Yu Liu

Computer Vision Researcher in Sensetime Group

Ph.D. candidate,
MMLAB, CUHK

EMAIL

liuyuisanai@gmail.com

ADDRESS

Rm304,
Ho Sin-Hang Engineering Bldg,
The Chinese University of Hong Kong,
Shatin, N.T., Hong Kong.

News

[Nov.1, 2018] Two paper accepted by AAAI 2019!
[Sept.1, 2018] We release our Code for talking face generation.
[Jul.3, 2018] One paper accepted by ECCV 2018!
[Jun.1, 2018] One paper accepted by IJCV!
[Feb.21, 2018] Two paper accepted by CVPR 2018!
[Nov.13, 2017] One paper accepted by AAAI 2018!
[Sep.05, 2017] One paper accepted by workshop in NIPS 2017!
[Sep.01, 2017] One paper accepted by T-PAMI!
[Jul.17, 2017] One paper accepted by ICCV 2017!
[Mar.04, 2017] Two papers accepted by CVPR 2017!
[Nov., 2016] We win the first place in ILSVRC2016 DET (aka ImageNet)! We also release our Code.
[Jun., 2016] We win the first place in ECCV-MOT16 Challenge! We also release our appearance feature here.

Introduction

I'm looking for industrial or academic internships, research intern position related to AutoML is preferred.
I am a 2nd year Ph.D. student in MMLab in Chinese University of Hong Kong, established by Prof. Xiaoou Tang and supervised by Prof. Xiaogang Wang .
My research interests include: (1) AutoML with genetic algorithm, (2) face/body analysis (detection, attribute, recognition, synthesis) in large scale (>1M identities) and (3) interpretability for deep neural network.
From 2016 to 2017, I was a computer vision researcher in Sensetime Group Limited.
In 2015~2016, I was a research intern in Microsoft Research Asia.
In 2016, I received my bachelor degree with best bachelor thesis award in Beihang University.
In recent years I served as a reviewer for CVPR, IJCV, TCSVT.

Projects & Datasets

GitHub
CaffeMex v2.3
Y Liu, H Li

A multi-GPU & memory-reduced MAT-Caffe on LINUX and WINDOWS

Labeled Pedestrains in the Wild
Y Liu, G Song

A large scale pedestrain re-identification benchmark

Publications

Google Scholar
Gradient Harmonized Single-stage Detector PDF Code

2019 AAAI Conference on Artificial Intelligence (AAAI)

Buyu Li*, Yu Liu*, Xiaogang Wang (*equal contribution)
Talking Face Generation by Adversarially Disentangled Audio-Visual Representation PDF Code

2019 AAAI Conference on Artificial Intelligence (AAAI)

Hang Zhou, Yu Liu, Ziwei Liu, Ping Luo, Xiaogang Wang.
Transductive Centroid Projection for Semi-supervised Large-scale Recognition PDF

2018 European Conference on Computer Vision (ECCV)

Yu Liu, Guanglu Song, Jing Shao, Xiao Jin, Xiaogang Wang.
Exploring Disentangled Feature Representation Beyond Face Identification PDF Page

2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Yu Liu, Fangyin Wei, Jing Shao, Lv Sheng, Junjie Yan, Xiaogang Wang.
Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy PDF

2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Guanglu Song*, Yu Liu*, Ming Jiang, Yujie Wang, Junjie Yan, Biao Leng (*equal contribution)
Rethinking Feature Discrimination and Polymerization for Large-scale Recognition PDF Code

2017 Conference on Neural Information Processing Systems (NIPS) deep learning workshop

Yu Liu, Hongyang Li, Xiaogang Wang.
Recurrent Scale Approximation for Object Detection in CNN PDF Code

2017 IEEE International Conference on Computer Vision (ICCV)

Yu Liu, Hongyang Li, Junjie Yan et al.
Quality Aware Network for Set to Set Recognition PDF Code

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Yu Liu, Junjie Yan, Wanli Ouyang
Scale-Aware Face Detection PDF

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Zekun Hao, Yu Liu, Hongwei Qin, Junjie Yan
Region-based Quality Estimation Network for Large-Scale Person Re-identiļ¬cation PDF Code

2018 AAAI Conference on Artificial Intelligence (AAAI)

Guanglu Song, Biao Leng, Yu Liu, Congrui Hetang, Shaofan Cai
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection PDF Code

International Journal of Computer Vision (IJCV), 2018

Hongyang Li, Yu Liu, W Ouyang, X Wang
Learning Deep Features via Congenerous Cosine Loss for Person Recognition PDF Code

arxiv:1702.06890, 2017

Yu Liu, Hongyang Li, Xiaogang Wang
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature PDF

2016 European Conference on Computer Vision (ECCV) workshop

F Yu, W Li, Q Li, Y Liu, X Shi, J Yan
Crafting GBD-Net for Object Detection PDF Code

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)

X Zeng, W Ouyang, J Yan, H Li, T Xiao, K Wang, Y Liu, Y Zhou, B Yang, ...
3D object understanding with 3D Convolutional Neural Networks PDF

Information Sciences 366, 188-201, 2016

B Leng, Y Liu, K Yu, X Zhang, Z Xiong