About Me

I am a Computer Science PhD student at the University of Adelaide and supervised by Prof. Chunhua Shen. Before that I got my Bachelor degree from Tongji University. I had a great time researching computer vision at Megvii (Face++), Tencent Youtu Lab and ByteDance AI Lab.

My research interests lie in the area of computer vision and machine learning, especially in enabling machines to see and understand the environment. Specific research topics include 2D/3D/video object detection and segmentation, and their label efficient learning.

Contact

Feel free to send me an email if you are interested in my research.

Email: xinlong.wang96 [AT] gmail.com OR xinlong.wang [AT] adelaide.edu.au

News

[Dec.2020] Optimized SOLO/SOLOv2 with PyTorch on MMDetection and Detectron2, and third-party implementation with PaddlePaddle.
[Dec.2020] Presented our work SOLOv2 at NeurIPS 2020 virtually at home.
[Dec.2020] One paper is accepted by AAAI 2021.
[Sept.2020] One paper is accepted by NeurIPS 2020.
[Aug.2020] Presented our work SOLO at ECCV 2020 virtually at home.
[Jul.2020] Two papers are accepted by ECCV 2020.
[Nov.2019] One paper is accepted by AAAI 2020 as Oral.
[Jun.2019] Presented our work ASIS at CVPR 2019 in Long Beach, USA.
[Feb.2019] One paper is accepted by CVPR 2019.
[Jul.2018] Graduated from Tongji Univerisity with honors.
[Jun.2018] Presented our work Repulsion Loss at CVPR 2018 in Salt Lake City, USA.
[Feb.2018] One paper is accepted by CVPR 2018.

Publications

• Dense Contrastive Learning for Self-Supervised Visual Pre-Training
  Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li
  arXiv pre-print, 2020
  [arXiv] [bibtex]

• BoxInst: High-Performance Instance Segmentation with Box Annotations
  Zhi Tian, Chunhua Shen, Xinlong Wang, Hao Chen
  arXiv pre-print, 2020
  [arXiv] [demo]

• End-to-End Video Instance Segmentation with Transformers
  Yuqing Wang, Zhaoliang Xu, Xinlong Wang, Chunhua Shen, Baoshan Cheng, Hao Shen, Huaxia Xia
  arXiv pre-print, 2020
  [arXiv]

• Diverse Knowledge Distillation for End-to-End Person Search
  Xinyu Zhang, Xinlong Wang, Jia-Wang Bian, Chunhua Shen, Mingyu You
  AAAI Conference on Artificial Intelligence (AAAI), 2021
  [arXiv]

• SOLOv2: Dynamic and Fast Instance Segmentation
  Xinlong Wang, Rufeng Zhang, Tao Kong, Lei Li, Chunhua Shen
  Advances in Neural Information Processing Systems (NeurIPS), 2020
  [arXiv] [bibtex] [demo] [code] [code@adet]

• SOLO: Segmenting Objects by Locations
  Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, Lei Li
  European Conference on Computer Vision (ECCV), 2020
  [arXiv] [bibtex] [code]

• Instance-Aware Embedding for Point Cloud Instance Segmentation
  Tong He, Yifan liu, Chunhua Shen, Xinlong Wang, Changming Sun
  European Conference on Computer Vision (ECCV), 2020
  [Paper]

• Task-Aware Monocular Depth Estimation for 3D Object Detection
  Xinlong Wang, Wei Yin, Tao Kong, Yuning Jiang, Lei Li and Chunhua Shen
  AAAI Conference on Artificial Intelligence (AAAI), 2020, (Oral)
  [arXiv] [bibtex] [code]

• Associatively Segmenting Instances and Semantics in Point Clouds
  Xinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen and Jiaya Jia
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
  [arXiv] [bibtex] [code]

• Repulsion Loss: Detecting Pedestrians in a Crowd
  Xinlong Wang, Tete Xiao, Yuning Jiang, Shuai Shao, Jian Sun and Chunhua Shen
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
  [arXiv] [bibtex]

Professional Activities

• Journal Reviewer
  TIP, TMM, Neurocomputing, PR

• Conference Reviewer
  ICCV 2021, ICML 2021, CVPR 2021, AAAI 2021, NeurIPS 2020, AAAI 2020

• Presentations
  Microsoft Research Asia (MSRA) VCG talk: “SOLO: Segmenting Objects by Locations”, 2020
  Megvii Detection talk: “SOLO: Segmenting Objects by Locations”, 2019
  Beihang University CoLab talk: “SOLO: Segmenting Objects by Locations”, 2019
  Jishi Online talk: “Instance Segmentation in 3D Point Clouds”, 2019

 unique visitors since Feb 2018