News

[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 am a first year Ph.D. student in Chinese University of Hong Kong, supervised by Prof. Xiaogang Wang .
My research interests include: (1) face/person analysis (detection, attribute and recognition) in large scale (>1M identities). Specifically, exploring strategy for metric learning, transfer learning and optimization methods with good generalization ability on mass data. (2) 2/3D object detection and (3) interpretability for deep neural network.
In 2016~2017, 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.

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
Rethinking Feature Discrimination and Polymerization for Large-scale Recognition PDF Code
Yu Liu, Hongyang Li, Xiaogang Wang.

2017 Conference on Neural Information Processing Systems (NIPS) workshop

Recurrent Scale Approximation for Object Detection in CNN PDF Code
Yu Liu, Hongyang Li, Junjie Yan et al.

2017 IEEE International Conference on Computer Vision (ICCV)

Quality Aware Network for Set to Set Recognition PDF Code
Yu Liu, Junjie Yan, Wanli Ouyang

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

Scale-Aware Face Detection PDF Code(coming soon)
Zekun Hao, Yu Liu, Hongwei Qin, Junjie Yan

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

Region-based Quality Estimation Network for Large-Scale Person Re-identiļ¬cation PDF Code
Guanglu Song, Biao Leng, Yu Liu, Congrui Hetang, Shaofan Cai

2018 AAAI Conference on Artificial Intelligence (AAAI)

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

arxiv:1702.06890, 2017

Zoom Out-and-In Network with Recursive Training for Object Proposal PDF Code
Hongyang Li, Yu Liu, W Ouyang, X Wang

arxiv:1702.05711, 2017

POI: Multiple Object Tracking with High Performance Detection and Appearance Feature PDF
F Yu, W Li, Q Li, Y Liu, X Shi, J Yan

European Conference on Computer Vision (ECCV), 2017, workshop

Crafting GBD-Net for Object Detection PDF Code
X Zeng, W Ouyang, J Yan, H Li, T Xiao, K Wang, Y Liu, Y Zhou, B Yang, ...

IEEE Transactions on Pattern Analysis and Machine Intelligence

3D object understanding with 3D Convolutional Neural Networks PDF
B Leng, Y Liu, K Yu, X Zhang, Z Xiong

Information Sciences 366, 188-201, 2016