Zhiwu Huang
I am a Lecturer (Assistant Professor) affiliated with the Vision, Learning, and Control (VLC) group in the School of Electronics and Computer Science (ECS) at the University of Southampton. I specialize in computer vision and machine learning for artificial general intelligence. I am committed to teaching AI/machines to comprehend the world through multimodal data, enabling them to achieve animal-level, or human-level, or superhuman-level general intelligence. My current focus is on making machine learning models more capable and controllable to understand the physical world, through scaling and aligning compute, data, models, and tasks for deep learning. I am interested in exploring machine learning methodologies, including Riemannian computing, generative modeling, continual learning, and affective computing.
Selected Publication
Han Xue, Zhiwu Huang, Qianru Sun, Li Song, Wenjun Zhang. Freestyle Layout-to-Image Synthesis. Accepted as a highlight (10% of accepted papers, 2.5% of submissions). In Computer Vision and Pattern Recognition (CVPR), 2023. Preprint | Project Page | Code | Oral Presentation
Yabin Wang*, Zhiheng Ma*, Zhiwu Huang, Yaowei Wang, Zhou Su, Xiaopeng Hong. (*indicates equal contribution) . Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference. In Association for the Advancement of Artificial Intelligence (AAAI) , 2023. Preprint | Code
Dario Fuoli, Zhiwu Huang, Danda Pani Paudel, Luc Van Gool, Radu Timofte. An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement. International Journal of Computer Vision (IJCV), 2022. Preprint
Yuan Tian, Klaus-Rudolf Kladny, Qin Wang, Zhiwu Huang, Olga Fink. Multi-agent Actor-Critic with Time Dynamical Opponent Model. Neurocomputing, 2022. Paper | Code
Yabin Wang, Zhiwu Huang*, Xiaopeng Hong*. (*indicates corresponding author) . S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning. In Conference on Neural Information Processing Systems (NeurIPS) , 2022. Paper | OpenReview | Presentation@ContinualAI | Code
Chuqiao Li, Zhiwu Huang*, Danda Pani Paudel, Yabin Wang, Mohamad Shahbazi, Xiaopeng Hong, Luc Van Gool. (*indicates corresponding author) . A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials. In Winter Conference on Applications of Computer Vision (WACV) , 2023. Preprint | Project Page | Oral Presentation
Yan Wu, Zhiwu Huang, Suryansh Kumar, Rhea Sanjay Sukthanker, Radu Timofte, Luc Van Gool. Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution. In Computer Vision and Pattern Recognition (CVPR) NAS workshop , 2022. Extended Abstract Paper | Supplementary Material | Preprint | Oral Presentation
Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool. Generative Flows with Invertible Attentions. In Computer Vision and Pattern Recognition (CVPR), 2022. Preprint |
Aoming Liu, Zehao Huang, Zhiwu Huang, Naiyan Wang. Direct Differentiable Augmentation Search. In International Conference on Computer Vision (ICCV), 2021. Preprint | Code
Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar, Erik Goron Endsjo, Yan Wu, Luc Van Gool. Neural Architecture Search of SPD Manifold Networks. In International Joint Conference on Artificial Intelligence (IJCAI), 2021 . Paper | Code | Oral Presentation Extension: Samuele Serafino, Zhiwu Huang, Suryansh Kumar, Luc Van Gool. Neural Architecture Search on Lie Groups for Skeleton-based Action Recognition. Tech. Report (Semester Thesis), 2020. Paper
Mohamad Shahbazi, Zhiwu Huang, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool. Efficient Conditional GAN Transfer with Knowledge Propagation across Classes. In Computer Vision and Pattern Recognition (CVPR), 2021. Paper | Supp | Code | Oral Presentation
Stefano D'Apolito, Danda Pani Paudel, Zhiwu Huang*, Andres Romero Vergara, Luc Van Gool. (*indicates corresponding author ) . GANmut: Learning Interpretable Conditional Space for Gamut of Emotions. In Computer Vision and Pattern Recognition (CVPR), 2021. Paper | Supp | Code | Oral Presentation
Anton Obukhov, Maxim Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis, Dengxin Dai, Luc Van Gool. Spectral Tensor Train Parameterization of Deep Learning Layers. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. Preprint | Project Page
Yan Wu*, Aoming Liu*, Zhiwu Huang, Siwei Zhang, Luc Van Gool. (*indicates equal contributions) . Neural Architecture Search as Sparse Supernet. In Association for the Advancement of Artificial Intelligence (AAAI), 2021 . Preprint | Oral Presentation (short) | Code (raw)
Siwei Zhang, Zhiwu Huang, Danda Pani Paudel, Luc Van Gool. Facial Emotion Recognition with Noisy Multi-task Annotations. In Winter Conference on Applications of Computer Vision (WACV), 2021 . Preprint | Code | Oral Presentation
Dario Fuoli, Zhiwu Huang, Radu Timofte and et al. AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results. In European Conference on Computer Vision (ECCV) workshop, 2020 . Paper | Oral Presentation | Challenge Entry
Yuan Tian*, Qin Wang*, Zhiwu Huang, Wen Li, Dengxin Dai, Minghao Yang, Jun Wang, Olga Fink. (*indicates equal contributions) . Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search. In European Conference on Computer Vision (ECCV), 2020 . Paper | Code | Oral Presentation
Dario Fuoli, Zhiwu Huang, Martin Danelljan, Radu Timofte and et al. NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results. In Computer Vision and Pattern Recognition (CVPR) workshop, 2020. Paper | Slides | Challenge Entry
Jiqing Wu*, Zhiwu Huang*, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc Van Gool. (*indicates equal contributions) . Sliced Wasserstein Generative Models. In Computer Vision and Pattern Recognition (CVPR), 2019 . Paper | Supp | Code
Extension: Dinesh Acharya, Zhiwu Huang, Danda Pani Paudel, Luc Van Gool. Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs. arXiv preprint arXiv:1810.02419 , 2018.
Jiqing Wu, Zhiwu Huang, Janine Thoma, Dinesh Acharya, Luc Van Gool. Wasserstein Divergence for GANs. In European Conference on Computer Vision (ECCV), 2018 . Paper | Code
Zhiwu Huang, Jiqing Wu, Luc Van Gool. Building Deep Networks on Grassmann Manifolds. In Association for the Advancement of Artificial Intelligence (AAAI), 2018 . Paper | Code
Zhiwu Huang, Chengde Wan, Thomas Probst, Luc Van Gool. Deep Learning on Lie Groups for Skeleton-based Action Recognition. In Computer Vision and Pattern Recognition (CVPR), 2017. (Spotlight) . Paper | Code
Zhiwu Huang and Luc Van Gool. A Riemannian Network for SPD Matrix Learning. In Association for the Advancement of Artificial Intelligence (AAAI), 2017 . Paper | Code Extension: Dinesh Acharya, Zhiwu Huang, Danda Pani Paudel, Luc Van Gool. Covariance Pooling for Facial Expression Recognition. In Computer Vision and Pattern Recognition (CVPR) workshop, 2018 . Paper | Code