(* indicates equal contribution)
Zero-shot linear combinations of grounded social interactions with Linear Social MDPs.
Ravi Tejwani*, Yen-Ling Kuo*, Tianmin Shu, Bennett Stankovits, Dan Gutfreund, Joshua B. Tenenbaum, Boris Katz, and Andrei Barbu.
37th AAAI Conference on Artificial Intelligence (AAAI), 2023.
Incorporating Rich Social Interactions Into MDPs.
Ravi Tejwani*, Yen-Ling Kuo*, Tianmin Shu, Bennett Stankovits, Dan Gutfreund, Joshua B. Tenenbaum, Boris Katz, and Andrei Barbu.
IEEE International Conference on Robotics and Automation (ICRA), 2022.
(Excellent Paper Award at IROS Cognitive and Social Aspects of Human Multi-Robot Interaction Workshop, 2022)
A Unified Psychological Space for Human Perception of Physical and Social Events
Tianmin Shu, Yujia Peng, Song-Chun Zhu, and Hongjing Lu.
Cognitive Psychology, 128: 101398, 2021.
Paper   Code (Stimuli Generation)   Code (Model)   Data
AGENT: A Benchmark for Core Psychological Reasoning
Tianmin Shu, Abhishek Bhandwaldar, Chuang Gan, Kevin A. Smith, Shari Liu, Dan Gutfreund, Elizabeth Spelke, Joshua B. Tenenbaum, and Tomer D. Ullman.
38th International Conference on Machine Learning (ICML), 2021.
Paper   Supp   Project   Code (Data Generation)   ScienceNews for Students   VentureBeat   Blog
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Joshua B. Tenenbaum, Sanja Fidler, and Antonio Torralba.
9th International Conference on Learning Representations (ICLR), 2021. (Spotlight presentation)
(Best Paper Award at NeurIPS Cooperative AI Workshop, 2020)
PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception
Aviv Netanyahu*, Tianmin Shu*, Boris Katz, Andrei Barbu, and Joshua B. Tenenbaum.
35th AAAI Conference on Artificial Intelligence (AAAI), 2021.
(Best Paper Award at NeurIPS Shared Visual Representations in Human and Machine Intelligence Workshop, 2020)
Paper   Supp   Project   Code (Data Generation)
Exploring Biological Motion Perception in Two-stream Convolutional Neural Networks
Yujia Peng, Hannah Lee, Tianmin Shu, and Hongjing Lu
Vision Research, 178: 28-40, 2021.
Learning to Infer Human Attention in Daily Activities
Zhixiong Nan, Tianmin Shu, Ran Gong, Shu Wang, Ping Wei, Song-Chun Zhu, and Nanning Zheng.
Pattern Recognition, 103: 107314, 2020.
VRKitchen: an Interactive 3D Environment for Learning Real Life Cooking Tasks
Xiaofeng Gao, Ran Gong, Tianmin Shu, Xu Xie, Shu Wang, and Song-Chun Zhu.
ICML workshop on Reinforcement Learning for Real Life, 2019.
Paper   Project   Code   Tech Xplore   Bibtex
Interactive agent modeling by learning to probe
Tianmin Shu, Caiming Xiong, Ying Nian Wu, and Song-Chun Zhu.
NeurIPS Deep Reinforcement Learning Workshop, 2018.
Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning
Tianmin Shu, Caiming Xiong, and Richard Socher.
6th International Conference on Learning Representations (ICLR), 2018.
Paper   ScienceNews   Bibtex
Perception of Human Interaction Based on Motion Trajectories: from Aerial Videos to Decontextualized Animations
Tianmin Shu*, Yujia Peng*, Lifeng Fan, Hongjing Lu, and Song-Chun Zhu.
Topics in Cognitive Science, 10(1): 225 - 241, 2018.
Inferring Human Interaction from Motion Trajectories in Aerial Videos
Tianmin Shu*, Yujia Peng*, Lifeng Fan, Hongjing Lu, and Song-Chun Zhu.
39th Annual Meeting of the Cognitive Science Society (CogSci), 2017.
(Computational Modeling Prize)
Learning Social Affordance Grammar from Videos:
Transferring Human Interactions to Human-Robot Interactions
Tianmin Shu, Xiaofeng Gao, Michael S. Ryoo, and Song-Chun Zhu.
IEEE International Conference on Robotics and Automation (ICRA), 2017.
Paper   Project   Slides   New Scientist   Bibtex
Joint Inference of Groups, Events and Human Roles in Aerial Videos
Tianmin Shu, Dan Xie, Brandon Rothrock, Sinisa Todorovic, and Song-Chun Zhu.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
(Oral presentation, acceptance rate: 71/2123 = 3.3%)