activity
20162023
most citedTopology-Preserving Deep Image Segmentation

85 citations · 227 across the 14 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

cs.LG2021

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

Yu-Ying Liu, Alexander Moreno, Maxwell A. Xu +7

The Continuous-Time Hidden Markov Model (CT-HMM) is an attractive approach to modeling disease progression due to its ability to describe noisy observations arriving irregularly in…

cs.CV2021

Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation

Jay Patravali, Gaurav Mittal, Ye Yu +2

We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D…

cs.CV2021

Space Time Recurrent Memory Network

Hung Nguyen, Chanho Kim, Fuxin Li

Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the featur…

cs.CV2021★ 14 cited

Topology-Aware Segmentation Using Discrete Morse Theory

Xiaoling Hu, Yusu Wang, Li Fuxin +2

In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern. Topological correctness, such as vessel conne…

cs.LG2021

Generative Particle Variational Inference via Estimation of Functional Gradients

Neale Ratzlaff, Qinxun Bai, Li Fuxin +1

Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference…

cs.AI2021★ 68 cited

Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning

Matthew L. Olson, Roli Khanna, Lawrence Neal +2

Counterfactual explanations, which deal with "why not?" scenarios, can provide insightful explanations to an AI agent's behavior. In this work, we focus on generating counterfactua…