Cumulative Attribute Space for Age and Crowd Density Estimation

By Ke Chen, Shaogang Gong, Tao A. Xiang, Chen Change Loy. 2013

451 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

Transductive Multi-View Zero-Shot Learning (2015, methodology): “Zero-shot learning Multi-class single label zero-shot learning has now been widely studied using attribute-based intermediate semantic layers [3, 6, 10, 11, 19, 25] or data-driven [8, 9, 21, 30] representations.”
Distribution Matching for Crowd Counting (2020, methodology): “Later methods [5, 6, 49, 7] avoid the detection problem and directly learn to regress the count from a feature vector.”
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network (2017, methodology): “Several methods [3, 6, 7, 8, 15] try to predict counts by using global regressors trained with low-level features.”
Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, background): “tial auxiliary tasks include head pose estimation, gender classification, age estimation [15], facial expression recognition, or facial attribute inference [16].”
COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation (2015, methodology): “We achieved the state-of-the-art performance on all three metrics, and improved the mean absolute error (mae) by 27% relative to the best previous result on the Mall dataset [10].”
Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (2018, methodology): “Earlier regression-based approaches mapped global image features or a combination of local patch features to obtain counts [15], [5], [12], [6].”
Imbalanced Deep Learning by Minority Class Incremental Rectification (2018, background): “Automatic recognition of these nameable properties is very useful [14,15], but challenging for model learning due to: (1) Very large scale imbalanced training data [10,16,17], with clothing and facial attribute labelled data exhibiting power-law distributions (Fig.”
Class Rectification Hard Mining for Imbalanced Deep Learning (2017, background): “…and facial characteristics, is very useful [17, 15], but also challenging due to: (1) Very large scale training data with signiﬁcantly imbalanced distributions on annotated attribute data [1, 6, 21], with clothing and face attributes typically exhibiting a power-law distribution (Figure 1).”
Fine-Grained Visual Comparisons with Local Learning (2014, methodology): “Aside from learning to rank formulations, researchers have applied the Elo rating system for biometrics [29], and regression over “cumulative attributes” for age and crowd density estimation [9].”
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding (2018, methodology): “Counting by regression: Counting by regression approaches differs depending on the target of regression: object count [5, 4], or object density [15].”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, methodology): “Various approaches have been proposed to tackle the problem of crowd counting in images [41, 19, 52, 107, 111] and videos [12, 35, 77, 21].”
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].”
Learning Multi-Level Density Maps for Crowd Counting (2020, background): “Over the last few years, a variety of approaches have been proposed to tackle crowd counting problem in images and videos, including traditional methods [17]–[21] and CNN-based ones [12], [13], [15], [22]–[25].”
Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks (2016, methodology): “…Geng et al. [18] introduce AGES (AGing pat-tErn Subspace), Zhang et al. [61] propose a multi-task warped gaussian process (MTWGP), Chen et al. [4] derive CA-SVR with a cumulative attribute space and SVR, Chang et al. [1] rank hyperplanes for age estimation (OHRank), Huerta et al. [29] fuse…”
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (2016, unknown): “97 Cumulative Attribute Regression [6] 2.”
Understanding Traffic Density from Large-Scale Web Camera Data (2017, unknown): “Cumulative Attribute Regression [5] 2.”
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (2018, unknown): “[46] 2.”