Yue Wu

Yue Wu

Auto-generated profile, based on publicly available information

Yue Wu

The Information Sciences Institute University of Southern California Marina del Rey USA

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2013 in Information Sciences
Verified
Journal Article
Closed access
YWYue Wu
Yue Wu
YZYicong Zhou
Yicong Zhou
GSGeorge Saveriades
George Saveriades
SASos Agaian
Sos Agaian
JNJoseph P. Noonan
Joseph P. Noonan
PNPremkumar Natarajan
Premkumar Natarajan

1 October 2018
Verified
Conference Paper
Closed access
IMIacopo Masi
Iacopo Masi
YWYue Wu
Yue Wu
THTal Hassner
Tal Hassner
PNPrem Natarajan
Prem Natarajan
Face recognition made tremendous leaps in the last five years with a myriad of systems proposing novel techniques substantially backed by deep convolutional neural networks (DCNN). Although face recognition performance sky-rocketed using deep-learning in classic datasets like LFW, leading to the belief that this technique reached human performance, it still remains an open problem in unconstrained environments as demonstrated by the newly released IJB datasets. This survey aims to summarize the main advances in deep face recognition and, more in general, in learning face representations for verification and identification. The survey provides a clear, structured presentation of the principal, state-of-the-art (SOTA) face recognition techniques appearing within the past five years in top computer vision venues. The survey is broken down into multiple parts that follow a standard face recognition pipeline: (a) how SOTA systems are trained and which public data sets have they used; (b) face preprocessing part (detection, alignment, etc.); (c) architecture and loss functions used for transfer learning (d) face recognition for verification and identification. The survey concludes with an overview of the SOTA results at a glance along with some open issues currently overlooked by the community.

6 October 2018
Verified
Book Chapter
Closed access
PDF file
YWYue Wu
Yue Wu
WAWael Abd-Almageed
Wael Abd-Almageed
PNPrem Natarajan
Prem Natarajan

1 January 2012 in Journal of Electronic Imaging
Verified
Journal Article
Closed access
PDF file
YWYue Wu
Yue Wu
GYGelan Yang
Gelan Yang
HJHuixia Jin
Huixia Jin
JNJoseph P. Noonan
Joseph P. Noonan
Chaos maps and chaotic systems have been proved to be useful and effective for cryptography. In our study, the two-dimensional logistic map with complicated basin structures and attractors are first used for image encryption. The proposed method adopts the classic framework of the permutation-substitution network in cryptography and thus ensures both confusion and diffusion properties for a secure cipher. The proposed method is able to encrypt an intelligible image into a random-like one from the statistical point of view and the human visual system point of view. Extensive simulation results using test images from the USC-SIPI image database demonstrate the effectiveness and robustness of the proposed method. Security analysis results of using both the conventional and the most recent tests show that the encryption quality of the proposed method reaches or excels the current state-of-the-art methods. Similar encryption ideas can be applied to digital data in other formats (e.g., digital audio and video). We also publish the cipher MATLAB open-source-code under the web page https://sites.google.com/site/tuftsyuewu/source-code.

1 April 2014 in Information Sciences
Verified
Journal Article
Closed access
YWYue Wu
Yue Wu
YZYicong Zhou
Yicong Zhou
JNJoseph P. Noonan
Joseph P. Noonan
SASos S. Agaian
Sos S. Agaian
CCC. L. Philip Chen
C. L. Philip Chen

25 December 2017 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYue Wu
Yue Wu
THTal Hassner
Tal Hassner
KKKangGeon Kim
KangGeon Kim
GMGerard Medioni
Gerard Medioni
PNPrem Natarajan
Prem Natarajan
This paper concerns the problem of facial landmark detection. We provide a unique new analysis of the features produced at intermediate layers of a convolutional neural network (CNN) trained to regress facial landmark coordinates. This analysis shows that while being processed by the CNN, face images can be partitioned in an unsupervised manner into subsets containing faces in similar poses (i.e., 3D views) and facial properties (e.g., presence or absence of eye-wear). Based on this finding, we describe a novel CNN architecture, specialized to regress the facial landmark coordinates of faces in specific poses and appearances. To address the shortage of training data, particularly in extreme profile poses, we additionally present data augmentation techniques designed to provide sufficient training examples for each of these specialized sub-networks. The proposed Tweaked CNN (TCNN) architecture is shown to outperform existing landmark detection methods in an extensive battery of tests on the AFW, ALFW, and 300W benchmarks. Finally, to promote reproducibility of our results, we make code and trained models publicly available through our project webpage.