Search Results for author: Jian Ma

Found 51 papers, 26 papers with code

Change Point Detection with Copula Entropy based Two-Sample Test

2 code implementations3 Feb 2024 Jian Ma

In this paper we propose a nonparametric multivariate method for multiple change point detection with the copula entropy-based two-sample test.

Change Point Detection Time Series

Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting

no code implementations19 Jan 2024 Hao Ai, Zidong Cao, Haonan Lu, Chen Chen, Jian Ma, Pengyuan Zhou, Tae-Kyun Kim, Pan Hui, Lin Wang

To this end, we propose a transformer-based 360 image outpainting framework called Dream360, which can generate diverse, high-fidelity, and high-resolution panoramas from user-selected viewports, considering the spherical properties of 360 images.

Image Outpainting

Root Cause Analysis on Energy Efficiency with Transfer Entropy Flow

no code implementations11 Jan 2024 Jian Ma

A method, called TE flow, is proposed in that a TE flow from physical measurements of each subsystem to the energy efficiency indicator along timeline is considered as causal strength for diagnosing root cause of anomaly states of energy efficiency of a system.

End-to-end Learnable Clustering for Intent Learning in Recommendation

1 code implementation11 Jan 2024 Yue Liu, Shihao Zhu, Jun Xia, Yingwei Ma, Jian Ma, Wenliang Zhong, Xinwang Liu, Guannan Zhang, Kejun Zhang

Concretely, we encode users' behavior sequences and initialize the cluster centers (latent intents) as learnable neurons.

Clustering Contrastive Learning +2

AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition

1 code implementation15 Dec 2023 Yuhang Ming, Jian Ma, Xingrui Yang, Weichen Dai, Yong Peng, Wanzeng Kong

We evaluate our AEGIS-Net on the ScanNetPR dataset and compare its performance with a pre-deep-learning feature-based method and five state-of-the-art deep-learning-based methods.

Semantic Segmentation

Layered 3D Human Generation via Semantic-Aware Diffusion Model

no code implementations10 Dec 2023 Yi Wang, Jian Ma, Ruizhi Shao, Qiao Feng, Yu-Kun Lai, Yebin Liu, Kun Li

To keep the generated clothing consistent with the target text, we propose a semantic-confidence strategy for clothing that can eliminate the non-clothing content generated by the model.

PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendation

no code implementations4 Dec 2023 Chunjing Gan, Bo Huang, Binbin Hu, Jian Ma, Ziqi Liu, Zhiqiang Zhang, Jun Zhou, Guannan Zhang, Wenliang Zhong

To help merchants/customers to provide/access a variety of services through miniapps, online service platforms have occupied a critical position in the effective content delivery, in which how to recommend items in the new domain launched by the service provider for customers has become more urgent.

Recommendation Systems

Photometric Redshifts with Copula Entropy

1 code implementation25 Oct 2023 Jian Ma

In this paper we propose to apply copula entropy (CE) to photometric redshifts.

Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning

1 code implementation21 Jul 2023 Jian Ma, Junhao Liang, Chen Chen, Haonan Lu

In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain.

Diffusion Personalization Tuning Free Text-to-Image Generation

Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models

1 code implementation23 May 2023 Ruichen Wang, Zekang Chen, Chen Chen, Jian Ma, Haonan Lu, Xiaodong Lin

Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image.

Attribute Image Generation

Edit Everything: A Text-Guided Generative System for Images Editing

1 code implementation27 Apr 2023 Defeng Xie, Ruichen Wang, Jian Ma, Chen Chen, Haonan Lu, Dong Yang, Fobo Shi, Xiaodong Lin

We introduce a new generative system called Edit Everything, which can take image and text inputs and produce image outputs.

UNADON: Transformer-based model to predict genome-wide chromosome spatial position

1 code implementation26 Apr 2023 Muyu Yang, Jian Ma

The spatial positioning of chromosomes relative to functional nuclear bodies is intertwined with genome functions such as transcription.

Position

System Identification with Copula Entropy

1 code implementation23 Apr 2023 Jian Ma

In this paper we propose a method for identifying differential equation of dynamical systems with CE.

