Describable Visual Attributes for Face Verification and Image Search

By Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, Shree K. Nayar. 2011

500 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, methodology): “PubFig [31] Celebrity 13K X Model generated predictions no”
Describing Textures in the Wild (2013, background): “Recently visual attributes have raised significant interest in the community [6, 11, 17, 25].”
Diversity in Faces (2019, methodology): “Many other data sets have been proposed for different facial analysis tasks, such as age and gender classification [24, 27, 31, 54–56], facial expression analysis [55], memorability [57], attributes [35] and aging [58].”
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (2015, background): “, due to backgrounds and hair style [19], that may occur in LFW.”
Probabilistic Elastic Matching for Pose Variant Face Verification (2013, methodology): “Face recognition has remained an active research topic in computer vision for decades [17, 32, 31, 22, 2, 11, 1, 21, 30, 14, 18, 29, 7].”
MegaFace: A Million Faces for Recognition at Scale (2015, background): “Since all the identities in the FaceScrub dataset (our test set) are celebrities, human recognition rates may be biased due to familiarity with the person [22].”
Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose (2016, unknown): “, hair style and glasses) [26].”
Continuous User Authentication on Mobile Devices: Recent progress and remaining challenges (2016, methodology): “Visual attributes are essentially labels that can be given to an image to describe its appearance [30].”
Learning Discriminant Face Descriptor (2014, background): “[23] have proposed attribute and simile representations for face recognition.”
Self-supervised learning of a facial attribute embedding from video (2018, background): “for pose or expression, the embedding can be learned by training in a supervised manner to directly predict the attribute [28, 32, 46], or to generate images (of faces, cars, or other classes) at a new, known pose, expression, etc.”
Demographic Estimation from Face Images: Human vs. Machine Performance (2015, methodology): “There has been a growing interest in automatic extraction of demographic information from face images or videos, due to many emerging applications [2], [4], [5], [6].”
Discovering Attribute Shades of Meaning with the Crowd (2015, methodology): “Standard, which is the standard consensus approach used in (Ferrari and Zisserman 2007; Kumar et al. 2011; Lampert et al. 2009; Farhadi et al. 2009; Vaquero et al. 2009; Branson et al. 2010; Wang and Mori 2010; Patterson and Hays 2012); 2.”
From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, methodology): “The study of visual texture attributes [17, 34, 151] was motivated by the significant interest raised by visual attributes [58, 176, 175, 105].”
Attribute relation learning for zero-shot classification (2014, methodology): “Consequently, a class of attribute-based methods in face verification [6], image annotation [14], image Contents lists available at ScienceDirect”
FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation (2021, unknown): “…image datasets [21, 31, 13, 70, 37, 23, 43, 69, 14, 26, 48, 8, 40] have been proposed and fostered research and development for automated face detection [35, 20], alignment [67, 46], recognition [57, 51], generation [68, 5, 25, 58], modiﬁcation [3, 32, 18], and attribute classiﬁcation [31, 37].”
Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification (2012, methodology): “[18, 19] also adopt this two-level classifier structure, using a set of attribute (gender, race, hair color, etc.”
Attribute-Based Classification for Zero-Shot Visual Object Categorization (background): “Numerous follow-up papers have explored even more applications of attributes in computer vision tasks, e.g. for scene classification [46], face verification [35], action recognition [47] and surveillance [48].”