A Sparsity Inducing Nuclear-Norm Estimator (SpINNEr) for Matrix-Variate Regression in Brain Connectivity Analysis

1 code implementation • 30 Jan 2020 • Damian Brzyski, Xixi Hu, Joaquin Goni, Beau Ances, Timothy W. Randolph, Jaroslaw Harezlak

We present an alternative approach - regularized matrix regression - where the matrix of regression coefficients is defined as a solution to the specific optimization problem.

regression

Structure from Silence: Learning Scene Structure from Ambient Sound

1 code implementation • 10 Nov 2021 • Ziyang Chen, Xixi Hu, Andrew Owens

From whirling ceiling fans to ticking clocks, the sounds that we hear subtly vary as we move through a scene.

Mix and Localize: Localizing Sound Sources in Mixtures

no code implementations • CVPR 2022 • Xixi Hu, Ziyang Chen, Andrew Owens

This task requires a model to both group a sound mixture into individual sources, and to associate them with a visual signal.

AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies

1 code implementation • 6 Feb 2024 • Xixi Hu, Bo Liu, Xingchao Liu, Qiang Liu

To address this challenge, we propose AdaFlow, an imitation learning framework based on flow-based generative modeling.

Imitation Learning