Wei Tsang Ooi
Associate Professor, Department of Computer Science, National University of Singapore
Co-Director, IPAL, a
Franco-Singaporean Joint Research Lab
Associate Professor, Department of Computer Science, National University of Singapore
Co-Director, IPAL, a
Franco-Singaporean Joint Research Lab
Our research studies interactive media systems and interactive intelligent systems: systems that sense, represent, stream, understand, and adapt rich media while staying responsive to people and their contexts. Across multimedia systems, computer vision, interaction, and human-AI collaboration, we work on the full path from efficient media representation and delivery to perception, decision-making, and user-facing interaction.
Our recent work on 3D Gaussian Splatting studies how high-fidelity, dynamic 3D scenes can be represented compactly and streamed interactively over changing networks. We attack the problem across the stack: designing layered and structure-aware 3DGS representations, allocating bits across frames and attributes, and building adaptive streaming systems that balance visual quality, bandwidth, latency, and client capability.
Yuan-Chun Sun, Yuang Shi*, Chen-Tse Lee, Mufeng Zhu, Wei Tsang Ooi, Yao Liu, Chun-Ying Huang, and Cheng-Hsin Hsu, In Proceedings of the 16th ACM Multimedia Systems Conference (MMSYS'25), Stellenbosch, South Africa, 31 March - 4 April 2025, 136-147 (Best Paper Award).
Yuang Shi*, Geraldine Morin, Simone Gasparini, and Wei Tsang Ooi, In Proceedings of the 2025 International Conference on 3D Vision (3DV'25), Singapore, 25-28 March 2025.
Yuang Shi*, Simone Gasparini, Geraldine Morin, Chenggang Yang*, and Wei Tsang Ooi, In Proceedings of the 17th International Workshop on IMmersive Mixed and Virtual Environment Systems (MMVE'25), Stellenbosch, South Africa, 31 March - 4 April 2025, 51-57.
Yuan-Chun Sun, Yuang Shi*, Wei Tsang Ooi, Chun-Ying Huang, and Cheng-Hsin Hsu, In Proceedings of the 2024 SIGCOMM Workshop on Emerging Multimedia Systems (EMS'24), Sydney, Australia, 4-8 August 2024 (Best Paper Award).
Our recent work on 2D/3D video studies Gaussian splats as media representations for video coding and adaptive delivery. We use 2D Gaussians to represent ordinary image and video frames compactly, then organize these representations progressively so clients can trade quality, resolution, bitrate, and decoding cost under changing delivery conditions.
Longan Wang*, Yuang Shi*, and Wei Tsang Ooi, In Proceedings of the 17th ACM Multimedia Systems Conference (MMSys'26), Hong Kong, 1 - 4 April 2026, 156-166.
Longan Wang*, Yuang Shi*, and Wei Tsang Ooi, In Proceedings of the 35th Workshop on Network and Operating System Support for Audio and Video (NOSSDAV'25), Stellenbosch, South Africa, 31 March - 4 April 2025, 15-21.
Our work on 3D point clouds studies how volumetric scenes can be captured, compressed, streamed, and recovered under practical network and rendering constraints. The work spans end-to-end streaming systems, MPEG V-PCC encoded volumetric video, quality assessment datasets and models, compression comparisons, and error concealment for dynamic point-cloud delivery.
I-Chun Huang, Yuang Shi*, Yuan-Chun Sun, Wei Tsang Ooi, Chun-Ying Huang, and Cheng-Hsin Hsu, ACM Transactions on Multimedia Computing, Communications and Applications, 2025, 157:1-157:28.
Yuang Shi*, Bennet Clements, and Wei Tsang Ooi, In Proceedings of the 15th ACM Multimedia Systems Conference (MMSys'24), Bari, Italy, 15-19 April 2024.
Yuang Shi*, Pranav Venkatram*, Yifan Ding, and Wei Tsang Ooi, In Proceedings of the 14th ACM Multimedia Systems Conference (MMSys'23), Vancouver, Canada, 7-10 June 2023, 108-118.
Samuel Rhys Cox*, May Lim, and Wei Tsang Ooi, In Proceedings of the 14th ACM Multimedia Systems Conference (MMSys'23), Vancouver, Canada, 7-10 June 2023, 357-362 (Dataset Track).
Yuan-Chun Sun, I-Chun Huang, Yuang Shi*, Wei Tsang Ooi, Chun-Ying Huang, and Cheng-Hsin Hsu, In Proceedings of the 14th ACM Multimedia Systems Conference (MMSys'23), Vancouver, Canada, 7-10 June 2023, 376-383 (Dataset Track).
Tzu-Kuang Hung, I-Chun Huang, Samuel Rhys Cox*, Wei Tsang Ooi, and Cheng-Hsin Hsu, In Proceedings of the 30th ACM International Conference on Multimedia (MM'22), Lisboa, Portugal, 10-14 October 2022, 3134-3142.
