A Deep Sum-Product Architecture for Robust Facial Attributes Analysis

By Ping Luo, Xiaogang Wang, Xiaoou Tang. 2013

85 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

3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, background): “On the other hand, the past few years have seen a resurgence of research in the design of deep neural networks, and impressive progresses were made on learning image features from raw data [7, 27, 12, 11, 17, 5].”
Deeply learned face representations are sparse, selective, and robust (2014, neutral): “Attribute learning is an active topic [9, 21, 20, 36].”
A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition (2015, unknown): “In this way, the configuration of the CNNs are dynamically adjusted together with searching for the appropriate latent variables of input videos.”
Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, background): “Index Terms—Face Alignment, face landmark detection, deep learning, convolutional network Ç”
Pedestrian Parsing via Deep Decompositional Network (2013, background): “Instead of completing the missing data, Luo et al. [13] marginalized missing data with proposed deep sum product network for facial attribute recognition.”
DeepID-Net: Deformable deep convolutional neural networks for object detection (2014, background): “Because of the power on learning feature representation, deep models have been widely used for object recognition, detection and other vision tasks [36, 54, 19, 37, 61, 17, 22, 14, 28, 30, 55, 56, 27, 23, 41, 43, 41, 42, 25, 26, 24, 58].”
Facial Landmark Detection by Deep Multi-task Learning (2014, background): “This study aims to investigate the possibility of optimizing facial landmark detection (the main task) with related/auxiliary tasks, which include head pose estimation, gender classification, age estimation [6], facial expression recognition, or facial attribute inference [17].”
Deep domain adaptation for describing people based on fine-grained clothing attributes (2015, background): “Deep Convolutional Neural Networks have recently achieved dramatic accuracy improvements in image classification [26], object detection [13], and many other computer vision areas, including attribute modeling [46, 34].”
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach (2017, background): “The sum-product network (SPN) adopted in [19] for modeling attribute correlations may not be feasible because of the exponentially growing number of attribute group combinations.”
DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks (2017, unknown): “Because of the power on learning feature representation, deep models have been widely used for object recognition, detection and other vision tasks [1], [6], [7], [19], [20], [21], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47],”
Learning Social Relation Traits from Face Images (2015, background): “face parsing [25], face landmark detection [42], face attribute prediction [24, 26], and face recognition [33, 43].”
Pedestrian Attribute Recognition At Far Distance (2014, background): “[12], for the applications such as image retrieval and recommendation systems [3, 7, 11].”
Deep Learning Face Attributes in the Wild (2014, background): “Deep learning [18, 34, 23, 7, 19, 32, 31, 13, 33, 22, 3, 28] recently achieved great success in attribute prediction, due to their ability to learn compact and discriminative features.”
Learning Attributes Equals Multi-Source Domain Generalization (2016, methodology): “recent work has applied deep models to attribute detection [11, 83, 47, 16].”
Multi-source Deep Learning for Human Pose Estimation (2014, background): “Deep learning has achieved spectacular progress in computer vision [43, 19, 25, 35, 22, 56, 11, 41, 38, 48, 47, 57, 37, 36, 29, 31, 30, 28, 58, 27].”
Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations (2014, methodology): “Deep learning methods, such as Boltzmann machine [9], sum product network [17], and deep neural net [16, 25, 22, 23, 24, 26] have been applied to face recognition.”