About Me

I am a tenure-track Assistant Professor of the AI Thrust at The Hong Kong University of Science and Technology (Guangzhou). I received my Ph.D. at School of Computer Science and Engineering, Nanyang Technological University, supervised by Prof. Miao Chun Yan. My co-supervisor is Prof. Guosheng Lin. I also work closely with Prof. Steven Hoi. I was an intern working with Jiashi Feng at TikTok, Singapore.

My general research interests lie in the development of AI-powered perception and generation algorithms for multimodal data, including text, images, videos, and 3D shapes. Recently, we are working on projects of 3D reconstruction and LLM-based agents. Please drop me an email if you are interested in collaborations.

I am looking for self-motivated PhD students, RAs and interns.

Please check my recruitment page.


Selected Publications

  • GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes [Paper]
    Gaochao Song, Cheng Chong, Hao Wang*. (* denotes corresponding author)
    Conference on Neural Information Processing Systems (NeurIPS 2024)
  • LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay [Paper] [Code]
    Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang*. (* denotes corresponding author)
    The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main)
  • HMR-Adapter: A Lightweight Adapter with Dual-Path Cross Augmentation for Expressive Human Mesh Recovery [Paper]
    Wenhao Shen, Wanqi Yin, Hao Wang*, Chen Wei, Zhongang Cai, Lei Yang, Guosheng Lin*. (* denotes corresponding author)
    ACM International Conference on Multimedia (ACM MM-2024)
  • Learning Temporal Variations for 4D Point Cloud Segmentation [Paper]
    Hanyu Shi, Jiacheng Wei, Hao Wang, Fayao Liu, Guosheng Lin.
    International Journal of Computer Vision (IJCV-2024) [IF:19.5]
  • ManiCLIP: Multi-Attribute Face Manipulation from Text [Paper] [Code]
    Hao Wang, Guosheng Lin, Ana GarcĂ­a del Molino, Anran Wang, Jiashi Feng, Zhiqi Shen.
    International Journal of Computer Vision (IJCV-2024) [IF:19.5]
  • COM3D: Leveraging Cross-View Correspondence and Cross-Modal Mining for 3D Retrieval [Paper]
    Hao Wu, Ruochong LI, Hao Wang*, Hui Xiong. (* denotes corresponding author)
    IEEE Conference on Multimedia Expo (ICME-2024 Oral)
  • TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision [Paper] [Code]
    Jiacheng Wei*, Hao Wang*, Jiashi Feng, Guosheng Lin, Kim-Hui Yap. (* denotes equal contributions)
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2023)
  • Cross-Modal Graph with Meta Concepts for Video Captioning [Paper] [Code]
    Hao Wang, Guosheng Lin, Steven Hoi, Chunyan Miao.
    IEEE Transactions on Image Processing (TIP-2022) [IF:11.041]
  • Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval [Paper]
    Hao Wang, Guosheng Lin, Steven Hoi, Chunyan Miao.
    ACM International Conference on Multimedia (ACM MM-2022)
  • Learning Structural Representations for Recipe Generation and Food Retrieval [Paper]
    Hao Wang, Guosheng Lin, Steven Hoi, Chunyan Miao.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI-2022) [IF:24.314]
  • Cycle-Consistent Inverse GAN for Text-to-Image Synthesis [Paper]
    Hao Wang, Guosheng Lin, Steven Hoi, Chunyan Miao.
    ACM International Conference on Multimedia (ACM MM-2021)
  • Structure-Aware Generation Network for Recipe Generation from Images [Paper] [Code]
    Hao Wang, Guosheng Lin, Steven Hoi, Chunyan Miao.
    European Conference on Computer Vision (ECCV-2020)
  • SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds [Paper] [Code]
    Hanyu Shi, Guosheng Lin, Hao Wang, Tzu-Yi Hung, Zhenhua Wang.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2020)
  • FoodAI: Food Image Recognition via Deep Learning for Smart Food Logging [Paper]
    Doyen Sahoo, Hao Wang, Shu Ke, Xiongwei Wu, Hung Le, Palakorn Achananuparp, Ee-Peng Lim, Steven Hoi.
    ACM SIGKDD conference, 2019 (KDD-2019)
  • Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images [Paper] [Code]
    Hao Wang, Doyen Sahoo, Chenghao Liu, Ee-peng Lim, Steven C. H. Hoi.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR-2019)