Jianchao Tan

Jianchao Tan (谈建超)

Email: tanjianchaoustc@gmail.com
Phone: +1-7036273266
Phone: +86-15801501024

Currently, I am a Senior Research Scientist at Kwai inc. Previously, I was a Research Scientist at Megvii (Face++) in Redmond, WA. I obtained my Ph.D. degree from Computer Science Department (CS) in George Mason University (GMU) at May 2019. I was advised by Dr. Yotam Gingold at Creativity and Graphics Lab (CraGL). I obtained my Bachelor degree from Electronic Engineering and Information Science Department (EEIS) in University of Science and Technology of China (USTC) at July 2013. My undergraduate research advisor is Dr. Xuejin Chen.

My research interests are model compression, image and video processing, computer vision and graphics. I am focusing on empowering users in image and video analysis and editing. I am also interested in applying deep learning techniques to solve image, video and mesh related problems. I am working on model compression and neural architecture search algorithms to improve neural network models in terms of both efficiency and effectiveness.

Here is my: Resume , Github , Google Scholar and Youtube.



News


NEW!   I joined in Kwai inc. in Bellevue, WA as a Research Scientist at Oct 28th 2019!
NEW!   My Ph.D. thesis work is chosen to be presented at SIGGRAPH 2019 Thesis Fast Forward Live Presentation! Here is video demo.
NEW!   I joined in Megvii Research USA (Face++) in Redmond, WA as a Research Scientist at June 10th 2019!
NEW!   I passed dissertation final defense on April 26th, 2019. Finally Dr. Tan! My Thesis is Image and Video Decomposition and Editing.
NEW!   I received 2019 Outstanding Graduate Student Award in CS department (2 recipients)!
NEW!   Sep 25, 2018:   We released code Github:fastLayerDecomposition for our paper "Efficient palette-based decomposition and recoloring of images via RGBXY-space geometry"!
NEW!   Sep 25, 2018:   We released code Github:Pigmento-PaintingAnalysis for our paper "Pigmento: Pigment-Based Image Analysis and Editing"!
NEW!   Aug 11, 2018:   Our paper Efficient palette-based decomposition and recoloring of images via RGBXY-space geometry is accepted by SIGGRAPH Asia 2018
NEW!   July 09, 2018:   My Ph.D. work is selected by SIGGRAPH 2018 Doctoral Consortium, I will present it at SIGGRAPH on Aug 11 Saturday. There are totally 8 presenters this year. Here is my summary draft.
NEW!   Jun 14, 2018:   Our paper: Pigmento: Pigment-based image analysis and editing is accepted by IEEE TVCG. To appear.
NEW!   Mar 23, 2018:   I will be a Research Intern at Adobe Creative Intelligence Lab, San Francisco, in Summer 2018. See you there!
NEW!   Oct 12, 2016:   We released our code Github:Image-Decomposing for paper "Decomposing Images into Layers via RGB-space Geometry"!
NEW!   Feb 29, 2016:   I will be a Research Intern at Adobe Creative Technologies Lab, San Francisco, in Summer 2016. See you there!
NEW!   Jan 29, 2016:   We released our code Github:timelapse for paper "Decomposing Time-Lapse Paintings into Layers"!



Publications

If you are NOT a reviewer, feel free to click here to show publications under review.

GDP: Stablized Neural Network Pruning via Gates with Differentiable Polarization.   Yi Guo, Huan Yuan, Jianchao Tan, Zhangyang Wang, Sen Yang, Ji Liu.
ICCV 2021

Hand Image Understanding via Deep Multi-Task Learning.   Xiong Zhang, Hongsheng Huang, Jianchao Tan, Hongming Xu, Hong Mo, Cheng Yang, Guozhu Peng, Lei Wang, Wenqi Ren, Ji Liu.
ICCV 2021

Lossless CNN Channel Pruning via Decoupling Remembering and Forgetting.   Xiaohan Ding, Tianxiang Hao, Jianchao Tan, Ji Liu, Jungong Han, Yucheng Guo, Guiguang Ding.
ICCV 2021

Video Recoloring via Spatial-Temporal Geometric Palettes.   Zhengjun Du, Kaixiang Lei, Kun Xu, Jianchao Tan, Yotam Gingold.
ACM Transactions on Graphics (TOG), in proceedings of SIGGRAPH 2021

DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation.   Xiong Zhang, Hongmin Xu, Hong Mo, Jianchao Tan, Cheng Yang, Lei Wang, Wenqi Ren.
CVPR 2021

UMEC: Unified Model and Embedding Compression for Efficient Recommendation Systems.   Jiayi Shen, Haotao Wang, Shupeng Gui, Jianchao Tan, Zhangyang Wang, Ji Liu.
ICLR 2021

HOT-Net: Non-Autoregressive Transformer for 3D Hand-Object PoseEstimation.   Lin Huang, Jianchao Tan, Jingjing Meng, Ji Liu, Junsong Yuan.
in proceedings of ACM International Conference on Multimedia (ACM MM), 2020

Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation.   Lin Huang, Jianchao Tan, Ji Liu, Junsong Yuan.
European Conference on Computer Vision (ECCV), 2020

Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards.   Xuewen Yang, Heming Zhang, Di Jin, Yingru Liu, Chi-Hao Wu, Jianchao Tan, Dongliang Xie, Jue Wang, and Xin Wang.
European Conference on Computer Vision (ECCV), 2020

Learning Color Compatibility in Fashion Outfits.   Heming Zhang, Xuewen Yang, Jianchao Tan, Chi-Hao Wu, Jue Wang, and C-C.Jay Kuo
Arxiv 2020 Jul.

Hyperspectral Inverse Skinning   Songrun Liu, Jianchao Tan, Zhigang Deng, Yotam Gingold
Jan 2020.   Computer Graphics Forum (CGF) 2020.

Pigmento: Pigment-based image analysis and editing  Jianchao Tan, Stephen DiVerdi, Jingwan Lu, Yotam Gingold
Jun 2018.   IEEE Transactions on Visualization and Computer Graphics (TVCG), 2019.
And its exposure in I-Programmer website: Pigments - Beyond RGB

Efficient palette-based decomposition and recoloring of images via RGBXY-space geometry   Jianchao Tan, Jose Echevarria, Yotam Gingold
Aug 2018.   ACM Transactions on Graphics (TOG) 37(6). Also in Proceedings of SIGGRAPH Asia 2018.
Our core code

Decomposing Images into Layers via RGB-space Geometry   Jianchao Tan, Jyh-Ming Lien, Yotam Gingold
Aug 2016.   ACM Transactions on Graphics (TOG) 36(1).
Also presented at SIGGRAPH 2017.

Decomposing Time-Lapse Paintings into Layers   Jianchao Tan, Marek Dvorožňák, Daniel Sýkora, Yotam Gingold
Jul 2015.   ACM Transactions on Graphics (TOG) 34(4). Also in Proceedings of SIGGRAPH 2015.
Invited for presentation at FMX 2016 Highlights of SIGGRAPH.



Honors

May 2021:   2021 CVPR NAS Challenge: Performance Prediction Track, Rank 2nd among all teams from the world.

Jul. 2020:   2020 Low-Power Computer Vision Challenge (LPCV): Video Track, Rank 2nd among all teams from the world.

Jul. 2019:   2019 SIGGRAPH Thesis Fast Forward.

Mar. 2019:   2019 Outstanding Graduate Student Award in CS department (2 recipients).

Jul. 2018:   2018 SIGGRAPH Doctoral Consortium.

Dec. 2017:  2018 Adobe Research Fellowship Finalist.