Search Results for author: Li Ma

Found 22 papers, 9 papers with code

Deblur-NeRF: Neural Radiance Fields from Blurry Images

no code implementations29 Nov 2021 Li Ma, Xiaoyu Li, Jing Liao, Qi Zhang, Xuan Wang, Jue Wang, Pedro V. Sander

We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes.

3D Scene Reconstruction Novel View Synthesis

Microbiome subcommunity learning with logistic-tree normal latent Dirichlet allocation

1 code implementation11 Sep 2021 Patrick LeBlanc, Li Ma

We compare the LDA and the new model and show that in the presence of large cross-sample heterogeneity, LDA can produce inference which is sensitive to the specification of the number of subcommunities.

Bayesian Inference

Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain

1 code implementation ICCV 2021 Guangyao Chen, Peixi Peng, Li Ma, Jia Li, Lin Du, Yonghong Tian

This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image.

Adversarial Attack Data Augmentation +2

SciConceptMiner: A system for large-scale scientific concept discovery

no code implementations ACL 2021 Zhihong Shen, Chieh-Han Wu, Li Ma, Chien-Pang Chen, Kuansan Wang

In this paper, we introduce a self-supervised end-to-end system, SciConceptMiner, for the automatic capture of emerging scientific concepts from both independent knowledge sources (semi-structured data) and academic publications (unstructured documents).

Distillation based Multi-task Learning: A Candidate Generation Model for Improving Reading Duration

no code implementations14 Feb 2021 Zhong Zhao, Yanmei Fu, Hanming Liang, Li Ma, Guangyao Zhao, Hongwei Jiang

One solution to this problem is to model the click and the reading duration simultaneously under the multi-task learning (MTL) framework.

Multi-Task Learning Recommendation Systems

Tree boosting for learning probability measures

no code implementations26 Jan 2021 Naoki Awaya, Li Ma

This then gives rise to a simple boosting algorithm based on forward-stagewise (FS) fitting of an additive ensemble of measures, which sequentially minimizes the entropy loss.

Stability property and Dirichlet problem for translating solitons

no code implementations24 Dec 2020 Li Ma, Vicente Miquel

In this paper, we prove that the infimum of the mean curvature is zero for a translating solitons of hypersurface in $\re^{n+k}$.

Differential Geometry Analysis of PDEs translating solitons, stability, non-splitting, Dirichlet problem

Yamabe metrics, Fine solutions to the Yamabe flow, and local L1-stability

no code implementations24 Dec 2020 Li Ma

In this paper, we study the existence of complete Yamabe metric with zero scalar curvature on an n-dimensional complete Riemannian manifold $(M, g_0)$, $n\geq 3$.

Differential Geometry Analysis of PDEs 53C44, 53C20, 35Jxx, 35K50, 58J20

Two solutions to Kazdan-Warner's problem on surfaces

no code implementations24 Dec 2020 Li Ma

In this paper, we study the sign-changing Kazdan-Warner's problem on two dimensional closed Riemannian manifold with negative Euler number $\chi(M)<0$.

Differential Geometry Analysis of PDEs 53C20, 35J60, 58G99

Dirichlet-tree multinomial mixtures for clustering microbiome compositions

1 code implementation2 Aug 2020 Jialiang Mao, Li Ma

A common routine in microbiome research is to identify reproducible patterns in the population through unsupervised clustering of samples.

Methodology Applications

Privacy-preserving collaborative machine learning on genomic data using TensorFlow

1 code implementation11 Feb 2020 Cheng Hong, Zhicong Huang, Wen-jie Lu, Hunter Qu, Li Ma, Morten Dahl, Jason Mancuso

Machine learning (ML) methods have been widely used in genomic studies.

Cryptography and Security

CARP: Compression through Adaptive Recursive Partitioning for Multi-dimensional Images

1 code implementation CVPR 2020 Rongjie Liu, Meng Li, Li Ma

Fast and effective image compression for multi-dimensional images has become increasingly important for efficient storage and transfer of massive amounts of high-resolution images and videos.

Image Compression

POI Semantic Model with a Deep Convolutional Structure

no code implementations18 Mar 2019 Ji Zhao, Meiyu Yu, Huan Chen, Boning Li, Lingyu Zhang, Qi Song, Li Ma, Hua Chai, Jieping Ye

An accurate similarity calculation is challenging since the mismatch between a query and a retrieval text may exist in the case of a mistyped query or an alias inquiry.

Multiscale Fisher's Independence Test for Multivariate Dependence

1 code implementation18 Jun 2018 Shai Gorsky, Li Ma

Identifying dependency in multivariate data is a common inference task that arises in numerous applications.

Bayesian graphical compositional regression for microbiome data

2 code implementations13 Dec 2017 Jialiang Mao, Yuhan Chen, Li Ma

An important task in microbiome studies is to test the existence of and give characterization to differences in the microbiome composition across groups of samples.

Methodology Applications Computation

Learning Asymmetric and Local Features in Multi-Dimensional Data through Wavelets with Recursive Partitioning

1 code implementation2 Nov 2017 Meng Li, Li Ma

Effective learning of asymmetric and local features in images and other data observed on multi-dimensional grids is a challenging objective critical for a wide range of image processing applications involving biomedical and natural images.

Bayesian Inference Image Reconstruction

Mixture modeling on related samples by $ψ$-stick breaking and kernel perturbation

no code implementations17 Apr 2017 Jacopo Soriano, Li Ma

We introduce two techniques for incorporating these features in modeling related data samples using kernel mixtures.

Bayesian Inference

Recursive partitioning and multi-scale modeling on conditional densities

1 code implementation14 Nov 2016 Li Ma

We introduce a nonparametric prior on the conditional distribution of a (univariate or multivariate) response given a set of predictors.

Methodology Statistics Theory Computation Statistics Theory

Efficient functional ANOVA through wavelet-domain Markov groves

no code implementations12 Feb 2016 Li Ma, Jacopo Soriano

We introduce a wavelet-domain functional analysis of variance (fANOVA) method based on a Bayesian hierarchical model.

Cannot find the paper you are looking for? You can Submit a new open access paper.