Chengjiang Long 龙成江[CV]

Ph.D., Principal Scientist
JD Tech
675 E Middlefield Rd
Mountain View, CA 94043

Email: cjfykx AT gmail.com




 

Description: picture










 

Home Research/Publications Services Teachings Honors About Me

Research Interests

  • Computer Vision, Computer Graphics, Multimedia, Machine Learning, and Artificial Intelligence
    • Integration of Human and Machine Intelligence (e.g., collaborative active learning)
    • Human Sensing from Unconstrained Images and Videos (e.g., motion analysis and trajectory prediction)
    • Object, Scene Recognition and Segmentation
    • Shadow and Illumination Modeling (e.g., shadow removal and relighting)
    • Multimodal Fusion, Text-to-Image Generation, and Image/Video Caption
    • Style Transfer and Controllable Person Image Synthesis
    • Camera Pose Estimation and Relocalization
    • Image and Video Recovery and Enhancement (e.g., single image super resolution)
    • Explainable Artificial Intelligence
    • Personalized Information Retrieval and Recommendation System
    • Other Related Applications

Selected Publications

The following are selected journal and conference papers from 60 co-author papers, highlighting 1 TOG, 1 T-PAMI, 1 IJCV, 1 T-IP, 1 T-MM, 1 SIGGRAPH Asia, 4 CVPR, 8 ICCV, 2 AAAI, 1 ACM MM, 1 T-CSVT, 1 PR, 1 CAGD, 3 CGF, 2 WACV, 1 ICME, 1 ACCV and 1 ICTAI with 36 1st/2nd-author papers, in which the 2nd authorship indicates the 1st author as my advisors I worked with or as my students/interns/colleagues I closely supervised. For the full list, you can find it in My Google Scholar.

Description: picture

DDBN: Dual Detection Branch Network for Semantic Diversity Predictions

Qifeng Lin, Chengjiang Long, Jianhui Zhao, Gang Fu, and Zhiyong Yuan

Pattern Recognition (PR), Volume 122, 2022.

[PDF] [BibTeX] (Accepted, IF: 7.74)

Description: picture

Monte Carlo Denoising via Auxiliary Feature Guided Self-Attention

Jiaqi Yu, Yongwei Nie, Chengjiang Long, Wenju Xu, Qing Zhang, and Guiqing Li

ACM Transactions on Graphics (TOG), 40(6), 2021. Proceedings of the ACM SIGGRAPH Conference and Exhibition in Asia (SIGGRAPH Asia), Tokyo, Japan, Dec 14-17, 2021.

[PDF] [Supp] [Poster] [Presentation] [Github] [BibTeX] (Top 1 journal in Computer Graphics, IF: 6.495)

Description: picture

DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer

Wenju Xu, Chengjiang Long, Ruisheng Wang, and Guanghui Wang

Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, Oct 11-17, 2021.

[PDF] [Supp] [Poster] [Presentation] [Github] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 3%) (Oral Paper!)

Description: picture

CANet: A Context-Aware Network for Shadow Removal

Zipei Chen, Chengjiang Long, Ling Zhang, and Chunxia Xiao

Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, Oct 11-17, 2021.

[PDF] [Supp] [Poster] [Presentation] [Github] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 25.9%)

Description: picture

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

Zhian Liu, Yongwei Nie, Chengjiang Long, Qing Zhang, and Guiqing Li

Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, Oct 11-17, 2021.

[PDF] [Supp] [Poster] [Presentation] [Github] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 3%) (Oral Paper!)

Description: picture

MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction

Lingwei Dang, Yongwei Nie, Chengjiang Long, Qing Zhang, and Guiqing Li

Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, Oct 11-17, 2021.

[PDF] [Supp] [Poster] [Presentation] [Github] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 25.9%)

Description: picture

Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning

Xinzhi Dong, Chengjiang Long, Wenju Xu, and Chunxia Xiao

Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), Chengdu, Sichuan, China, Oct 20-24, 2021.

[PDF] [Supp] [Poster] [Github] [BibTeX] (Top 1 Conference in Multimedia, acceptance rate: 27.9%)

Description: picture

SGCN: Sparse Graph Convolution for Pedestrian Trajectory Prediction

Liushuai Shi, Le Wang, Chengjiang Long, Sanping Zhou, Mo Zhou, Zhenxing Niu, and Gang Hua

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, Jun 19-26, 2021.

