Jianfeng Zhang (张健锋)

PhD Student

Vision & Machine Learning Lab,
Block E4 #08-24,
4 Engineering Drive 3,
National University of Singapore

Email: jf.zhang958 dot outlook dot com

Biography

I am currently a first-year PhD student at NUS Vision & Machine Learning Lab, fortunately supervised by Prof. Jiashi Feng and working closely with Dr. Xuecheng Nie. Previously, I received the B.S. degree from Department of Applied Mathematics in Wuhan University, supervised by Prof. Xiaoping Zhang for undergraduate research.

My research interests include 3D computer vision and deep learning. Currently, I'm focusing on 3D human pose/shape estimation and related applications.

Always open to cooperation opportunities. If you're interested, don't hesitate to contact me.

Publications

	Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation Jianfeng Zhang, Xuecheng Nie, Jiashi Feng arxiv, 2020 PDF \| Code \| Demo \| Website \| Poster \| Slides \| BibTex
	Single-stage Multi-person Pose Machines Xuecheng Nie, Jianfeng Zhang, Shuicheng Yan, Jiashi Feng IEEE International Conference on Computer Vision (ICCV), 2019 PDF \| Code \| Demo \| Website \| Poster \| Slides \| BibTex
	Developing a LSTM based Model for Predicting Water Table Depth Jianfeng Zhang, Yan Zhu, Xiaoping Zhang, Ming Ye, Jinzhong Yang Journal of Hydrology (JH), 2018 PDF \| Code

Projects

	Deeplab V3+ in PyTorch We provide a high-performance PyTorch implementation of Deeplab V3+. This project receives more than 1.6k star on GitHub. PDF \| Code
	Deep Grabcut (DeepGC) We reimplement "Deep Grabcut for Object Selection" in PyTorch. This paper proposes an interactive segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map. A convolutional encoder-decoder network is trained end-to-end by concatenating images with these distance maps as inputs and predicting the object masks as outputs. PDF \| Code
	Video Activity Recognition in PyTorch We reimplement several video activity recognition models including C3D, R2Plus1D, R3D in PyTorch. In addition, we adopt C3D model to build an online web game called "You Perform, I Guess!", which obtains Excellent Demo Award in DeeCamp 2018. Code \| Demo
	Interactive Segmentation on RGBD Image We reimplement “Interactive Segmentation on RGBD Images via Cue Selection”. This paper proposes a novel interactive segmentation algorithm which can incorporate multiple feature cues like color, depth and normals in a graph cut framework. PDF \| Code
	Total Variation Image Segmentation Model Based on Primal-dual Method We implement total variation image segmentation algorithm and applied primal-dual method to optimize it. We implement our algorithm in an interactive fashion, which allows users to choose object of interest. Additionally, we combine the algorithm with K-means to improve the final results. PDF \| Code
	Video Object Segmentation Framework We build a Video Object Segmentation Framework. In this framework, we combine MobileNetV2, YOLOV2 and Deep Grabcut to perform video object segmentation. PDF \| Code

Honors & Awards

Excellent Demo Award, DeeCamp, 2018

Best Bachelor Thesis Award, School of Mathematics and Stastics, Wuhan University, 2018

Excellent Student Award, School of Mathematics and Stastics, Wuhan University, 2018

Award for Merit Student of Wuhan University, 2015-2017

Teaching

2017-2018	Spring	C Language Programming
2017-2018	Fall	Data Structures and Algorithms in Python

	Deeplab V3+ in PyTorch We provide a high-performance PyTorch implementation of Deeplab V3+. This project receives more than 1.6k star on GitHub. PDF \| Code
	Deep Grabcut (DeepGC) We reimplement "Deep Grabcut for Object Selection" in PyTorch. This paper proposes an interactive segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map. A convolutional encoder-decoder network is trained end-to-end by concatenating images with these distance maps as inputs and predicting the object masks as outputs. PDF \| Code
	Video Activity Recognition in PyTorch We reimplement several video activity recognition models including C3D, R2Plus1D, R3D in PyTorch. In addition, we adopt C3D model to build an online web game called "You Perform, I Guess!", which obtains Excellent Demo Award in DeeCamp 2018. Code \| Demo
	Interactive Segmentation on RGBD Image We reimplement “Interactive Segmentation on RGBD Images via Cue Selection”. This paper proposes a novel interactive segmentation algorithm which can incorporate multiple feature cues like color, depth and normals in a graph cut framework. PDF \| Code
	Total Variation Image Segmentation Model Based on Primal-dual Method We implement total variation image segmentation algorithm and applied primal-dual method to optimize it. We implement our algorithm in an interactive fashion, which allows users to choose object of interest. Additionally, we combine the algorithm with K-means to improve the final results. PDF \| Code
	Video Object Segmentation Framework We build a Video Object Segmentation Framework. In this framework, we combine MobileNetV2, YOLOV2 and Deep Grabcut to perform video object segmentation. PDF \| Code