Personal Photo Collections (2015, background): “Multiple other cues have been explored, for example: attributes classification [24, 25], explicit cloth modelling [15], relative camera positions [18], social context [16, 35], space-time priors [28], and photo-album priors [34].”
Recover Canonical-View Faces in the Wild with Deep Neural Networks (2014, methodology): “PubFig [23] and WDRef [12] are two larg巳r datasets than LFW. How巳ver， PubFig only has 200 people , which means the identity variation is insufficient , while WDRef is not publicly available.”