CACD

Cross-Age Celebrity Dataset

Dataset Information
Modalities
Images
Introduced
2014
Homepage

Overview

The Cross-Age Celebrity Dataset (CACD) contains 163,446 images from 2,000 celebrities collected from the Internet. The images are collected from search engines using celebrity name and year (2004-2013) as keywords. Therefore, it is possible to estimate the ages of the celebrities on the images by simply subtract the birth year from the year of which the photo was taken.

Source: https://bcsiriuschen.github.io/CARC/
Image Source: https://www.pkuml.org/resources/pku-vehicleid.html

Variants: CACD

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Age Estimation MiVOLO-V2 Beyond Specialization: Assessing the Capabilities … 2024-03-04
Age Estimation ResNet-50-Cross-Entropy A Call to Reflect on … 2023-07-10
Age Estimation ResNet-50-DLDL A Call to Reflect on … 2023-07-10
Age Estimation ResNet-50-DLDL-v2 A Call to Reflect on … 2023-07-10
Age Estimation ResNet-50-SORD A Call to Reflect on … 2023-07-10
Age Estimation FaRL+MLP A Call to Reflect on … 2023-07-10
Age Estimation ResNet-50-OR-CNN A Call to Reflect on … 2023-07-10
Age Estimation ResNet-50-Regression A Call to Reflect on … 2023-07-10
Age Estimation ResNet-50-Mean-Variance A Call to Reflect on … 2023-07-10
Age Estimation ResNet-50-Unimodal-Concentrated A Call to Reflect on … 2023-07-10
Age Estimation MWR Moving Window Regression: A Novel … 2022-03-24
Age Estimation RNDF Facial age estimation by deep … 2019-08-28
Age Estimation CORAL Rank consistent ordinal regression for … 2019-01-20

Research Papers

Recent papers with results on this dataset: