Zhiwu Huang

I will be starting as an Assistant Professor in the School of Computing and Information Systems at Singapore Management University (SMU). Before coming to Singapore, I worked as a Guest/Postdoc Researcher with Prof. Luc Van Gool in Computer Vision Lab at ETH Zurich. My AutoVL group studies Automated Visual Learning that aims for making machines to learn the visual world, all by themselves. Our research focuses on visual fake, affect and behavior computing through automated machine learning on data, label, feature, neuron and task.

I am actively looking for motivated and talented PhD students to join our research group at SMU. Please follow the instructions to reach me if you are interested.

News

  • 07/2021, One paper "Direct Differentiable Augmentation Search" is accepted by ICCV 2021.
  • 04/2021, One paper "Neural Architecture Search of SPD Manifold Networks" is accepted by IJCAI 2021.
  • 03/2021, Two papers "Efficient Conditional GAN Transfer with Knowledge Propagation across Classes" and "GANmut: Learning Interpretable Conditional Space for Gamut of Emotions" are accepted by CVPR 2021.
  • 01/2021, One paper "Spectral Tensor Train Parameterization of Deep Learning Layers" is accepted by AISTATS 2021.
  • 12/2020, One paper "Neural Architecture Search as Sparse Supernet" is accepted by AAAI 2021.
  • 11/2020, One paper "Facial Emotion Recognition with Noisy Multi-task Annotations" is accepted by WACV 2021.
  • 08/2020, One paper "AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results" will appear at the workshop AIM in conjunction with ECCV 2020.
  • 07/2020, One paper "Weakly Paired Multi-Domain Image Translation" is accepted by BMVC 2020 as an oral.
  • 07/2020, One paper "Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search" is accepted by ECCV 2020.
  • 05/2020, We are organizing AIM Video Super-Resolution Challenge @ECCV 2020.
  • 05/2020, One paper "NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results" will appear at the workshop NTIRE in conjunction with CVPR 2020.
  • 12/2019, We are organizing NTIRE Video Quality Mapping Challenge @CVPR 2020.
  • 10/2019, One dataset paper "The Vid3oC and IntVID Datasets for Video Super Resolution and Quality Mapping" will appear at the workshop AIM in ICCV 2019.
  • 10/2019, We are organizing a workshop "AIM: Advances in Image Manipulation Workshop and Challenges on Image and Video Manipulation" and a tutorial "FIRE: From Image Restoration to Enhancement and Beyond" at ICCV, Oct. 27, 2019.
  • 02/2019, One paper "Sliced Wasserstein Generative Models" is accepted by CVPR 2019. This paper was selected as one of the best publications of the week (20.04.2019), by DeepAI. Link to DeepAI Website
  • Older news...
  • Research

    Memembers (/Collaborators)

  • Suryansh Kumar (Postdoc researcher), Nov. 2019 - Present, with Luc Van Gool
  • Anton Obukhov (PhD candidate), Feb. 2020 - Present, with Dengxin Dai , Stamatios Georgoulis , Luc Van Gool
  • Yuan Tian (PhD candidate), Feb. 2020 - Present, with Olga Fink
  • Qin Wang (PhD candidate), Feb. 2020 - Present, with Wen Li , Dengxin Dai , Olga Fink
  • Mohamad Shahbazi (PhD candidate), Nov. 2019 - Present, with Danda Pani Paudel , Ajad Chhatkuli , Luc Van Gool
  • Dario Fuoli (PhD candidate), June 2019 - Present, with Radu Timofte , Danda Pani Paudel , Martin Danelljan , Luc Van Gool
  • Jiqing Wu (PhD, graduated, Thesis ), Nov. 2016 - March 2020, with Luc Van Gool
  • Projects (GitHub Group)

    Adversarial Fake Computing

    Source Code | TrailerFaces Dataset

    Sliced Wasserstein Generative Models. Jiqing Wu* , Zhiwu Huang*, Dinesh Acharya, Wen Li , Janine Thoma , Danda Pani Paudel , Luc Van Gool . (*indicates equal contributions). In Computer Vision and Pattern Recognition (CVPR), 2019 . Paper
    Extension: Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs. Dinesh Acharya, Zhiwu Huang, Danda Pani Paudel , Luc Van Gool . arXiv preprint arXiv:1810.02419, 2018. Paper | Code (Automated Data Learning)

    Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search. Yuan Tian*, Qin Wang*, Zhiwu Huang, Wen Li, Dengxin Dai , Minghao Yang , Jun Wang , Olga Fink. (*indicates equal contributions) . In European Conference on Computer Vision (ECCV), 2020 . Paper | Code (Automated Neuron Learning)

    Efficient Conditional GAN Transfer with Knowledge Propagation across Classes. Mohamad Shahbazi, Zhiwu Huang, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool. In Computer Vision and Pattern Recognition (CVPR), 2021. Preprint | Code (Automated Task Learning)

    Video Quality Mapping Challenge | Video Super-Resolution Challenge

    The Vid3oC and IntVID Datasets for Video Super Resolution and Quality Mapping. Sohyeong Kim, Guanju Li, Dario Fuoli , Martin Danelljan , Zhiwu Huang, Shuhang Gu , Radu Timofte . In International Conference on Computer Vision (ICCV) workshop, 2019 . Paper

    Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement. Zhiwu Huang, Danda Pani Paudel , Dario Fuoli , Guanju Li , Jiqing Wu , Radu Timofte , Luc Van Gool . arXiv preprint arXiv:1910.10455, 2019 . Paper

    NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results. Dario Fuoli , Zhiwu Huang, Martin Danelljan, Radu Timofte and et al. In Computer Vision and Pattern Recognition (CVPR) workshop, 2020 . Paper

    AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results. Dario Fuoli , Zhiwu Huang, Radu Timofte and et al. In European Conference on Computer Vision (ECCV) workshop, 2020 . Paper

    Dario Fuoli , Zhiwu Huang, Danda Pani Paudel , Luc Van Gool , Radu Timofte . An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement. arXiv preprint arXiv:2012.13033, 2020 . Paper

    Facial Affective Computing

    Source Code | AFEW SPDData | TrailerAffect Dataset

    A Riemannian Network for SPD Matrix Learning. Zhiwu Huang, Luc Van Gool . In Association for the Advancement of Artificial Intelligence (AAAI), 2017. Paper | Code (Automated Feature Learning)
    Extension: Covariance Pooling for Facial Expression Recognition. Dinesh Acharya, Zhiwu Huang, Danda Pani Paudel , Luc Van Gool . In Computer Vision and Pattern Recognition (CVPR) workshop, 2018 . Paper | Code

    Building Deep Networks on Grassmann Manifolds. Zhiwu Huang, Jiqing Wu , Luc Van Gool . In Association for the Advancement of Artificial Intelligence (AAAI), 2018. Paper | Code (Automated Feature Learning)

    Neural Architecture Search of SPD Manifold Networks. Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar , Erik Goron Endsjo, Yan Wu, Luc Van Gool . In International Joint Conference on Artificial Intelligence (IJCAI), 2021. Paper (Automated Neuron Learning)

    Facial Emotion Recognition with Noisy Multi-task Annotations. Siwei Zhang, Zhiwu Huang, Danda Pani Paudel , Luc Van Gool . In Winter Conference on Applications of Computer Vision (WACV), 2021 . Paper | Code (Automated Label Learning)

    GANmut: Learning Interpretable Conditional Space for Gamut of Emotions. Stefano D'Apolito, Danda Pani Paudel, Zhiwu Huang, Andres Romero Vergara, Luc Van Gool. In Computer Vision and Pattern Recognition (CVPR), 2021. Preprint | Code (Automated Label Learning)

    Skeletal Behavior Computing

    Source Code | G3D LieGroupData

    Deep Learning on Lie Groups for Skeleton-based Action Recognition. Zhiwu Huang, Chengde Wan , Thomas Probst , Luc Van Gool . In Computer Vision and Pattern Recognition (CVPR), 2017 . Paper | Code | Spotlight (Automated Feature Learning)
    Extension: Studying Multiple Cues for Human Action Recognition on RGB+D Data. Jonathan Gan, Zhiwu Huang, Danda Pani Paudel Tech. Report (Semester Thesis), 2017. Paper

    Building Deep Networks on Grassmann Manifolds. Zhiwu Huang, Jiqing Wu , Luc Van Gool . In Association for the Advancement of Artificial Intelligence (AAAI), 2018. Paper | Code (Automated Feature Learning)

    Neural Architecture Search of SPD Manifold Networks. Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar , Erik Goron Endsjo, Yan Wu, Luc Van Gool . In International Joint Conference on Artificial Intelligence (IJCAI), 2021. Paper (Automated Neuron Learning) Extension: Neural Architecture Search on Lie Groups for Skeleton-based Action Recognition. Samuele Serafino, Zhiwu Huang, Suryansh Kumar , Luc Van Gool . Tech. Report (Semester Thesis), 2020. Paper