1 code implementation • 2 Dec 2023 • Michael A. Alcorn, Noah Schwartz
Our key insight is that, by deliberately collecting separate "background" and "object" datasets (i. e., "factoring the real world"), we can intelligently combine them to produce a combinatorially large and diverse training set.
1 code implementation • 21 Jan 2023 • Michael A. Alcorn
Accurately modeling complex, multimodal distributions is necessary for optimal decision-making, but doing so for rotations in three-dimensions, i. e., the SO(3) group, is challenging due to the curvature of the rotation manifold.
1 code implementation • ICML Workshop INNF 2021 • Michael A. Alcorn, Anh Nguyen
In this paper, we propose an alternative approach for encoding feature identities, where each feature's identity is included alongside its value in the input.
1 code implementation • NeurIPS 2021 • Michael A. Alcorn, Anh Nguyen
In many multi-agent spatiotemporal systems, agents operate under the influence of shared, unobserved variables (e. g., the play a team is executing in a game of basketball).
Ranked #1 on Trajectory Modeling on NBA SportVU
1 code implementation • NeurIPS 2021 • Michael A. Alcorn, Anh Nguyen
Multi-agent spatiotemporal modeling is a challenging task from both an algorithmic design and computational complexity perspective.
no code implementations • 10 Oct 2019 • Qi Li, Long Mai, Michael A. Alcorn, Anh Nguyen
Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities.
1 code implementation • CVPR 2019 • Michael A. Alcorn, Qi Li, Zhitao Gong, Chengfei Wang, Long Mai, Wei-Shinn Ku, Anh Nguyen
Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects in ImageNet.