Variable Selection

GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation

3 code implementations31 Mar 2023 Jian Ma, Mingjun Zhao, Chen Chen, Ruichen Wang, Di Niu, Haonan Lu, Xiaodong Lin

Recent breakthroughs in the field of language-guided image generation have yielded impressive achievements, enabling the creation of high-quality and diverse images based on user instructions. Although the synthesis performance is fascinating, one significant limitation of current image generation models is their insufficient ability to generate text coherently within images, particularly for complex glyph structures like Chinese characters.

Optical Character Recognition (OCR) Text-to-Image Generation

Identifying Time Lag in Dynamical Systems with Copula Entropy based Transfer Entropy

1 code implementation15 Jan 2023 Jian Ma

In this paper we propose to use the CE-based estimator of TE to identify time lag in dynamical systems.

EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations

3 code implementations26 Sep 2022 Ahmad Darkhalil, Dandan Shan, Bin Zhu, Jian Ma, Amlan Kar, Richard Higgins, Sanja Fidler, David Fouhey, Dima Damen

VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets.

Object Segmentation +4

Copula Entropy based Variable Selection for Survival Analysis

1 code implementation4 Sep 2022 Jian Ma

Variable selection is an important problem in statistics and machine learning.

Survival Analysis Variable Selection

Evaluating Independence and Conditional Independence Measures

2 code implementations15 May 2022 Jian Ma

For the CI measures, two simulated data with normal distribution and Gumbel copula, and one real data (the Beijing air data) were utilized to test the CI measures in prespecified linear or nonlinear setting and real scenario.

A deep learning pipeline for breast cancer ki-67 proliferation index scoring

no code implementations14 Mar 2022 Khaled Benaggoune, Zeina Al Masry, Jian Ma, Christine Devalland, L. H Mouss, Noureddine Zerhouni

The extracted nuclei are then divided into overlapped and non-overlapped regions based on eight geometric and statistical features.

Semantic Segmentation

Causal Domain Adaptation with Copula Entropy based Conditional Independence Test

1 code implementation27 Feb 2022 Jian Ma

In this sense, causal DA is transformed as a causal discovery problem that finds invariant representation across domains through the conditional independence between the state variables and observable state of the system given interventions.

Causal Discovery Domain Adaptation

Hand-Object Interaction Reasoning

no code implementations13 Jan 2022 Jian Ma, Dima Damen

This paper proposes an interaction reasoning network for modelling spatio-temporal relationships between hands and objects in video.

Action Recognition Object

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark

1 code implementation5 Nov 2021 Yuhang Li, Mingzhu Shen, Jian Ma, Yan Ren, Mingxin Zhao, Qi Zhang, Ruihao Gong, Fengwei Yu, Junjie Yan

Surprisingly, no existing algorithm wins every challenge in MQBench, and we hope this work could inspire future research directions.

Quantization

Sequential Attention Module for Natural Language Processing

no code implementations7 Sep 2021 Mengyuan Zhou, Jian Ma, Haiqin Yang, Lianxin Jiang, Yang Mo

In this paper, we target at how to further improve the token representations on the language models.

Language Modelling Sentiment Analysis

Sattiy at SemEval-2021 Task 9: An Ensemble Solution for Statement Verification and Evidence Finding with Tables

no code implementations SEMEVAL 2021 Xiaoyi Ruan, Meizhi Jin, Jian Ma, Haiqin Yang, Lianxin Jiang, Yang Mo, Mengyuan Zhou

Question answering from semi-structured tables can be seen as a semantic parsing task and is significant and practical for pushing the boundary of natural language understanding.

Natural Language Understanding Question Answering +1

PALI at SemEval-2021 Task 2: Fine-Tune XLM-RoBERTa for Word in Context Disambiguation

no code implementations SEMEVAL 2021 Shuyi Xie, Jian Ma, Haiqin Yang, Lianxin Jiang, Yang Mo, Jianping Shen

Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not.

Data Augmentation TAG +1

Associations between finger tapping, gait and fall risk with application to fall risk assessment

no code implementations30 Jun 2020 Jian Ma

To address the elderly's issues on dementia and fall risk, we have investigated smart cognitive and fall risk assessment with machine learning methodology based on the data collected from finger tapping test and Timed Up and Go (TUG) test.

copent: Estimating Copula Entropy and Transfer Entropy in R

1 code implementation27 May 2020 Jian Ma

Copula Entropy is a mathematical concept defined by Ma and Sun for multivariate statistical independence measuring and testing, and also proved to be closely related to conditional independence (or transfer entropy).

