Publications

Kernel Multimodal Continuous Attention

NeurIPS 2022
Alexander Moreno, Zhenke Wu, Supriya Nagesh, Walter Dempsey, James M. Rehg

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

NeurIPS 2022
Stefan Stojanov, Anh Thai, Zixuan Huang, James M Rehg

PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation

NeurIPS 2022
Maxwell A. Xu, Alexander Moreno, Supiya Nagesh, V. Burak Aydemir, David W. Wetter, Santosh Kumar, James M. Rehg

Discovering Novel Predictors of Minimally Verbal Outcomes in Autism through Computational Modeling

INSAR 2022 Oral + Press Conference (< 1% acceptance rate)
Maxwell Xu, James M. Rehg, Agata Rozga, Jena McDaniel, Paul Yoder, Linda R. Watson, Nancy Brady

Egocentric Activity Recognition and Localization on a 3D Map

ECCV 2022
Miao Liu, Lingni Ma, Kiran Somasundaram, Yin Li, Kristen Grauman, James M. Rehg, Chao Li

Generative Adversarial Network for Future Hand Segmentation from Egocentric Video

ECCV 2022
Wenqi Jia, Miao Liu, James M. Rehg

Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues

ECCV 2022
Zixuan Huang, Stefan Stojanov, Anh Thai, Varun Jampani, James M. Rehg

Ego4D: Around the World in 3,000 Hours of Egocentric Video

CVPR 2022 (oral)
Kristen Grauman et al., (including lab members Miao Liu, Fiona Ryan, Wenqi Jia, Audrey Southerland, and James M. Rehg)

mRisk: Continuous Risk Estimation for Smoking Lapse from Noisy Sensor Data with Incomplete and Positive-Only Labels

IMWUT 2022
Md Azim Ullah, Soujanya Chatterjee, Christopher P Fagundes, Cho Lam, Inbal Nahum-Shani, James M. Rehg, David W Wetter, Santosh Kumar

The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction

3DV 2022
Anh Thai, Stefan Stojanov, Zixuan Huang, James M. Rehg

The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction

3DV 2022
Anh Thai, Stefan Stojanov, Zixuan Huang, James M. Rehg

4D Human Body Capture from Egocentric Video via 3D Scene Grounding

3DV 2021
Miao Liu, Dexin Yang, Yan Zhang, Zhaopeng Cui, James M. Rehg, Siyu Tang

No RL, No Simulation: Learning to Navigate without Navigating

NeurIPS 2021
Meera Hahn, Devendra Singh Chaplot, Shubham Tulsiani, Mustafa Mukadam, James M. Rehg, Abhinav Gupta

Transformers for prompt-level EMA non-response prediction

arXiv preprint
Supriya Nagesh, Alexander Moreno, Stephanie M. Carpenter, Jamie Yap, Soujanya Chatterjee, Steven Lloyd Lizotte, Neng Wan, Santosh Kumar, Cho Lam, David W. Wetter, Inbal Nahum-Shani, James M. Rehg

Efficient Learning and Decoding of the Continuous-Time Hidden Markov Model for Disease Progression Modeling

arXiv preprint
Yu-Ying Liu, Alexander Moreno, Maxwell A. Xu, Shuang Li, Jena C. McDaniel, Nancy C. Brady, Agata Rozga, Fuxin Li, Le Song, James M. Rehg

Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking

CVPR 2021
Chanho Kim, Li Fuxin, Mazen Alotaibi, James M. Rehg

Orthogonal Over-Parameterized Training

CVPR 2021
Weiyang Liu, Rongmei Lin, Zhen Liu, James M. Rehg, Liam Paull, Li Xiong, Le Song, Adrian Weller

Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias

CVPR 2021
Stefan Stojanov, Anh Thai, James M. Rehg

3D Reconstruction of Novel Object Shapes from Single Images

3DV 2021
Anh Thai, Stefan Stojanov, Vijay Upadhya, James M. Rehg

Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning

ICRA 2021
Keuntaek Lee, Bogdan Vlahov, Jason Gibson, James M. Rehg, Evangelos A Theodorou