Search Results for author: Fei Xu

Found 31 papers, 2 papers with code

Cross-Attention Based Influence Model for Manual and Nonmanual Sign Language Analysis

no code implementations12 Sep 2024 Lipisha Chaudhary, Fei Xu, Ifeoma Nwogu

Both manual (relating to the use of hands) and non-manual markers (NMM), such as facial expressions or mouthing cues, are important for providing the complete meaning of phrases in American Sign Language (ASL).

Decoder Machine Translation +2

FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering

no code implementations9 Jul 2024 Md Sirajul Islam, Simin Javaherian, Fei Xu, Xu Yuan, Li Chen, Nian-Feng Tzeng

Federated learning (FL) is an emerging distributed machine learning paradigm that enables collaborative training of machine learning models over decentralized devices without exposing their local data.

Federated Learning

SignAvatar: Sign Language 3D Motion Reconstruction and Generation

no code implementations13 May 2024 Lu Dong, Lipisha Chaudhary, Fei Xu, Xiao Wang, Mason Lary, Ifeoma Nwogu

Achieving expressive 3D motion reconstruction and automatic generation for isolated sign words can be challenging, due to the lack of real-world 3D sign-word data, the complex nuances of signing motions, and the cross-modal understanding of sign language semantics.

Causality Extraction from Nuclear Licensee Event Reports Using a Hybrid Framework

no code implementations8 Apr 2024 Shahidur Rahoman Sohag, Sai Zhang, Min Xian, Shoukun Sun, Fei Xu, Zhegang Ma

Industry-wide nuclear power plant operating experience is a critical source of raw data for performing parameter estimations in reliability and risk models.

Relation Relation Extraction

FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clustering

no code implementations7 Mar 2024 Md Sirajul Islam, Simin Javaherian, Fei Xu, Xu Yuan, Li Chen, Nian-Feng Tzeng

Clustered federated learning (CFL) addresses this challenge by grouping clients based on the similarity of their data distributions.

Federated Learning

Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs

1 code implementation16 Dec 2023 Aodong Chen, Fei Xu, Li Han, Yuan Dong, Li Chen, Zhi Zhou, Fangming Liu

GPUs have become the \emph{defacto} hardware devices for accelerating Deep Neural Network (DNN) inference workloads.

Scheduling

Review of Machine Learning Methods for Additive Manufacturing of Functionally Graded Materials

no code implementations28 Sep 2023 Mohammad Karimzadeh, Deekshith Basvoju, Aleksandar Vakanski, Indrajit Charit, Fei Xu, Xinchang Zhang

Through an extensive survey of the literature, this review article explores the role of ML in addressing the inherent challenges in FGMs fabrication and encompasses parameter optimization, defect detection, and real-time monitoring.

Defect Detection

AGFormer: Efficient Graph Representation with Anchor-Graph Transformer

no code implementations12 May 2023 Bo Jiang, Fei Xu, Ziyan Zhang, Jin Tang, Feiping Nie

To alleviate the local receptive issue of GCN, Transformers have been exploited to capture the long range dependences of nodes for graph data representation and learning.

CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation

no code implementations9 Mar 2023 Shoukun Sun, Min Xian, Fei Xu, Luca Capriotti, Tiankai Yao

Remarkably, our model reduces by 33. 2\%, and 15. 5\% the number of clicks required to surpass an IoU of 0. 95 in the previous state-of-the-art approach on the Berkeley and DAVIS sets, respectively.

Image Augmentation Image Segmentation +3

Soft Sensing Regression Model: from Sensor to Wafer Metrology Forecasting

no code implementations21 Jan 2023 Angzhi Fan, Yu Huang, Fei Xu, Sthitie Bom

The semiconductor industry is one of the most technology-evolving and capital-intensive market sectors.

Fault Detection regression +1

Advanced Characterization-Informed Framework and Quantitative Insight to Irradiated Annular U-10Zr Metallic Fuels

no code implementations17 Oct 2022 Fei Xu, Lu Cai, Daniele Salvato, Fidelma Dilemma, Luca Capriotti, Tiankai Yao

Conclusive findings were obtained and allowed for evaluation of the lanthanide transportation through connected bubbles based on approximately 67, 000 fission gas bubbles of the two advanced samples.

