245358868_orig
983961564_orig
*Corresponding author.
2020
cvpr2020
CVPR_Logo_Horz2_web

Context-aware and Scale-insensitive Temporal Repetition Counting

Huaidong Zhang, Xuemiao Xu, Guoqiang Han, and Shengfeng He*
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seatle, 2020
[PDF]
cvpr2020B
CVPR_Logo_Horz2_web

Don’t Hit Me! Glass Detection in Real-world Scenes

Haiyang Mei, Xin Yang, Yang Wang, Yuanyuan Liu, Shengfeng He, Qiang Zhang, Xiaopeng Wei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seatle, 2020
[PDF]
qq-20191203085334_orig
348444506_orig

GDFace: Gated Deformation for Multi-view Face Image Synthesis

Xuemiao Xu, Keke Li, Cheng Xu, and Shengfeng He*
Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020), New York, 2020.
[PDF] [More visual results]
QQ截图20191225220712

Unsupervised Domain Adaptation via Importance Sampling

Xuemiao Xu, Hai He, Huaidong Zhang, Yangyang Xu, and Shengfeng He*
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), to appear
[PDF]
rank1

Few-shot Breast Cancer Metastases Classification via Unsupervised Cell Ranking

Jiaojiao Chen, Jianbo Jiao, Shengfeng He*Guoqiang Han, and Jing Qin
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), to appear
[PDF]
2019
qq-20191203084416_orig

Fast User-Guided Single Image Reflection Removal via Edge-aware Cascaded Networks

Huaidong Zhang, Xuemiao Xu, Hai He, Shengfeng HeGuoqiang Han, Jing Qin, and Dapeng Wu
IEEE Transactions on Multimedia (TMM), to appear
[PDF]
iccv19_orig
677707512_orig

Visualizing the Invisible: Occluded Vehicle Segmentation and Recovery

Xiaosheng Yan, Feigege WangWenxi Liu, Yuanlong YuShengfeng He, and Jia Pan
International Conference on Computer Vision (ICCV 2019), Seoul, 2019
 [PDF]
reflection_3
692771250_3

Single Image Reflection Removal Beyond Linearity

Qiang Wen, Yinjie Tan, Jing QinWenxi LiuGuoqiang Han, and Shengfeng He*
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, 2019
 [PDF] [Supp] [Source Code]
10001_orig
692771250_3

Context-aware Spatio-recurrent Curvilinear Structure Segmentation

Feigege Wang, Yue Gu, Wenxi Liu, Yuanlong Yu, Shengfeng He, and Jia Pan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, 2019
[PDF]

flow_orig
692771250_3

Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics

Jiangliu Wang, Jianbo JiaoLinchao Bao, Shengfeng He, Yunhui Liu, and Wei Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, 2019
[PDF]

tnnls_1

Exploring Duality in Visual Questions Driven Top-Down Saliency

Shengfeng He, Chu Han, Guoqiang Han, and Jing Qin
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), to appear.
[PDF]
tracking_orig

Deformable Object Tracking with Gated Fusion

Wenxi LiuYibing Song, Dengsheng Chen, Shengfeng He*, Yuanlong Yu, Tao Yan,
Gehard P. Hancke, and Rynson W.H. Lau
IEEE Transactions on Image Processing (TIP), to appear.
[PDF]
715954916

Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement

Yibing Song, Jiawei Zhang, Lijun Gong, Shengfeng He, Linchao BaoJinshan Pan,
Qingxiong Yang, and Ming-Hsuan Yang

International Journal of Computer Vision (IJCV), 2019
[PDF]

Joint Shape Matching for Overlapping Cytoplasm Segmentation in Cervical Smear Images
Youyi Song, Jing Qin, Baiying Lei, Shengfeng He, and Kup-Sze Cho
IEEE International Symposium on Biomedical Imaging (ISBI 2019), Venice, 2019.

Deep Binocular Tone Mapping
Zhuming Zhang, Chu Han, Shengfeng He, Xueting Liu, Haichao Zhu, Xinghong Hu, and Tien-Tsin Wong
The Visual Computer (Proc. CGI), June 2019

Proposal-Driven Segmentation for Videos
Junliang Li, Shengfeng He*,  Hon-Cheng Wong*, and Sio-Long Lo
IEEE Signal Processing Letters, 26 (8), 1098-1102,  2019

Age Estimation via Attribute-region Association
Yiliang Chen, Shengfeng He*, Zichang Tan, Chu Han, Guoqiang Han, and Jing Qin
Neurocomputing, to appear

2018
bunny-box_orig
199414897

Active Matting

Xin Yang, Ke Xu, Shaoze Shen, Shengfeng He*, Baocai Yin, and Rynson W.H. Lau
Advances in Neural Information Processing Systems (NeurIPS), Dec. 2018
[PDF]
siga2018_orig
296505600_orig

Deep Unsupervised Pixelization

Chu Han^, Qiang Wen^, Shengfeng He*, Qianshu Zhu, Yinjie Tan, Guoqiang Han, and Tien-Tsin Wong 
(^joint first authors)