[PDF] [Supp] [Poster] [Github] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 27%)

Description: picture

A Novel Visual Representation on Text Using Diverse Conditional GAN for Visual Recognition

Tao Hu, Chengjiang Long, and Chunxia Xiao

IEEE Transactions on Image Processing (T-IP), 30, 3499-3512, 2021.

[PDF] [BibTeX] (Top 1 Journal in Image Processing, IF: 9.34)

Description: picture

A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization

Ashraful Islam, Chengjiang Long, and Richard Radke

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada, Feb 2-9, 2021.

[PDF] [Supp] [Poster] [BibTeX] (Top 1 Conference in Artificial Intelligence, acceptance rate: 21%)

Description: picture

A Two-Stage Attentive Network for Single Image Super Resolution

Jiqing Zhang, Chengjiang Long, Yuxin Wang, Haiyin Piao, Haiyang Mei, Xin Yang, and Baocai Yin

IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2021.

[PDF] [BibTeX] (Top Journal in Multimedia, IF: 4.13)

Description: picture

Luminance Attentive Networks for HDR Image and Panorama Reconstruction

Hanning Yu, Wentao Liu, Chengjiang Long, Bo Dong, Qin Zou, and Chunxia Xiao

Computer Graphics Forum (CGF), 40(7), 2021. Proceedings of Pacific Graphics (PG), Wellington, New Zealand, Oct 18 – 21, 2020&2021.

[PDF] [Supp] [BibTeX] (Top Journal in Computer Graphics, IF: 2.116)

Description: picture

Scene Inference for Object Illumination Editing

Zhongyun Bao, Chengjiang Long, Gang Fu, Daquan Liu, Yuanzhen Li, Jiaming Wu, and Chunxia Xiao

arXiv, 2021.

[PDF] [BibTeX] (arXiv:2108.00150)

Description: picture

CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation

Tao Hu, Chengjiang Long, and Chunxia Xiao

arXiv, 2021.

[PDF] [BibTeX] (arXiv:2107.13516)

Description: picture

Explore Video Clip Order with Self-Supervised and Curriculum Learning for Video Applications

Jun Xiao, Lin Li, Dejing Xu, Chengjiang Long, Jian Shao, Shifeng Zhang, Shiliang Pu, and Yueting Zhuang

IEEE Transactions on Multimedia (T-MM), 2020.

[PDF] [BibTeX] (Top 1 Journal in Multimedia, IF: 6.051)

Description: picture

DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-move Forgery Detection and Localization

Ashraful Islam, Chengjiang Long, Arslan Basharat, and Anthony Hoogs

In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, Jun 14-19, 2020.

[PDF] [Supp] [Presentation] [Poster] [BibTeX] (Top 3 Conference in Computer Vision, acceptance rate: 22%) (The Full-Score Paper!)

Description: picture

ARShadowGAN: Shadow Generative Adversarial Network for Augmented Reality in Single Light Scenes

Daquan Liu, Chengjiang Long, Hongpan Zhang, Hanning Yu, Xinzhi Dong, and Chunxia Xiao

In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, Jun 14-19, 2020.

[PDF] [Supp] [Presentation] [Poster] [Github] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 22%)

Description: picture

RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal

Ling Zhang, Chengjiang Long, Xiaolong Zhang, and Chunxia Xiao

In Proc. AAAI Conference on Artificial Intelligence (AAAI), New York, NY, USA, Feb 7-12, 2020.

[PDF] [Spotlight] [Poster] [Github] [BibTeX] (Top 1 Conference in Artificial Intelligence, acceptance rate: 20.6%, arXiv:1911.09178)

Description: picture

Multi-Stage Point Completion Network with Critical Set Supervision

Wenxiao Zhang, Chengjiang Long, Qingan Yan, Alix L.H. Chow, and Chunxia Xiao

Computer-Aided Geometric Design (CAGD), 82, p.101925, 2020. Proceedings of International Conference on Geometric Modeling and Processing (GMP), 2020.

[PDF] [BibTeX] (Top Journal in Computer Graphics, IF: 1.23)

Description: picture

CLA-GAN: A Context and Lightness Aware Generative Adversarial Network for Shadow Removal

Ling Zhang, Chengjiang Long, Qingan Yuan, Xiaolong Zhang, and Chunxia Xiao

Computer Graphics Forum (CGF), 39(7), 483-494, 2020. Proceedings of Pacific Graphics (PG), Wellington, New Zealand, Oct 18 – 21, 2020&2021.

