Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval

By Bor-Chun Chen, Chu-Song Chen, Winston H. Hsu. 2014

425 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

GAN Inversion: A Survey (2021, background): “7 3 7 3 7 7 [16] [14], [16], [47] GH-Feat [104] 2020, arxiv L.”
How Image Degradations Affect Deep CNN-Based Face Recognition? (2016, methodology): “Finetuning has been done using a combination of the following datasets: CASIA-Webface [14], FaceScrub [15], and CACD [16].”
Learning latent representations across multiple data domains using Lifelong VAEGAN (2020, background): “3-a and 3-b, for CelebA to CACD and CelebA to 3D-chair lifelong learning, respectively.”
Age Progression/Regression by Conditional Adversarial Autoencoder (2017, methodology): “We ﬁrst collect face images from the Morph dataset [11] and the CACD [2] dataset.”
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (2015, background): “In the future, datasets like [5, 9] can be easily incorporated into our benchmark.”
Learning Face Representation from Scratch (2014, background): “The scale of CACD is large enough to train deep models but the dataset contains much noise and incorrect identity labels.”
Person Recognition in Personal Photo Collections (2015, methodology): “To measure the effect of training on larger data we consider fine-tuning using two open face recognition datasets: CASIA-WebFace (CASIA) [40] and the “Cross-Age Reference Coding Dataset” (CACD) [6].”
Lifelong Twin Generative Adversarial Networks (2021, background): “The results generated after the lifelong learning one database under the CelebA [21] to CACD [22], and CelebA to 3D-Chair database lifelong learning, shown in Fig.”
Cross-Domain Similarity Learning for Face Recognition in Unseen Domains (2021, methodology): “First, we considered an experiment using the Cross-Age Celebrity Dataset (CACD-VS) [4].”
Collaborative Learning for Faster StyleGAN Embedding (2020, methodology): “We evaluate our framework on two datasets: CelebAHQ [17] and CACD [6], which represent challenges in different aspects.”
Deep Face Recognition: A Survey (2018, background): “c [161] (VI-C3) [15] 2013 2,802 265 – OC) 95.67%@ 10 2 [161] (VI-C3) [107] 2008 1,910 47 – (CMC) [160] (VI-C3) [271] 12174 4025 2/3/4 OC) [25] (VI-A2) [164] 2006 55,134 13,618 4.1 (CMC) [121] (VI-A2) [26] 2014 163,446 2000 81.7 OC) MAP [217] (2004-2006)[270] (VI-A2) [1] 2010 1,002 82 12.2 (CMC) [217”
Person Recognition in Personal Photo Collections (2017, methodology): “Although smaller in total number of images than CASIA, CACD features greater number of samples per identity ( 2 Þ.”
DEX: Deep EXpectation of Apparent Age from a Single Image (2015, background): “There are numerous studies [1] [3] [6] and several large datasets [1] [9] [11] on the (biological, real) age estimation based on a single face image.”
Face Recognition and Retrieval Using Cross-Age Reference Coding With Cross-Age Celebrity Dataset (2015, background): “The preliminary results have been published in [29], and the contributions are presented here as a whole.”
Cost-Effective Active Learning for Deep Image Classification (2017, methodology): “, CACD [1] and the Caltech-256 object categorization [2] data set (see Fig.”
Rank consistent ordinal regression for neural networks with application to age estimation (2019, methodology): “The CACD dataset (Chen et al., 2014) was downloaded from http://bcsiriuschen.”
Lifelong Generative Modelling Using Dynamic Expansion Graph Model (2021, background): “…various models under CCCOSCZC lifelong learning setting, where each task is associated with one of the datasets: CelebA (Liu et al. 2015), CACD (Chen, Chen, and Hsu 2014), 3D-Chair (Aubry et al. 2014), Ommiglot (Lake, Salakhutdinov, and Tenenbaum 2015), ImageNet* (Krizhevsky, Sutskever, and…”
AgeDB: The First Manually Collected, In-the-Wild Age Database (2017, methodology): “In 2014, Cross-Age Celebrity Dataset (CACD) [4, 5] was introduced, containing 163,446 “in-the-wild” images of 2,000 celebrities.”