Cheng-Hao Wu, Chih-Fan Hsu, Tzu-Kuan Hung, Carsten Griwodz, Wei Tsang Ooi, and Cheng-Hsin Hsu, IEEE Transactions on Multimedia, 2022, 3073-3088.
Cheng-Hao Wu, Xiner Li, Rahul Rajesh*, Wei Tsang Ooi, and Cheng-Hsin Hsu, In Proceedings of the 31st Workshop on Network and Operating System Support for Audio and Video (NOSSDAV'21), Istanbul, Turkey, 28 September - 1 October 2021, 98-105.
Our work on event-based vision studies how event cameras can support perception in dynamic scenes where conventional frame cameras struggle with motion, lighting, latency, or bandwidth. We build models and benchmarks that connect event streams with object detection, semantic scene understanding, vision-language reasoning, and aerial and driving perception.
Dongyue Lu*, Rong Li, Ao Liang*, Lingdong Kong*, Wei Yin, Lai Xing Ng, Benoit Cottereau, Camille Simon Chance, and Wei Tsang Ooi, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'26), Denver, Colorado, 3 - 7 June 2026.
Lingdong Kong*, Dongyue Lu*, Alan Liang*, Rong Li, Yuhao Dong, Tianshuai Hu, Lai Xing Ng, Wei Tsang Ooi, and Benoit Cottereau, In Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS'25), San Diego, CA, 30 November - 5 December 2025 (Spotlight).
Dongyue Lu*, Lingdong Kong*, Gim Hee Lee, Camille Simon Chane, and Wei Tsang Ooi, In Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS'25), San Diego, CA, 30 November - 5 December 2025.
Lingdong Kong*, Dongyue Lu, Xiang Xu, Lai Xing Ng, Wei Tsang Ooi, and Benoit Cottereau, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'25), Nashville, TN, 11 - 15 June 2025.
Lingdong Kong*, Youquan Liu, Lai Xing Ng, Benoit R Cottereau, and Wei Tsang Ooi, In Proceedings of the 2024 Conference on Computer Vision and Pattern Recognition (CVPR'24), Seattle, WA, 17-21 June 2024 (Poster Highlight).
Our work on robust 3D/4D scene understanding studies perception and world modeling for autonomous systems operating in real environments. We focus on models, datasets, and evaluations that handle viewpoint changes, corruptions, multimodal 3D data, LiDAR sequences, and dynamic world generation.
Dongyue Lu*, Ao Liang*, Tianxin Huang, Xiao Fu, Yuyang Zhao, Baorui Ma, Liang Pan, Wei Yin, Lingdong Kong, Wei Tsang Ooi, and Ziwei Liu, Computer Graphics Forum, 25 April 2026 (EuroGraphics 2026).
Ao Liang*, Lingdong Kong*, Tianyi Yan, Hongsi Liu, Yu Yang, Ziqi Huang, Wei Yin, Jialong Zuo, Yixuan Hu, Dekai Zhu, Dongyue Lu, Yongquan Liu, Guangfeng Jiang, Linfeng Li, Xingtai Li, Long Zhuo, Lai Xing Ng, Benoit Cottereau, Changxin Gao, Liang Pan, Wei Tsang Ooi, and Ziwei Liu, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'26), Denver, Colorado, 3 - 7 June 2026 (Oral).
Alan Liang*, Youquan Liu, Yu Yang, Dongyue Lu, Linfeng Li, Lingdong Kong, Huaici Zhao, and Wei Tsang Ooi, In Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI'26), Singapore, 20 - 27 January 2026, 184-6-18414.
Alan Liang*, Lingdong Kong*, Dongyue Lu*, Youquan Liu, Jian Fang, Huaici Zhao, and Wei Tsang Ooi, In Proceedings of the International Conference on Computer Vision (ICCV'25), Honolulu, HI, 19 - 23 October 2025.
Lingdong Kong*, Shaoyuan Xie, Hanjiang Hu, Lai Xing Ng, Benoit R Cottereau, and Wei Tsang Ooi, In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS'23), New Orleans, LA, 12-14 December 2023 (Datasets and Benchmarks Track).
Lingdong Kong*, Xiang Xu, Jiawei Ren, Wenwei Zhang, Liang Pan, Kai Chen, Wei Tsang Ooi, and Ziwei Liu, IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5), 2025, 3748-3765.
Our work in assistive and wearable interaction studies how emerging platforms can help people perceive, navigate, learn, and work more effectively in situated tasks. We design and evaluate systems around drones, augmented reality, smart glasses, and LLM-powered assistants, with an emphasis on accessibility, safety-critical work, and everyday mobile tasks.
Yize Wei, Ibnu Taimiyyah bin Adam, Hanjun Wu, Moritz Messeschmidt, Wei Tsang Ooi, Christophe Jouffrais, and Suranga Nanayakkara, In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'26), Barcelona, Spain, 13 - 17 April 2026, 231:1-231:18.
Yize Wei, Nathan Rocher, Chitralekha Gupta, Wei Tsang Ooi, Christophe Jouffrais, and Suranga Nanayakkara, In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'25), Yokohama, Japan, 26 April - 1 May 2025.
Peisen Xu, Jeremy Garcia, Wei Tsang Ooi, and Christophe Jouffrais, In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'25), Yokohama, Japan, 26 April - 1 May 2025 (Honorable Mention).
Yize Wei, Maelle Dubucq, Malsha de Zoysa, Christophe Jouffrais, Suranga Nanayakkara, and Wei Tsang Ooi, In Proceedings of the 26th International ACM SIGACCESS Conference on Computers and Accessibility (ASSET'24), St. John's NL, Canada, 27-30 October 2024, 115:1-115:7, Short Paper.
Chen Zhou, Zihan Yan, Ashwin Ram, Yue Gu, Yan Xiang, Can Liu, Yun Huang, Wei Tsang Ooi, and Shendong Zhao, In Proceedings of the ACM Conference on Designing Interactive Systems (DIS'24), Copenhagen, Denmark, 1-5 July 2024.
Our work on chatbots and conversational agents studies how conversational systems should communicate, remember, disclose context, and support users in sensitive or creative settings. We examine language formality, privacy expectations across sessions, motivational message generation, deception in care robots, and conversational design for LLM-driven game characters.
Samuel Rhys Cox*, Grace Cheong, and Wei Tsang Ooi, In Proceedings of the 11th International Conference on Human-Agent Interaction (HAI'23), Gothenburg, Sweden, 4-7 December 2023, Short Paper.
Samuel Rhys Cox*, Ashraf Abdul, and Wei Tsang Ooi, In Proceedings of the 11th International Conference on Human-Agent Interaction (HAI'23), Gothenburg, Sweden, 4-7 December 2023, Short Paper.
Samuel Rhys Cox*, Yi-Chieh Lee, and Wei Tsang Ooi, In Proceedings of the 11th International Conference on Human-Agent Interaction (HAI'23), Gothenburg, Sweden, 4-7 December 2023.
Samuel Rhys Cox* and Wei Tsang Ooi, In Proceedings of the 7th International Workshop on Chatbot Research (Conversations), Oslo, Norway, 22-23 November 2023.
Samuel Rhys Cox* and Wei Tsang Ooi, In Proceedings of the ACM 4th Conference on Conversational User Interfaces (CUI'22), Glasgow, UK, 26-28 July 2022, 1-13.
Our recent work on Learning-to-Defer studies how AI systems can decide when to answer locally, when to consult a stronger model or human expert, and how many experts to ask. The work treats deferral as a cost-sensitive allocation problem: small or on-device models handle easy cases, while difficult, high-stakes, or resource-sensitive queries are routed to external experts or larger models.
Yannis Montreuil*, Axel Carlier, Lai Xing Ng, and Wei Tsang Ooi, In Proceedings of the 14th Annual Conference on Learning Representation (ICLR'26), Rio de Janeiro, Brazil, 23 - 27 April 2026.
Yannis Montreuil*, Hoang Dang, Maxime Meyer, Lai Xing Ng, Axel Carlier, and Wei Tsang Ooi, In Proceedings of the 29th Annual Conference on Artificial Intelligence and Statistics (AISTATS'26), Tangier, Morocco, 2 - 5 May 2026.
Yannis Montreuil*, Letian Yu, Axel Carlier, Lai Xing Ng, and Wei Tsang Ooi, In Proceedings of the 29th Annual Conference on Artificial Intelligence and Statistics (AISTATS'26), Tangier, Morocco, 2 - 5 May 2026.
Yannis Montreuil*, Shu Heng Yeo, Axel Carlier, Lai Xing Ng, and Wei Tsang Ooi, In Proceedings of the 29th Annual Conference on Artificial Intelligence and Statistics (AISTATS'26), Tangier, Morocco, 2 - 5 May 2026.
Yannis Montreuil*, Axel Carlier, Lai Xing Ng, and Wei Tsang Ooi, In Proceedings of the 42nd International Conference on Machine Learning (ICML'25), Vancouver, Canada, 13 - 19 July 2025.
Yannis Montreuil*, Shu Heng Yeo, Axel Carlier, Lai Xing Ng, and Wei Tsang Ooi, In Proceedings of the 42nd International Conference on Machine Learning (ICML'25), Vancouver, Canada, 13 - 19 July 2025.