Home   ·   Competitions   ·   Publications  ·   Datasets  ·   Team  ·   Github   ·   Google Scholar   ·   Related Link   ·   中文版本


Guangcong Wang 王广聪


Research Fellow
School of Computer Science and Engineering
Nanyang Technological University
Email: wanggc3 at gmail.com or guangcong.wang at ntu.edu.sg
Address: ABN-02b-14, S-LAB, Nanyang Avenue


Short Bio

Guangcong Wang is currently a research fellow in the School of Computer Science and Engineering at Nanyang Technological University, working with Prof. Ziwei Liu and Prof. Chen Change (Cavan) Loy. Before that, he was a PhD student in the School of Computer Science at Sun Yat-set University, supervised by Prof. Jianhuang Lai and also co-supervised by Prof. Xiaohua Xie.

His research interests include generative models, 3D, person re-identification, semi-supervised learning, interpretability of neural networks, and meta-learning. He has published some papers, such as TOG, IEEE T-NNLS, IEEE TIP, IEEE T-CSVT, ICCV, CVPR, ECCV, KDD, and AAAI.

He has served as a reviewer of IJCV, ICML, NeurIPS, ICCV, CVPR, ECCV, ICLR, AAAI, ICPR, IEEE TIP, IEEE T-CSVT, IEEE TOMM, Neurocomputing and IEEE Signal Processing Letters.

He was awarded Excellent Doctoral Dissertation Award of China Education Society of Electronics.

He joined MMLab@NTU. He is also a member of FAST Lab.

Goals

He has two long-tern goals in this life. One is to build a plausible 3D virtual world system with machine learning methods, called Open 3D Virtual Reality (Open3DVR). The other is to build a biotechnologial system with machine learning methods to solve biotechnologial problems in the future, called Open Biotechnology and Machine Learning (OpenBiotechML).

Open3DVR and OpenBiotechML are non-profit open research platforms, which focus on advancing technologies and benefit humanity.

Life is short. He will spend 30 years to develop related technologies to achieve these two goals. All relevant researchers are welcome.

For every yes, there are a thousand no's.

   

News

[2023-04] Program Chair of Pre-CVPR@NTU.

[2023-04] Code of SceneDreamer is released. Welcome to create your world at Huggingface.

[2022-08] One TOG 2022 (Proc. SIGGRAPH Asia, journal-track) paper is accepted, Text2Light. Welcome to make your high-qualtiy HDR panoramas with texts at Colab.

[2022-07] Two ECCV 2022 papers are accepted, StyleLight and Fast-Vid2Vid. Welcome to use StyleLight to generate HDR panoramas given a LDR FOV image and use Fast-Vid2Vid to compress video-to-video GAN for translation.

[2021-07] One ICCV 2021 paper (oral) is accepted, Efficient Self-supervised Learning. Welcome to use our code.

[2021-06] One TIP paper is accepted, Unsupervised Cross-modality Learning. The first work for unsupervised cross-modality person re-identification

[2021-04] I joined MMLab@NTU.

[2021-03] One IEEE T-NNLS and one ICME (oral) are accepted, Architecture Adaptation and Adaptive VSO.

[2020-12] I have received my PhD degree (CS) from Sun Yat-set University (Excellent Doctoral Dissertation Award of China Education Society of Electronics and Excellent Doctoral Dissertation of SYSU).

[2020-12] Media Coverage: A large-scale person re-identification dataset named SYSU-30k is released, link. The dataset contains lots of persons, which might be used for person-centric tasks. Welcome to use our dataset.

Academic Services

Program chair of Pre-CVPR@NTU

Conferences (Reviewer)

  • ICLR: 2022, 2023
  • ICML: 2021, 2022, 2023
  • NeurIPS: 2020, 2021, 2022, 2023
  • ICCV: 2021, 2023
  • CVPR: 2021, 2022
  • ECCV: 2022
  • AAAI: 2020, 2021, 2022, 2023
  • ICPR: 2020, 2022
  • Journals (Reviewer)

  • IJCV
  • IEEE TIP
  • IEEE TOMM
  • IEEE TCSVT
  • Neurocomputing
  • IEEE Signal Processing Letters
  • The Visual Computer
  • Image and Vison Computing
  • Teaching and Co-supervision