Backward bifurcation and saddle-node bifurcation in virus-immune dynamics

no code implementations1 Dec 2021 Tengfei Wang, Shaoli Wang, Fei Xu

The values of backward bifurcation point and saddle node bifurcation point are the elite control threshold and post-treatment control threshold respectively.

Math

Multimodal Dialogue Response Generation

no code implementations ACL 2022 Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang

In such a low-resource setting, we devise a novel conversational agent, Divter, in order to isolate parameters that depend on multimodal dialogues from the entire generation model.

Dialogue Generation Response Generation +1

Completeness of the induced cotorsion pairs in functor categories

no code implementations11 Feb 2021 Zhenxing Di, Liping Li, Li Liang, Fei Xu

This paper focuses on a question raised by Holm and J{\o}rgensen, who asked if the induced cotorsion pairs $(\Phi({\sf X}),\Phi({\sf X})^{\perp})$ and $(^{\perp}\Psi({\sf Y}),\Psi({\sf Y}))$ in $\mathrm{Rep}(Q,{\sf{A}})$ -- the category of all $\sf{A}$-valued representations of a quiver $Q$ -- are complete whenever $(\sf X,\sf Y)$ is a complete cotorsion pair in an abelian category $\sf{A}$ satisfying some mild conditions.

Representation Theory K-Theory and Homology

Breast Anatomy Enriched Tumor Saliency Estimation

no code implementations23 Oct 2019 Fei Xu, Yingtao Zhang, Min Xian, H. D. Cheng, Boyu Zhang, Jianrui Ding, Chunping Ning, Ying Wang

Then we refine the layers by integrating a non-semantic breast anatomy model to solve the problems of incomplete mammary layers.

Anatomy Saliency Prediction

Tumor Saliency Estimation for Breast Ultrasound Images via Breast Anatomy Modeling

no code implementations18 Jun 2019 Fei Xu, Yingtao Zhang, Min Xian, H. D. Cheng, Boyu Zhang, Jianrui Ding, Chunping Ning, Ying Wang

First, we model breast anatomy and decompose breast ultrasound image into layers using Neutro-Connectedness; then utilize the layers to generate the foreground and background maps; and finally propose a novel objective function to estimate the tumor saliency by integrating the foreground map, background map, adaptive center bias, and region-based correlation cues.

Anatomy Feature Correlation +1

A Hybrid Framework for Tumor Saliency Estimation

no code implementations27 Jun 2018 Fei Xu, Min Xian, Yingtao Zhang, Kuan Huang, H. D. Cheng, Boyu Zhang, Jianrui Ding, Chunping Ning, Ying Wang

Automatic tumor segmentation of breast ultrasound (BUS) image is quite challenging due to the complicated anatomic structure of breast and poor image quality.

Saliency Prediction Segmentation +1

BUSIS: A Benchmark for Breast Ultrasound Image Segmentation

1 code implementation9 Jan 2018 Min Xian, Yingtao Zhang, H. D. Cheng, Fei Xu, Kuan Huang, Boyu Zhang, Jianrui Ding, Chunping Ning, Ying Wang

Breast ultrasound (BUS) image segmentation is challenging and critical for BUS Comput-er-Aided Diagnosis (CAD) systems.

Image Segmentation Segmentation +1

Neutro-Connectedness Cut

no code implementations19 Dec 2015 Min Xian, Yingtao Zhang, H. D. Cheng, Fei Xu, Jianrui Ding

Interactive image segmentation is a challenging task and receives increasing attention recently; however, two major drawbacks exist in interactive segmentation approaches.

Image Segmentation Interactive Segmentation +2

Individuation, Identification and Object Discovery

no code implementations NeurIPS 2009 Charles Kemp, Alan Jern, Fei Xu

Humans are typically able to infer how many objects their environment contains and to recognize when the same object is encountered twice.

Object Object Discovery

A rational model of preference learning and choice prediction by children

no code implementations NeurIPS 2008 Christopher G. Lucas, Thomas L. Griffiths, Fei Xu, Christine Fawcett

Young children demonstrate the ability to make inferences about the preferences of other agents based on their choices.

An ideal observer model of infant object perception

no code implementations NeurIPS 2008 Charles Kemp, Fei Xu

Before the age of 4 months, infants make inductive inferences about the motions of physical objects.

Object

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