[PDF] [BibTeX] (Top Journal in Computer Graphics, IF: 2.116)

Description: picture

Multi-Context and Enhanced Reconstruction Network for Single Image Super Resolution

Jiqing Zhang, Chengjiang Long, Yuxin Wang, Xin Yang, Haiyang Mei, and Baocai Yin

In Proc. IEEE International Conference on Multimedia & Expo (ICME), London, United Kingdom, Jun 6-10, 2020.

[PDF] [Supp] [BibTeX] (Acceptance rate: 30%)

Description: picture

Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations

Bhavan Vasu and Chengjiang Long

In Proc. IEEE Winter Conf. on Applications of Computer Vision (WACV), Snowmass Village, CO, USA, Mar 2-5, 2020.

[PDF] [Presentation] [YouTube] [Poster] [Github] [BibTeX] (Acceptance rate: 34.5%, arXiv:1912.08387)

Description: picture

ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal

Bin Ding, Chengjiang Long, Ling Zhang, and Chunxia Xiao

In Proc. IEEE International Conf. on Computer Vision (ICCV), Seoul, South Korea, Oct 27-Nov 2, 2019.

[PDF] [Poster] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 25%. arXiv:1908.01323)

Description: picture

Shadow Inpainting and Removal Using Generative Adversarial Networks with Slice Convolutions

Jinjiang Wei, Chengjiang Long, Hua Zou, and Chunxia Xiao

Computer Graphics Forum (CGF), 38(7), 381-392, 2019. Proceedings of Pacific Graphics (PG), Seoul, Korea, Oct 14-17, 2019.

[PDF] [Presentation] [BibTeX] (Top Journal in Computer Graphics, IF: 2.116)

Description: picture

Automated Pig Counting Using Deep Learning

Mengxiao Tian, Hao Guo, Hong Chen, Qing Wang, Chengjiang Long, and Yuhao Ma

Computers and Electronics in Agriculture, 2019.

[PDF] [BibTeX] (Top Journal in Agriculture, IF: 3.858)

Description: picture

Deep Neural Networks In Fully Connected CRF For Image Labeling With Social Network Metadata

Chengjiang Long, Roddy Collins, Eran Swears, and Anthony Hoogs

In Proc. IEEE Winter Conf. on Applications of Computer Vision (WACV), Waikoloa Village, HI, USA, Jan 7-11, 2019.

[PDF] [Supp] [Presentation] [YouTube] [Poster] [BibTeX] (Acceptance rate: 36.0%, arXiv:1801.09108)

Description: picture

A Coarse-to-fine Deep Convolutional Neural Network Framework for Frame Duplication Detection and Localization in Forged Videos

Chengjiang Long, Arslan Basharat, and Anthony Hoogs

In Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) on Media Forensics, Long Beach, CA, USA, June 17, 2019.

[PDF] [Spotlight] [Poster] [BibTeX] (arXiv:1811.10762v2)

Description: picture

Urban Semantic 3D Reconstruction from Multiview Satellite Imagery

Matthew J. Leotta, Chengjiang Long, Bastien Jacquet, Matthieu Zins, Dan Lipsa, Jie Shan, Bo Xu, Zhixin Li, Xu Zhang, Shih-Fu Chang, Matthew Purri, Jia Xue, and Kristin Dana

In Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) on EARTHVISION, Long Beach, CA, USA, June 17, 2019.

[PDF] [Poster] [Project] [Github] [BibTeX] (The Best Paper Award!)

Description: picture

VITAL: A Visual Interpretation on Text with Adversarial Learning for Image Labeling

Tao Hu, Chengjiang Long, Leheng Zhang, and Chunxia Xiao

arXiv 2019.

[PDF] [BibTeX] (arXiv:1907.11811v2)

Description: picture

Collaborative Active Visual Recognition from Crowds: A Distributed Ensemble Approach

Gang Hua, Chengjiang Long, Ming Yang, and Yan Gao

IEEE Trans. on Pattern Analysis and Machine Intelligence (T-PAMI), 40(3): 582-594, 2018.

[PDF] [Datasets] [BibTeX] (Top 1 journal in Artificial Intelligence, IF: 17.861)

Description: picture

How Does A Camera Look At One 3D CAD Object?

Chuang Xing, Chengjiang Long , Hao Guo , Yongwei Nie , Yuan Zhang , Dehai Zhu , Qin Ma , and Mengxiao Tian

In Proc. IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Boston, MA, USA, Nov 6-8, 2017.

[PDF] [Presentation] [BibTeX] (Acceptance rate: 36.7%)

Description: picture

Correlational Gaussian Processes for Cross-domain Visual Recognition

Chengjiang Long and Gang Hua

In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, USA, July 21-26, 2017.

