科学研究
MEOW LAB（Modeling Egocentric Omniscient Worlds）
PI：Miao LIU
研究方向：实验室聚焦于第一视角视觉与多模态生成式人工智能
课题组简介
我们的实验室聚焦于第一视角视觉（Egocentric Vision）与多模态生成式人工智能(Multimodal Generative AI)。我们将致力于：
Designing AI that sees through your eyes, learns your skills, and understands your intentions. (构建能“看你所见、学你所会、懂你所想”的下一代人本智能系统。)
我目前在Meta GenAI担任高级研究科学家，博士毕业于佐治亚理工学院，入选国家高层次青年人才计划（海外），致力于第一视角视觉和多模态生成式AI的理论研究。以主要作者身份在CVPR、ECCV、ACL、TPAMI等顶级会议/期刊发表20余篇论文，研究成果共被引用9000余次，其中8篇被选为口头报告。CVPR 2022、ECCV2024论文入围最佳论文候选，BMVC2022论文获最佳学生论文奖。
作为主要作者，我参与构建了多个广受关注的第一视角视频数据集，包括Ego4D、EgoExo4D、EGTEA Gaze+与Behavior Vision Suite等，相关成果已广泛应用于学术界与工业界。在第一视角行为理解方面，我提出了多项用于动作识别与预测的算法，将应用于Meta Reality Labs的下一代智能眼镜产品中。此外，在Meta GenAI工作期间，我深度参与了生成式多模态大模型EMU、Llama3与Llama4（仅多模态部分）的训练与评估。
代表性论文
Zeyi Huang, Yuyang Ji, Xiaofang Wang, Nikhil Mehta, Tong Xiao, Donghyun Lee, Sigmund Vanvalkenburgh, Shengxin Zha, Bolin Lai, Licheng Yu, Ning Zhang, Yong Jae Lee*, Miao Liu* (* Co-corresponding author)
Conference on Computer Vision and Pattern Recognition (CVPR), 2025
2. LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning
Bolin Lai, Xiaoliang Dai, Lawrence Chen, Guan Pang, James M. Rehg, Miao Liu
European Conference on Computer Vision (ECCV), 2024 Oral, Best Paper Award Candidate, 15/8585})
3. Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation
Bolin Lai, Fiona Ryan, Wenqi Jia, Miao Liu*, James M. Rehg* (* Co-corresponding author)
European Conference on Computer Vision (ECCV), 2024
4. In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation
Bolin Lai, Miao Liu*, Fiona Ryan, James M. Rehg (* Co-corresponding author)
British Machine Vision Conference (BMVC), 2022 (Spotlight, Best Student Paper, 2/770)
5. Egocentric Activity Recognition and Localization on a 3D Map
Miao Liu, Lingni Ma, Kiran Somasundaram, Yin Li, Kristen Grauman, James M. Rehg, Chao Li
European Conference on Computer Vision (ECCV), 2022 (Spotlight presentation at the 2nd International Ego4D Workshop@ECCV 2022)
6. Generative Adversarial Network for Future Hand Segmentation from Egocentric Video
Wenqi Jia*, Miao Liu*, James M. Rehg (* Co-first author)
European Conference on Computer Vision (ECCV), 2022
7. Ego4D: Around the World in 3,000 Hours of Egocentric Video
Kristen Grauman, Andrew Westbury, Eugene Byrne*, Zachary Chavis*, Antonino Furnari*, Rohit Girdhar*, Jackson Hamburger*, Hao Jiang*, Miao Liu*, Xingyu Liu*, Miguel Martin*, Tushar Nagarajan*, ... , Jitendra Malik (*:Co-first author (student))
Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral, Best Paper Final list, 33/8161)
8. Attention Distillation for Learning Video Representations
Miao Liu, Xin Chen, Yun Zhang, Yin Li, James M. Rehg
British Machine Vision Conference (BMVC), 2020 (Oral, top 5.0%})
Miao Liu, Siyu Tang, Yin Li, James M. Rehg
European Conference on Computer Vision (ECCV), 2020 (Oral, top 2.0%)