Zhi Tian

I am currently a Research Scientist at Bytedance. Before that, I obtained a PhD in May 2021 at School of Computer Science, The University of Adelaide, Australia, advised by Prof. Chunhua Shen. I was also fortunate to work with Dr. Weilin Huang and Prof. Yu Qiao at Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences.

I published a few well-known computer vision algorithms including the object detector FCOS, and the scene text detection method CTPN.
I was awarded Google Phd Fellowship in 2019.

We are always looking for talented interns/full-time researchers with strong coding skills and research experience. Please drop me an email if interested.

Links to: [GitHub] [Google Scholar]

Research

I am working to develop high-performance and practical algorithms for the following computer vision research problems:

2D/3D Object detection, instance segmentation and semantic segmentation.
Scene text understanding (i.e., OCR).

Publications

Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images
Zhi Tian, Xiangxiang Chu, Xiaoming Wang, Xiaolin Wei, Chunhua Shen. NeurIPS 2022
[ArXiv Link]

Instance and Panoptic Segmentation Using Conditional Convolutions
Zhi Tian, Bowen Zhang, Hao Chen, Chunhua Shen. TPAMI 2022
[ArXiv Link] [Code]

BoxInst: High-Performance Instance Segmentation with Box Annotations
Zhi Tian, Chunhua Shen, Xinlong Wang, Hao Chen. CVPR 2021
[ArXiv Link] [Code] [Video Demo]

FCOS: A Simple and Strong Anchor-free Object Detector
Zhi Tian, Chunhua Shen, Hao Chen, Tong He. TPAMI 2020
[ArXiv Link] [Code]

Conditional Convolutions for Instance Segmentation
Zhi Tian, Chunhua Shen, Hao Chen. ECCV 2020, Oral (top 2%)
[ArXiv Link] [Code]

DirectPose: Direct End-to-End Multi-Person Pose Estimation
Zhi Tian, Hao Chen, Chunhua Shen. Preprint 2019
[ArXiv Link]

FCOS: Fully Convolutional One-Stage Object Detection
Zhi Tian, Chunhua Shen, Hao Chen, Tong He. ICCV 2019
[ArXiv Link] [Code] [Code built on Detectron2]

Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
Zhi Tian, Tong He, Chunhua Shen, Youliang Yan. CVPR 2019
[ArXiv Link]

An End-to-end TextSpotter with Explicit Alignment and Attention
Tong He*, Zhi Tian*, Weilin Huang, Chunhua Shen, Yu Qiao, Changming Sun. CVPR 2018
[ArXiv Link] [Code]

Detecting Text in Natural Image with Connectionist Text Proposal Network
Zhi Tian, Weilin Huang, Tong He, Pan He, Yu Qiao. ECCV 2016
[ArXiv Link] [Code]

SegViT: Semantic Segmentation with Plain Vision Transformers
Bowen Zhang, Zhi Tian, Quan Tang, Xiangxiang Chu, Xiaolin Wei, Chunhua Shen, Yifan Liu. NeurIPS 2022
[ArXiv Link]

Poseur: Direct Human Pose Regression with Transformers
Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, Anton van den Hengel. ECCV 2022
[ArXiv Link]

Dynamic Neural Representational Decoders for High-resolution Semantic Segmentation
Bowen Zhang, Yifan Liu, Zhi Tian, Chunhua Shen. NeurIPS 2021
[ArXiv Link]

Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen. NeurIPS 2021
[ArXiv Link] [Code]

FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutions
Weian Mao, Zhi Tian, Xinlong Wang, Chunhua Shen. CVPR 2021
[ArXiv Link] [Code]

Unifying Instance and Panoptic Segmentation with Dynamic Rank-1 Convolutions
Hao Chen, Chunhua Shen, Zhi Tian. Preprint 2020
[ArXiv Link]

Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
Tong He, Dong Gong, Zhi Tian, Chunhua Shen. ECCV 2020
[ArXiv Link]

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
Hao Chen, Kunyang Sun, Zhi Tian, Chunhua Shen, Yongming Huang, Youliang Yan. CVPR 2020, Oral
[ArXiv Link] [Code]

NAS-FCOS: Fast Neural Architecture Search for Object Detection
Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen. CVPR 2020
[ArXiv Link] [Code]

Mask Encoding for Single Shot Instance Segmentation
Rufeng Zhang, Zhi Tian, Mingyu You, Chunhua Shen, Youliang Yan. CVPR 2020
[ArXiv Link] [Code]

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Wei Yin, Xinlong Wang, Chunhua Shen, Yifan Liu, Zhi Tian, Songcen Xu, Changming Sun, Dou Renyin. Preprint 2020
[ArXiv Link] [Code]

Convolutional Character Networks
Linjie Xing, Zhi Tian, Weilin Huang, Matthew Scott. ICCV 2019
[ArXiv Link] [Code]

Knowledge Adaptation for Efficient Semantic Segmentation
Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, Youliang Yan. CVPR 2019
[ArXiv Link]

Prominent Awards

Google Phd Fellowship 2019
Google Blog

University Doctoral Research Medal 2021 (for the highest quality theses, in the top 3%)
Research Student Excellence Awards

First Place in Apps for Office Challenge
Imagine Cup 2014 World Finals, Microsoft

Professional Activities

Reviewer: ICML 2021, TPAMI, CVPR 2021, AAAI 2021, NeurIPS 2020, IJCV, ECCV 2020, CVPR 2020, AAAI 2020, ICCV 2019 and CVPR 2019