[PDF] [Poster] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 29.2%)

Description: picture

A C3D-based Convolutional Neural Network for Frame Dropping Detection in a Single Video Shot

Chengjiang Long, Eric Smith, Arslan Basharat, and Anthony Hoogs

In Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) on Media Forensics, Honolulu, Hawaii, USA, July 26, 2017.

[PDF] [Presentation] [BibTeX]

Description: picture

L2GSCI: Local to Global Seam Cutting and Integrating for Accurate Face Contour Extraction

Yongwei Nie, Xu Cao, Chengjiang Long, Ping Li, and Guiqing Li

arXiv, 2017.

[PDF] [BibTeX] (arXiv:1703.01605)

Description: picture

A Joint Gaussian Process Model for Active Visual Recognition with Expertise Estimation in Crowdsourcing.

Chengjiang Long, Gang Hua, and Ashishi Kapoor

International Journal of Computer Vision (IJCV), 116(2): 136®C160, 2016.

[PDF] [Datasets] [BibTeX] (Top 1 Journal in Computer Vision, IF: 5.698)

Description: picture

Multi-class Multi-annotator Active Learning with Robust Gaussian Process for Visual Recognition

Chengjiang Long and Gang Hua

In Proc. IEEE International Conf. on Computer Vision (ICCV), Santiago, Chile, Dec 13-16, 2015.

[PDF] [Poster] [Spotlight] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 30.92%)

Description: picture

Accurate Object Detection with Location Relaxation and Regionlets Re-localization

Chengjiang Long, Xiaoyu Wang, Gang Hua, Ming Yang, and Yuanqing Lin

In Proc. The 12th Asian Conf. on Computer Vision (ACCV), Singapore, Nov 1-5, 2014.

[PDF] [Poster] [BibTeX] (Acceptance rate: 27% )

Description: picture

Active Visual Recognition with Expertise Estimation in Crowdsourcing

Chengjiang Long, Gang Hua, and Ashish Kapoor

In Proc. IEEE International Conf. on Computer Vision (ICCV), Sydney, Australia, Dec 3-6, 2013.

[PDF] [Poster] [Datasets] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 27.87% )

Description: picture

Collaborative Active Learning of a Kernel Machine Ensemble for Recognition

Gang Hua, Chengjiang Long, Ming Yang, and Yan Gao

In Proc. IEEE International Conf. on Computer Vision (ICCV), Sydney, Australia, Dec 3-6, 2013.

[PDF] [Poster] [Datasets] [BibTeX] (Top 3 Conferences in Computer Vision, acceptance rate: 27.87% )

Description: picture

A New K Nearest Neighbors Search Algorithm Using Cell Grids for 3D Scattered Point Cloud

Jianhui Zhao, Chengjiang Long, Shuping Xiong, Cheng Liu, and Zhiyong Yuan

ELEKTRONIKA IR ELEKTROTECHNIKA, 20(1):81-87, 2014.

[PDF] [BibTeX] (SCI journal)

Description: picture

A New Region Growing Algorithm for Triangular Mesh Recovery from Scattered 3D Points

Chengjiang Long, Jianhui Zhao, Ravindra S. Goonetilleke, Shuping Xiong, Yihua Ding, Zhiyong Yuan, and Yuanyuan Zhang

Transactions on Edutainment VI, LNCS, 6758: 237®C246, 2011.

[PDF] [BibTeX]

Description: picture

Transmission: A New Feature for Computer Vision Based Smoke Detection

Chengjiang Long, Jianhui Zhao, Shizhong Han, Lu Xiong, Zhiyong Yuan, Jing Huang, and Weiwei Gao

AICI 2010, Part I, Lecture Notes in Artificial Intelligence, 6319: 389-396, 2010

[PDF] [BibTeX]

Description: picture

Improvements on IPD Algorithm for Triangular Mesh Reconstruction from 3D Point Cloud

Chengjiang Long, Jianhui Zhao, Zhiyong Yuan, Lu Xiong, Guozhong Liang, and Xuangmin Jiang

In Proc. MINES, Pages 305-308, 2009.

[PDF] [BibTeX]

Description: picture

A New K-Nearest Neighbors Search Algorithm Based on 3D Cell Grids

Jianhui Zhao, Chengjiang Long, Yihua Ding, and Zhiyong Yuan

Geomatics and Information Science of Wuhan University (in Chinese), 34(5):615-618, 2009.

[PDF] [BibTeX]





Description: Free Hit Counter
© By Chengjiang Long since Mar 21, 2012.