ACM Transactions on Graphics (SIGGRAPH Asia 2018 issue), 2018
[
PDF] [Supp] [Source Code]
pg2018_orig

Example-based Colorization via Dense Encoding Pyramids

Chufeng Xiao^, Chu Han^,  Zhuming Zhang, Jing Qin, Tien-Tsin WongGuoqiang Han, and Shengfeng He* 
(^joint first authors)

Computer Graphics Forum (Pacific Graphics 2018 Fast Track), 2018
[
PDF] [Source Code]
tits_orig

SINet: A Scale-insensitive Convolutional Neural Network for Fast Vehicle Detection

Xiaowei Hu, Xuemiao Xu, Yongjie Xiao, Hao Chen, Shengfeng He, Jing Qin and Pheng-Ann Heng
IEEE Transactions on Intelligent Transportation Systems (TITS), to appear
[PDF] [Source Code]
1_2

Image Captioning via Semantic Element Embedding

Xiaodan Zhang, Shengfeng He, Xinhang Song, Pengxu Wei, Shuqiang Jiang,
Qixiang Ye, Jianbin Jiao and Rynson W.H. Lau

Neurocomputing, to appear
[PDF]
figure-1_1

Efficient Image Super Resolution Integration

Ke Xu, Xin Wang, Xin Yang, Shengfeng He*, Baocai Yin, Qiang Zhang, and Rynson W.H. Lau
The Visual Computer (Proc. CGI), June 2018
[PDF]
2017
iccv17_2
918865511_1

Delving into Salient Object Subitizing and Detection

Shengfeng He, Jianbo Jiao, Xiaodan Zhang, Guoqiang HanRynson W.H. Lau
International Conference on Computer Vision (ICCV 2017), Venice, 2017
[
PDF]
srd_2
458517372

DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal

Liangqiong QuJiandong Tian, Shengfeng He, Yandong Tang, and Rynson W.H. Lau
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Hawaii, 2017
(Spotlight Oral, Acceptance Rate 8%)
[PDF] [SRD testset] [SRD training set (Baidu/Code: kuzj) (Google)] [Code]
373558548_2
893126111_2

Learning to Hallucinate Face Images via Component Generation and Enhancement

Yibing Song, Jiawei ZhangShengfeng He, Linchao Bao, and Qingxiong Yang 
International Joint Conference on Artificial Intelligence (IJCAI 2017), pp 4537-4543, Melbourne, 2017
[
PDF]
cvprw_orig

FormResNet: Formatted Residual Learning for Image Restoration

Jianbo Jiao, Wei-Chih Tu, Shengfeng He, and Rynson W.H. Lau
IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPR Workshop 2017), Hawaii, 2017 (Oral)
[
PDF]
icme-cdblstm-v9_orig

Keyword-driven Image Captioning via Context-dependent Bilateral LSTM

Xiaodan Zhang, Shengfeng He, Xinhang Song, Pengxu Wei, Shuqiang Jiang,
Qixiang Ye, Jianbin Jiao and Rynson W.H. Lau

IEEE International Conference on Multimedia and Expo (ICME 2017), Hong Kong, 2017
(Oral)
[
PDF]
ijcv2017_orig

Joint Image Denoising and Disparity Estimation via Stereo Structure PCA and Noise-tolerant Cost

Jianbo JiaoQingxiong Yang, Shengfeng He, Shuhang GuLei Zhang, and Rynson W.H. Lau
International Journal of Computer Vision (IJCV), 124(2): 204-222 (2017) .
[PDF]
l0tip_orig

L0-Regularized Image Downscaling

Junjie Liu, Shengfeng He*, and Rynson W.H. Lau
IEEE Transactions on Image Processing (TIP), to appear.
[PDF] [Code] [BSDS Results] [User Study]
egotip_1

Egocentric Temporal Action Proposals

Shao Huang, Weiqiang Wang, Shengfeng He*, and Rynson W.H. Lau
IEEE Transactions on Image Processing (TIP), to appear.
[PDF]
000252-left-o_orig

RGBD Salient Object Detection via Deep Fusion

 Liangqiong Qu, Shengfeng He*Jiawei Zhang, Jiandong TianYandong Tang, and Qingxiong Yang
IEEE Transactions on Image Processing (TIP), 26(5):2274-2285, May. 2017
[
PDF] [Source Code (Google Drive)]
interactiveobjectproposal-v6_orig

Interactive Hierarchical Object Proposals

Mingliang ChenJiawei Zhang, Shengfeng He*, Qingxiong Yang, Qing Liand Ming-Hsuan Yang
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), to appear.
[
PDF]
egocentric-hand-detection-via-dynamic-region-growing-major-revision_1

Egocentric Hand Detection Via Dynamic Region Growing

Shao Huang, Weiqiang Wang, Shengfeng He, and Rynson W.H. Lau
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), to appear.
[PDF]
cviu_orig

