The CASIA NIR-VIS 2.0 Face Database

By S. Li, Dong Yi, Zhen Lei, Shengcai Liao. 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2013

329 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4f0a1a7f9b25cd4ccbb9b1709692be12293ea60e

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

1. Xiaogang Wang
2. Yi Yang
3. Dacheng Tao
4. Ran He
5. Luc Van Gool
6. Jiwen Lu
7. Zhen Lei
8. S. Li

In Signal Processing

1. Ran He
2. Zhenan Sun
3. Zhen Lei
4. Tien-Ping Tan
5. Xiang Wu
6. S. Li
7. Jie Zhou
8. Xiangyu Zhu

Citations in the corpus

• Frankenstein: Learning Deep Face Representations Using Small Data (2016, unknown): “D. NIR-VIS face recognition 1) Database and protocol: The largest face database across NIR and VIS spectrum so far is the CASIA NIR-VIS 2.0 face database [23].”
• Learning Compact Binary Face Descriptor for Face Recognition (2015, methodology): “0 dataset [33] was used for heterogeneous face matching evaluation.”
• A Light CNN for Deep Face Representation With Noisy Labels (2015, unknown): “0 database [18] for heterogeneous face recognition.”
• Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition (2017, methodology): “, lightings, poses, and expressions) [4], [18], [19], we divide the highlevel layer of the WCNN into two orthogonal subspaces that contain modality-invariant identity information and modality-variant spectrum information.”
• Learning an Evolutionary Embedding via Massive Knowledge Distillation (2020, methodology): “0 Face database [28], OuluCASIA NIR-VIS database [3] and BUAA-VisNir face database [19], are used for evaluations.”
• Learning Meta Face Recognition in Unseen Domains (2020, methodology): “0, we follow the standard protocol in View 2 evaluation [31] and we report the average value of 10 folds.”
• Deep Face Recognition: A Survey (2018, unknown): “c [169] 1:N: 69.96% MAP (2004-2006)[214] cross-age, 14 to 62 years old (IV-C) FG-NET [1] 2010 1,002 82 12.2 1:N: Rank-N (CMC) 88.1% Rank-1 [169] cross-age, 0 to 69 years old (IV-C) CASIA NIR-VIS v2.0 [89] 2013 17,580 725 24.2 1:1: Acc, VR vs. FAR (ROC) 98.62% Acc, 98.32%@10−3FAR [177] NIR-VIS; with ”