BIG-bench Machine Learning Causal Discovery +3

Predicting MMSE Score from Finger-Tapping Measurement

no code implementations18 Apr 2020 Jian Ma

Based on measurement of finger tapping movement, the pipeline is first to select finger-tapping attributes with copula entropy and then to predict MMSE score from the selected attributes with predictive models.

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing

no code implementations27 Feb 2020 Ziqi Liu, Dong Wang, Qianyu Yu, Zhiqiang Zhang, Yue Shen, Jian Ma, Wenliang Zhong, Jinjie Gu, Jun Zhou, Shuang Yang, Yuan Qi

In this paper, we present a graph representation learning method atop of transaction networks for merchant incentive optimization in mobile payment marketing.

Graph Representation Learning Marketing

Predicting TUG score from gait characteristics with video analysis and machine learning

no code implementations23 Feb 2020 Jian Ma

As a byproduct, the associations between TUG score and several gait characteristics are discovered, which laid the scientific foundation of the proposed method and make the predictive models such built interpretable to clinical users.

BIG-bench Machine Learning

Hyper-SAGNN: a self-attention based graph neural network for hypergraphs

1 code implementation ICLR 2020 Ruochi Zhang, Yuesong Zou, Jian Ma

Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems.

Graph Representation Learning

Variable Selection with Copula Entropy

1 code implementation28 Oct 2019 Jian Ma

It is believed that CE based variable selection can help to build more explainable models.

Explainable Models Feature Importance +1

Estimating Transfer Entropy via Copula Entropy

3 code implementations10 Oct 2019 Jian Ma

Causal discovery is a fundamental problem in statistics and has wide applications in different fields.

Causal Discovery Causal Inference

Discovering Association with Copula Entropy

1 code implementation29 Jul 2019 Jian Ma

Discovering associations is of central importance in scientific practices.

Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization

no code implementations ICML 2018 Jinghui Chen, Pan Xu, Lingxiao Wang, Jian Ma, Quanquan Gu

We propose a nonconvex estimator for the covariate adjusted precision matrix estimation problem in the high dimensional regime, under sparsity constraints.

Rotation Equivariance and Invariance in Convolutional Neural Networks

2 code implementations31 May 2018 Benjamin Chidester, Minh N. Do, Jian Ma

Performance of neural networks can be significantly improved by encoding known invariance for particular tasks.

Classification General Classification +1

Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization

no code implementations NeurIPS 2017 Pan Xu, Jian Ma, Quanquan Gu

In order to speed up the estimation of the sparse plus low-rank components, we propose a sparsity constrained maximum likelihood estimator based on matrix factorization and an efficient alternating gradient descent algorithm with hard thresholding to solve it.

On the Reconstruction Risk of Convolutional Sparse Dictionary Learning

1 code implementation29 Aug 2017 Shashank Singh, Barnabás Póczos, Jian Ma

Sparse dictionary learning (SDL) has become a popular method for adaptively identifying parsimonious representations of a dataset, a fundamental problem in machine learning and signal processing.

Dictionary Learning Time Series +1

Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimizations

no code implementations NeurIPS 2017 Pan Xu, Jian Ma, Quanquan Gu

In order to speed up the estimation of the sparse plus low-rank components, we propose a sparsity constrained maximum likelihood estimator based on matrix factorization, and an efficient alternating gradient descent algorithm with hard thresholding to solve it.

A new correlation clustering method for cancer mutation analysis

no code implementations25 Jan 2016 Jack P. Hou, Amin Emad, Gregory J. Puleo, Jian Ma, Olgica Milenkovic

To test $C^3$, we performed a detailed analysis on TCGA breast cancer and glioblastoma data and showed that our algorithm outperforms the state-of-the-art CoMEt method in terms of discovering mutually exclusive gene modules and identifying driver genes.

Clustering Community Detection

Dependence Structure Estimation via Copula

1 code implementation28 Apr 2008 Jian Ma, Zengqi Sun

In this paper, a theoretical framework for such estimation based on copula and copula entropy -- the probabilistic theory of representation and measurement of statistical dependence, is proposed.

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