Coupled information-theoretic encoding for face photo-sketch recognition

By Wayne Zhang, Xiaogang Wang, Xiaoou Tang. Computer Vision and Pattern Recognition, 2011

397 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/013896c2ae9533be88f285a031ce839c672078b5

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

In Signal Processing

Citations in the corpus

DualGAN: Unsupervised Dual Learning for Image-to-Image Translation (2017, methodology): “To compare DualGAN with GAN and cGAN [4], four labeled datasets are used: PHOTO-SKETCH [22, 25], DAY-NIGHT [5], LABEL-FACADES [20], and AERIALMAPS, which was directly captured from Google Map [4].”
Deep Face Recognition: A Survey (2018, neutral): “c, VR vs. FAR (ROC) 97.58% Acc, 85.00%@10−3FAR [125] NIR-VIS; with eyeglasses and expression variation (IV-F) CUFS [166] 2009 1,212 606 2 1:N: Rank-N (CMC) 100% Rank-1 [201] sketch-photo (IV-G) CUFSF [204] 2011 2,388 1,194 2 1:N: Rank-N (CMC) 51.00% Rank-1 [163] sketch-photo; lighting variation; sha”
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation (2020, methodology): “In Figure 9 we provide a visual comparison of the competing approaches on the CelebAMask-HQ dataset containing 19 semantic categories.”
Learning from the Past: Meta-Continual Learning with Knowledge Embedding for Jointly Sketch, Cartoon, and Caricature Face Recognition (2020, methodology): “Sketch Face Recognition We evaluate our approach on two tasks in sketch datasets: photograph to sketch recognition and sketch to photograph recognition on CUFS dataset [30, 47], CUFSF dataset [47, 52], IIIT-D Sketch dataset [2], PRIP-VSGC dataset [3, 18], PRIP-HDC dataset [23], MGDB dataset [35], Uo”
Cross-Domain Adversarial Feature Learning for Sketch Re-identification (2018, methodology): “5, we compare our sketch Re-ID dataset with other two sketch datasets including CUFSF dataset [32] and QMUL-shoe dataset [29].”
Face Alignment at 3000 FPS via Regressing Local Binary Features (2014, methodology): “Ensemble trees can be used as a codebook for efficient encoding [22] or learning better descriptors [6] [33].”
A Practical Transfer Learning Algorithm for Face Verification (2013, methodology): “proposed a coupled information-theoretic encoding method [28] to narrow the distribution gap of the encoded features.”
Deep Learning Identity-Preserving Face Space (2013, background): “[35] extended [4] by introducing an inter-modality encoding method, which can match face images in two modalities, e.”
The CASIA NIR-VIS 2.0 Face Database (2013, methodology): “To our knowledge, there are five existing heterogeneous face databases: CUHK Face Sketch Database (CUFS) [16], CUHK Face Sketch FERET Database (CUFSF) [21], MSU Forensic Sketch Database [4], CASIA HFB Database (HFB) [7], and Long Distance Heterogeneous Face Database (LDHF-DB) [12].”
Learning Discriminant Face Descriptor (2014, methodology): “1), Zhang et al. [40] have proposed a coupled encoding method at the third step to reduce the difference of heterogeneous features.”
A Comprehensive Survey to Face Hallucination (2013, methodology): “As is shown in Liu et al. (2007b), Wang et al. (2011), and Zhang et al. (2011a), most available methods for FSPS averaged the overlapping regions, which may result in over-smoothing, and the residual image could therefore be learned from the training images to compensate for the lost high frequency…”
Face Recognition Vendor Test (FRVT) Performance of Face Identification Algorithms NIST IR 8009 (2014, background): “” The data was collected to support research into synthesis and recognition of sketches [25, 28].”
Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation (2020, background): “ID Dataset Name Image# Description ID Dataset Name Image# Description 1 CUFSF [19] 1,194 face sketch 2 COCO [20] 10,000 real 3 PASCAL [21] 10,000 realh 4 DomainNet [8] 10,000 real 5 SYNTHIA [22] 10,000 street syn 6 UIUC CAR [23] 1,220 car 7 ZuDuB [24] 210 building 8 Bark-101 [25] 2,586 bark 9 Domain”