Human Attribute Recognition by Rich Appearance Dictionary

By Jungseock Joo, Shuo Wang, Song-Chun Zhu. 2013

43 citations recorded by the source corpus.

We present a part-based approach to the problem of human attribute recognition from a single image of a human body. To recognize the attributes of human from the body parts, it is important to reliably detect the parts. This is a challenging task due to the geometric variation such as articulation and view-point changes as well as the appearance variation of the parts arisen from versatile clothing types. The prior works have primarily focused on handling geometric variation by relying on pre-trained part detectors or pose estimators, which require manual part annotation, but the appearance variation has been relatively neglected in these works. This paper explores the importance of the appearance variation, which is directly related to the main task, attribute recognition. To this end, we propose to learn a rich appearance part dictionary of human with significantly less supervision by decomposing image lattice into overlapping windows at multiscale and iteratively refining local appearance templates. We also present quantitative results in which our proposed method outperforms the existing approaches.

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, background): “Face attribute recognition is a task to classify various human attributes such as gender, race, age, emotions, expressions or other facial traits from facial appearance [31, 25, 74, 37].”
PANDA: Pose Aligned Networks for Deep Attribute Modeling (2013, methodology): “on that dataset as reported by [4], [27] and [14] respectively.”
Automated Facial Trait Judgment and Election Outcome Prediction: Social Dimensions of Face (2015, methodology): “In this paper we adopt a recent part learning approach in [18] learning the part dictionary directly from the images.”
Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose (2016, methodology): “Note that [8] did not use joint annotations during training, and [9] trained model on a different training dataset (25K images) which is much larger than the original set.”
Visual Persuasion: Inferring Communicative Intents of Images (2014, background): “Our paper is related to studies in computer vision on human attribute recognition [8, 22, 16, 13], such as gender, race, or facial expression recognition.”
FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation (2021, background): “The goal of face attribute recognition is to classify various human attributes such as gender, race, age, emotions, expressions or other facial traits from facial appearance [31, 24, 75, 37].”