  • Yinuo Yang, MSAI, NTU, Neural Perception and Reconstruction for Virtual Humans, 2021
  • Liang Tong, FYP, NTU, Editing Anime Images using Generative Adversarial Network, 2021
  • Long Zhuo, Intern, Sensetime, GAN compression, 2021
  • Wenqi Liang, Master, SYSU, Unsupervised Single-modality and Cross-modality Person Re-identification, Excellent Master's Thesis, 2021
  • Enqi Zhang, Wenqi Liang (Outstanding Undergraduate's Thesis), Yang Zhou, Xu Li, Bingyun Liu etc., FYP, SYSU, 2016-2020.
  • Statistical Analysis Method, TA, 2018
  • Signals and Systems, TA, 2018
  • Digital Image Processing, TA, 2017
  • Selected Publications

    SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
    Guangcong Wang, Zhaoxi Chen, Chen Change Loy, Ziwei Liu.
    Technical Report, 2023
    PDF Project Page Code Demo




    SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

    Zhaoxi Chen, Guangcong Wang, Ziwei Liu.
    ArXiv, 2023

    PDF Project Page Code Demo




    Text2Light: Zero-Shot Text-Driven HDR Panorama Generation

    Zhaoxi Chen, Guangcong Wang, Ziwei Liu.
    ACM Transactions on Graphics (SIGGRAPH Asia), 2022

    PDF Project Page Code Demo




    StyleLight: HDR Panorama Generation for Lighting Estimation and Editing

    Guangcong Wang, Yinuo Yang, Chen Change Loy, Ziwei Liu.
    European Conference on Computer Vision (ECCV), 2022

    PDF Project Page Code Demo




    Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis

    Long Zhuo, Guangcong Wang, Shikai Li, Wayne Wu, Ziwei Liu.
    European Conference on Computer Vision (ECCV), 2022

    PDF Project Page Code Demo




    Solving Inefficiency of Self-supervised Representation Learning

    Guangrun Wang, Keze Wang, Guangcong Wang, Philip Torr, Liang Lin.
    International Conference on Computer Vision (ICCV), 2021

    PDF Code arXiv




    Homogeneous-to-Heterogeneous: Unsupervised Learning for RGB-Infrared Person Re-Identification

    Wenqi Liang, Guangcong Wang, Jianhuang Lai, Xiaohua Xie.
    IEEE Transactions on Image Processing (TIP), 2021

    PDF




    Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition

    Guangrun Wang, Liang Lin, Rongcong Chen, Guangcong Wang, Jiqi Zhang.
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021

    PDF




    Confidence-Guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detection

    Peijia Chen, Jianhuang Lai, Guangcong Wang, Xiaohua Xie.
    IEEE International Conference on Multimedia and Expo (ICME), 2021 (oral)

    PDF




    Smoothing Adversarial Domain Attack and p-Memory Reconsolidation for Cross-Domain Person Re-Identification

    Guangcong Wang, Jianhuang Lai, Wenqi Liang, Guangrun Wang.
    Computer Vision and Pattern Recognition Conference (CVPR) , 2020

    PDF




    Weakly Supervised Person Re-identification: Cost-effective Learning with A New Benchmark

    Guangrun Wang, Guangcong Wang, Xujie Zhang, Jianhuang Lai, Liang Lin.
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020

    PDF Dataset, Code, Pretrained model




    Grammatically Recognizing Images with Tree Convolution

    Guangrun Wang, Guangcong Wang, Keze Wang, Xiaodan Liang, Liang Lin.
    ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), 2020

    PDF Code




    Spatial-Temporal Person Re-identification

    Guangcong Wang, Jianhuang Lai, Peigen Huang and Xiaohua Xie.
    The Association for the Advancement of Artificial Intelligence (AAAI), 2019

    PDF Code arXiv




    M2M-GAN: Many-to-Many Generative Adversarial Transfer Learning for Person Re-Identification

    Wenqi Liang, Guangcong Wang, Jianhuang Lai.
    ACTA AUTOMATICA SINICA, 2019

    arXiv




    P2SNet: Can an Image Match a Video for Person Re-identification in an End-to-end Way

    Guangcong Wang, Jianhuang Lai, Xiaohua Xie.
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018

    PDF




    Deep Growing Learning

    Guangcong Wang, Xiaohua Xie, Jianhuang Lai, Jiaxuan Zhuo.
    International Conference on Computer Vision (ICCV), 2017

    PDF Code




    Website template credits to Ziwei Liu