Stylizing Face Images via Multiple Exemplars

Yibing SongLinchao BaoShengfeng He, Qingxiong Yang,  and Ming-hsuan Yang 
Computer Vision and Image Understanding (CVIU), to appear.
[
PDF]
2016
9601541
937483

Exemplar-Driven Top-Down Saliency Detection via Deep Association

Shengfeng He and Rynson W.H. Lau
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), pp. 5723-5732, Las Vegas, June, 2016
(Spotlight Oral, Acceptance Rate 9.7%)
 [
PDF]
2344840
937483

Real-time Salient Object Detection with a Minimum Spanning Tree

Wei-Chih TuShengfeng He, Qingxiong Yang, and Shao-Yi Chien
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), pp. 2334-2342, Las Vegas, June, 2016
(Spotlight Oral, Acceptance Rate 9.7%)
 [
PDF]
stereo-proposals-v6_2

Stereo Object Proposals

Shao Huang, Weiqiang Wang, Shengfeng He*, and Rynson W.H. Lau
IEEE Transactions on Image Processing (TIP), vol. 26, no. 2, pp. 671-683, Feb. 2017
[PDF] [StereoObj dataset]
4881407

Robust Object Tracking via Locality Sensitive Histograms

Shengfeng He, Rynson W.H. LauQingxiong YangJiang Wang, and Ming-Hsuan Yang
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 27(5): 1006-1017 (2017)
(LSHT extension)
[PDF] [Supplemental Material]
2015
_6898913
7142600

Oriented Object Proposals

Shengfeng He and Rynson W.H. Lau
IEEE International Conference on Computer Vision (ICCV 2015), pp. 280 - 288, Santiago, Dec.  2015
 [
PDF]
_5547027

SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection

Shengfeng He, Rynson W.H. Lau, Wenxi Liu, Zhe Huang, and Qingxiong Yang
International Journal of Computer Vision (IJCV), vol. 115, no. 3, pp. 330-344, Dec. 2015
[
PDF]

6685941

Fast Weighted Histograms for Bilateral Filtering and Nearest Neighbor Searching

Shengfeng HeQingxiong YangRynson W.H. Lau, and Ming-Hsuan Yang
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 26, no. 5, pp. 891-902, May 2016.
(Extension of our Locality Sensitive Histograms for different applications.)
[
PDF

__7352142

Saliency-Guided Color-to-Gray Conversion Using Region-based Optimization

Du Hao, Shengfeng He, Sheng BinLizhuang Ma, and Rynson W.H. Lau
IEEE Transactions on Image Processing (TIP), vol. 24, no. 1, pp. 434 - 443, Jan. 2015
[
PDF] [Supplemental Material] [CSDD dataset] [Our Results on CSDD] [Our Results on Cadik]
[Source Code] [Demo

2014
1042145

A Tool-Free Calibration Method for Turntable-based 3D Scanning Systems

Xufang Pang, Rynson W.H. LauZhan SongYangyan Li, and Shengfeng He
IEEE Computer Graphics and Applications (CG&A), 36(1):52-61, Jan. 2016.
[
PDF]
9501388
230441899

Saliency Detection with Flash and No-flash Image Pairs

Shengfeng He and Rynson W.H. Lau
European Conference on Computer Vision (ECCV 2014), Zurich, September, 2014
 [
PDF] [Supplemental Material] [Video Spotlight]
2013
_4558597

Consistent Stereo Image Editing

Tao YanShengfeng He, Rynson W.H. Lau, and Yun Xu
ACM International Conference on Multimedia (ACM MM 2013), pp. 677-680, Barcelona, October, 2013
[PDF] [Supplemental Material]
_3860264_orig
262956929

Visual Tracking via Locality Sensitive Histograms

Shengfeng HeQingxiong Yang, Rynson W.H. Lau, Jiang Wang, and Ming-Hsuan Yang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013), pp. 2427-2434, Portland, June, 2013
 [
PDF] [Supplemental Material] [Video]
2012
_6004288_orig

Synthetic Controllable Turbulence using Robust Second Vorticity Confinement

Shengfeng He and Rynson W.H. Lau
Computer Graphics Forum (CGF), Volume 32, Issue 1, pp. 27–35, February 2013
[PDF] [Bibtex] [Video] [GPU Executable]
2011
3172298_orig

An Efficient Adaptive Vortex Particle Method for Real-Time Smoke Simulation

Shengfeng He, Hon-Cheng Wong, and Un-Hong Wong
CAD/Graphics 2011, pp. 317-324, 15-17 Sept. 2011
[PDF
]
1033620_orig

Real-time Smoke Simulation with Improved Turbulence by Spatial Adaptive Vorticity Confinement

Shengfeng He, Hon-Cheng Wong, Wai-Man Pang, and Un-Hong Wong
Journal of Computer Animation and Virtual Worlds (CASA2011 Special Issue), vol. 22, pp. 107-114
[
PDF] [YouTube]