My Portrait            

Jing SHAO

Associate Director @ SenseTime
  shaojing [at] sensetime.com
  amandajshao [at] gmail.com

Short Bio

Jing Shao is currently a Vice Director in SenseTime Group Limited. She received her PhD (2016) in Electronic Engineering from The Chinese University of Hong Kong (CUHK), supervised by Prof. Xiaogang Wang, and work closely with Prof. Chen Change Loy and the Multimedia Lab (MMLab) leaded by Prof. Xiaoou Tang. Her research interests include computer vision, pattern recognition, with focus on video surveillance, NLP with vision, deep generative models and 3D vision. She serves as the reviewer of IJCV, T-PAMI, T-CSVT, T-MM, T-ITS, and CVIU, and reviewed CVPR, ICCV, ECCV from 2016 to 2018. She is a member of IEEE.

alt textPositions available for self-motivated interns and full-time researchers in computer vision and deep learning! Please do not be hesitated to send your CV to shaojing [at] sensetime.com!

Recent News

  • alt textThree papers: 1@ICCV 2019 on Text-image retrieval, 1@NeurIPS 2019 on Layout to image generation, 1@AAAI 2020 on Dense point cloud completion
  • alt text[Bug (invalid links) fixed] Baidu Disk links of CUHK Crowd Dataset has been renewed!
  • Four papers accepted to CVPR 2019 (one Oral and three Posters)
  • Five papers: 3@ECCV 2018, 1@ACM MM 2018, 1@BMVC 2018
  • Three papers accepted to CVPR 2018 (one Oral and two Posters)
  • Two papers accepted to ICCV 2017
  • One paper accepted to CVPR 2017
  • One paper accepted to TCSVT 2016
  • One Spotlight paper accepted to CVPR 2016
  • I am invited to participate in MSRA Ph.D. Forum 2016
  • One paper accepted to TCSVT 2016
  • One Oral paper accepted to CVPR 2015
  • One Oral paper accepted to CVPR 2014

Datasets

CUHK Crowd Dataset

#Paper# Scene-Independent Group Profiling in Crowd, CVPR, Oral, 2014
#Password# cuhkivp

WWW Crowd Dataset

#Paper# Deeply Learned Attributes for Crowded Scene Understanding, CVPR, Oral, 2015
#Password# cuhk_ivp_www

Publications

Conference Papers

Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis

Xihui Liu, Guojun Yin, Jing Shao, Xiaogang Wang, Hongsheng Li

Neural Information Processing Systems (NeurIPS), 2019

PDF

CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval

Zihao Wang*, Xihui Liu*, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, Jing Shao**

IEEE International Conference on Computer Vision (ICCV), 2019

PDF

Semantics Disentangling for Text-to-Image Generation

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

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2019

Context and Attribute Grounded Dense Captioning

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

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Video Generation from Single Semantic Label Map

Junting Pan, Chengyu Wang, Xu Jia, Jing Shao, Lu Sheng, Junjie Yan, Xiaogang Wang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing

Xihui Liu, Zihao Wang, Jing Shao, Xiaogang Wang, Hongsheng Li

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

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
(** corresponding author)

European Conference on Computer Vision (ECCV), 2018

Transductive Centroid Projection for Semi-supervised Large-scale Recognition

Yu Liu, Guanglu Song, Jing Shao, Xiao Jin, Xiaogang Wang

European Conference on Computer Vision (ECCV), 2018

PDF

Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data

Xihui Liu, Hongsheng Li, Jing Shao, Dapeng Chen, Xiaogang Wang

European Conference on Computer Vision (ECCV), 2018

PDF

Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association

Dapeng Chen, Hongsheng Li, Xihui Liu, Yantao Shen, Jing Shao, Zejian Yuan, Xiaogang Wang

European Conference on Computer Vision (ECCV), 2018

PDF

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

Yongcheng Liu, Lu Sheng, Jing Shao**, Junjie Yan, Shiming Xiang, Chunhong Pan
(** corresponding author)

ACM International Conference on Multimedia (ACM MM), 2018

Localization Guided Learning for Pedestrian Attribute Recognition

Pengze Liu, Xihui Liu, Junjie Yan, Jing Shao**
(** corresponding author)

British Machine Vision Conference (BMVC), 2018

PDF

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

Lu Sheng, Ziyi Lin, Jing Shao**, Xiaogang Wang
(** corresponding author)

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

Real-time and achieve state-of-the-art performance.

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

Top performance on LFW as well as CelebA and LFWA. The proposed system is also ready to semantically control the face generation/editing based on various identities and attributes in an unsupervised manner.
PDF

Practical Block-wise Neural Network Architecture Generation

Zhao Zhong, Junjie Yan, Wei Wu, Jing Shao, Cheng-lin Liu

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

Tremendous reduction of search space in designing networks with 3 days and 32 GPUs, and strong generalizability that the network built on CIFAR also performs well on the ImageNet dataset.
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
(* equal contribution, ** corresponding author)

IEEE International Conference on Computer Vision (ICCV), 2017

Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification

Zhongdao Wang*, Luming Tang*, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan, Shengjin Wang, Hongsheng Li, Xiaogang Wang
(* equal contribution)

IEEE International Conference on Computer Vision (ICCV), 2017

PDF

Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion

Haiyu Zhao*, Maoqing Tian*, Shuyang Sun, Jing Shao, Junjie Yan, Shuai Yi, Xiaogang Wang, Xiaoou Tang
(* equal contribution)

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

Slicing Convolutional Neural Network for Crowd Video Understanding

Jing Shao, Chen Change Loy, Kai Kang, Xiaogang Wang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Spotlight, 2016
(Acceptance rate: 9.7%)

Deeply Learned Attributes for Crowded Scene Understanding

Jing Shao, Kai Kang, Chen Change Loy, Xiaogang Wang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2015
(Acceptance rate: 3.3%)

Scene-Independent Group Profiling in Crowd

Jing Shao, Chen Change Loy, Xiaogang Wang

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2014
(Acceptance rate: 5.7%)

An image-based fire detection method using color analysis

Jing Shao, Guanxiang Wang, Wei Guo

2012 International Conference on Computer Science and Information Processing, 2012

PDF

Moving-object Detection Based on Shadow Removal and Prospect Reconstruction

Wenping Wu, Jing Shao, Wei Guo

2012 International Conference on Artificial Intelligence and Soft Computing, 2012

PDF
Journal Papers

Crowded Scene Understanding by Deeply Learned Volumetric Slices

Jing Shao, Chen Change Loy, Kai Kang, Xiaogang Wang

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017

A journal extension of our CVPR 2015 paper.
PDF

Learning Scene-Independent Group Descriptors for Crowd Understanding

Jing Shao, Chen Change Loy, Xiaogang Wang

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2016

A journal extension of our CVPR 2014 paper.
PDF

Fire detection based on video dynamic texture (in Chinese)

Jing Shao, Guanxiang Wang, Wei Guo

Journal of Image and Graphics, 2013

PDF
Thesis

Scene-Independent Crowd Understanding and Crowd Behavior Analysis

Jing Shao, supervised by Prof. Xiaogang Wang

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

PDF