Learning Compact Binary Face Descriptor for Face Recognition

By Jiwen Lu, Venice Erin Liong, Xiuzhuang Zhou, Jie Zhou. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

380 citations recorded by the source corpus.

How researchers see this paper

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

Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (2017, methodology): “Related Work Hashing techniques [42, 16, 34, 62, 39, 30, 55, 35, 17, 14, 74, 36, 14, 70, 37, 47, 38, 54, 25, 33, 41] have recently been successfully applied to encode highdimensional features into compact similarity-preserving binary codes, which enables extremely fast similarity search by the use o”
Handcrafted vs. non-handcrafted features for computer vision classification (2017, methodology): “Let , - be the training set containing N samples, where is the n- th pixel difference vector and the aim of CBD is to learn K hash functions that map and quantize each into a binary vector , - * + that more compactly encodes the discriminative information.”
Frankenstein: Learning Deep Face Representations Using Small Data (2016, methodology): “We will explore the relative merit of both types of synthetic images in our experiments.”