My Portrait

Lu SHENG

PostDoc Researcher @ CUHK
  lsheng [at] ee.cuhk.edu.hk

Short Bio

I am now a PostDoctoral researcher in Electronic Engineering at The Chinese University of Hong Kong (CUHK), supervised by Prof. Xiaogang Wang. My research interests include image/video processing and computer vision, especially deep learning driven low-level/middle-level and 3D vision problems. I am a member of Image and Video Processing Lab, and closely work with Multimedia Lab. Previously, I have received the Ph.D in the same department in 2016, under the supervision of Prof. King Ngi Ngan. I also worked with Prof. Jianfei Cai during my visit to Nanyang Technological University.

My name is 盛律 (How to pronouce it?) in Chinese characters, while my English name may also be rendered as Lü Sheng, Lv Sheng or Lyu Sheng.

I am actively looking for Academia/Industry jobs all over the globe.

Publications

Conference Papers

Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection

Yongcheng Liu, Lu Sheng, Jing Shao, Junjie Yan, Shiming Xiang, Chunhong Pan

ACM International Conference on Multimedia (ACM MM), 2018

Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition

Guojun Yin, Lu Sheng, Bin Liu, Nenghai Yu, Xiaogang Wang, Jing Shao, Chen Change Loy

European Conference on Computer Vision (ECCV), 2018

Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration

Lu Sheng, Ziyi Lin, Jing Shao, Xiaogang Wang

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

Exploring Disentangled Feature Representation Beyond Face Identification

Yu Liu*, Fangyin Wei*, Jing Shao*, Lu Sheng, Junjie Yan, Xiaogang Wang

(* equal contribution)

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

Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition

Shuyang Sun, Zhanghui Kuang, Lu Sheng, Wanli Ouyang, Wei Zhang

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

PDF

HydraPlus-Net: Attentive Deep Features For Pedestrain Analysis

Xihui Liu, Haiyu Zhao, Maoqing Tian, Lu Sheng, Jing Shao, Shuai Yi, Junjie Yan, Xiaogang Wang

IEEE International Conference on Computer Vision (ICCV), 2017

A Generative Model for Depth-based Robust 3D Facial Pose Tracking

Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic, King Ngi Ngan

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

A Disocclusion Filling Method Using Multiple Sprites with Depth for Virtual View Synthesis

Chi Ho Cheung, Lu Sheng, King Ngi Ngan

IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 2015

DOI

Accelerating the Distribution Estimation for the Weighted Median/Mode Filters

Lu Sheng, King Ngi Ngan, Tak-Wai Hui

Asian Conference on Computer Vision (ACCV), 2014

Temporal Depth Video Enhancement Based on Intrinsic Static Structure

Lu Sheng, King Ngi Ngan, Songnan Li

IEEE International Conference on Image Processing (ICIP), oral, 2014

Screen-camera Calibration Using a Thread

Songnan Li, King Ngi Ngan, Lu Sheng

IEEE International Conference on Image Processing (ICIP), 2014

Depth Enhancement Based on Hybrid Geometric Hole Filling Strategy

Lu Sheng, King Ngi Ngan

IEEE International Conference on Image Processing (ICIP), 2013

A Head Pose Tracking System Using RGB-D Camera

Songnan Li, King Ngi Ngan, Lu Sheng

IEEE International Conference on Computer Vision Systems (ICVS), oral, 2013

Journal Papers

Spatio-Temporal Disocclusion Filling Using Novel Sprite Cells

Chi Ho Cheung, King N Ngan, Lu Sheng

IEEE Transactions on Multimedia (TMM), 2017

DOI

Real-time Head Pose Tracking with Online Face Template Reconstruction

Songnan Li, King Ngi Ngan, Raveendran Paramesran, Lu Sheng

IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2016

Online Temporally Consistent Indoor Depth Video Enhancement via Static Structure

Lu Sheng, King Ngi Ngan, Chern-Loon Lim, Songnan Li

IEEE Transaction on Image Processing (TIP), 2015

Thesis

Probabilistic Approaches for RGB-D Video Enhancement and Facial Pose Tracking

Lu Sheng, supervised by Prof. King Ngi Ngan

Ph.D. Thesis, The Chinese University of Hong Kong, 2016