Search Results for author: Lei Liu

Found 54 papers, 10 papers with code

Context Matters: A Strategy to Pre-train Language Model for Science Education

no code implementations27 Jan 2023 Zhengliang Liu, Xinyu He, Lei Liu, Tianming Liu, Xiaoming Zhai

However, the ideal type of data to contextualize pre-trained language model and improve the performance in automatically scoring student written responses remains unclear.

Language Modelling

Some Properties of L-banded Matrices

no code implementations20 Dec 2022 Shunqi Huang, Lei Liu, Brian M. Kurkoski

Damping is commonly employed to ensure the convergence of iterative algorithms.

Mitigation of Spatial Nonstationarity with Vision Transformers

no code implementations9 Dec 2022 Lei Liu, Javier E. Santos, Maša Prodanović, Michael J. Pyrcz

However, there is a paucity of demonstrated best practice and general guidance on mitigation of spatial nonstationarity with deep learning in the geospatial context.

Parameter-Efficient Transformer with Hybrid Axial-Attention for Medical Image Segmentation

no code implementations17 Nov 2022 Yiyue Hu, Lei Zhang, Nan Mu, Lei Liu

To this end, we propose a parameter-efficient transformer to explore intrinsic inductive bias via position information for medical image segmentation.

Image Segmentation Inductive Bias +2

High Speed Rotation Estimation with Dynamic Vision Sensors

no code implementations6 Sep 2022 Guangrong Zhao, Yiran Shen, Ning Chen, Pengfei Hu, Lei Liu, Hongkai Wen

By designing a series of signal processing algorithms bespoke for dynamic vision sensing on mobile devices, EV-Tach is able to extract the rotational speed accurately from the event stream produced by dynamic vision sensing on rotary targets.

Reinforcement Learning with Prior Policy Guidance for Motion Planning of Dual-Arm Free-Floating Space Robot

1 code implementation3 Sep 2022 Yuxue Cao, Shengjie Wang, Xiang Zheng, Wenke Ma, Xinru Xie, Lei Liu

However, due to the increase in planning dimension and the intensification of system dynamics coupling, the motion planning of dual-arm free-floating space robots remains an open challenge.

Motion Planning

Capacity Optimality of OAMP in Coded Large Unitarily Invariant Systems

no code implementations23 Jun 2022 Lei Liu, Shansuo Liang, Li Ping

Under the assumptions that the state evolution for joint OAMP and FEC decoding is correct and the replica method is reliable, we analyze the achievable rate of OAMP.

Sufficient Statistic Memory Approximate Message Passing

no code implementations23 Jun 2022 Lei Liu, Shunqi Huang, Brian M. Kurkoski

Approximate message passing (AMP) type algorithms have been widely used in the signal reconstruction of certain large random linear systems.

BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML

1 code implementation AutoML'2022 2022 Mehdi Bahrami, Wei-Peng Chen, Lei Liu, Mukul Prasad

One of the common data pre-processing operations implemented in AutoML systems is to encode categorical features as numerical features.

AutoML

Space-Air-Ground Integrated Multi-domain Network Resource Orchestration based on Virtual Network Architecture: a DRL Method

no code implementations3 Feb 2022 Peiying Zhang, Chao Wang, Neeraj Kumar, Lei Liu

Based on virtual network architecture and deep reinforcement learning (DRL), we model SAGIN's heterogeneous resource orchestration as a multi-domain virtual network embedding (VNE) problem, and propose a SAGIN cross-domain VNE algorithm.

Network Embedding

Attribute-Based Progressive Fusion Network for RGBT Tracking

1 code implementation AAAI2022 2022 Yun Xiao, Mengmeng Yang, Chenglong Li, Lei Liu, Jin Tang

RGBT tracking usually suffers from various challenging factors of fast motion, scale variation, illumination variation, thermal crossover and occlusion, to name a few.

Rgb-T Tracking

Optimal LED Spectral Multiplexing for NIR2RGB Translation

1 code implementation CVPR 2022 Lei Liu, Yuze Chen, Junchi Yan, Yinqiang Zheng

The industry practice for night video surveillance is to use auxiliary near-infrared (NIR) LED diodes, usually centered at 850nm or 940nm, for scene illumination.

Translation

Sufficient Statistic Memory AMP

no code implementations31 Dec 2021 Lei Liu, Shunqi Huang, Brian M. Kurkoski

As an example, we construct a sufficient statistic Bayes-optimal MAMP (SS-BO-MAMP) whose state evolution converges to the minimum (i. e., Bayes-optimal) mean square error (MSE) predicted by replica methods.

Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark

no code implementations8 Nov 2021 Chenglong Li, Tianhao Zhu, Lei Liu, Xiaonan Si, Zilin Fan, Sulan Zhai

To promote the research and development of cross-modal object tracking, we propose a new algorithm, which learns the modality-aware target representation to mitigate the appearance gap between RGB and NIR modalities in the tracking process.

Object Tracking Visual Tracking

Open-Set Crowdsourcing using Multiple-Source Transfer Learning

no code implementations7 Nov 2021 Guangyang Han, Guoxian Yu, Lei Liu, Lizhen Cui, Carlotta Domeniconi, Xiangliang Zhang

First, OSCrowd integrates crowd theme related datasets into a large source domain to facilitate partial transfer learning to approximate the label space inference of these tasks.

Transfer Learning

Cross-modal Zero-shot Hashing by Label Attributes Embedding

no code implementations7 Nov 2021 Runmin Wang, Guoxian Yu, Lei Liu, Lizhen Cui, Carlotta Domeniconi, Xiangliang Zhang

Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search.

MetaMIML: Meta Multi-Instance Multi-Label Learning

no code implementations7 Nov 2021 Yuanlin Yang, Guoxian Yu, Jun Wang, Lei Liu, Carlotta Domeniconi, Maozu Guo

Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances.

Meta-Learning Multi-Label Learning +1

AugmentedCode: Examining the Effects of Natural Language Resources in Code Retrieval Models

1 code implementation16 Oct 2021 Mehdi Bahrami, N. C. Shrikanth, Yuji Mizobuchi, Lei Liu, Masahiro Fukuyori, Wei-Peng Chen, Kazuki Munakata

Code retrieval is allowing software engineers to search codes through a natural language query, which relies on both natural language processing and software engineering techniques.

Retrieval

A Dialogue-based Information Extraction System for Medical Insurance Assessment

no code implementations Findings (ACL) 2021 Shuang Peng, Mengdi Zhou, Minghui Yang, Haitao Mi, Shaosheng Cao, Zujie Wen, Teng Xu, Hongbin Wang, Lei Liu

In the Chinese medical insurance industry, the assessor's role is essential and requires significant efforts to converse with the claimant.

Investigate the Essence of Long-Tailed Recognition from a Unified Perspective

1 code implementation8 Jul 2021 Lei Liu, Li Liu

Specifically, we demonstrate that long-tailed recognition suffers from both sample number and category similarity.

Self-Supervised Learning

Memory Approximate Message Passing

no code implementations4 Jun 2021 Lei Liu, Shunqi Huang, Brian M. Kurkoski

Approximate message passing (AMP) is a low-cost iterative parameter-estimation technique for certain high-dimensional linear systems with non-Gaussian distributions.

A Systematic Investigation of KB-Text Embedding Alignment at Scale

1 code implementation ACL 2021 Vardaan Pahuja, Yu Gu, Wenhu Chen, Mehdi Bahrami, Lei Liu, Wei-Peng Chen, Yu Su

Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and timely knowledge in an unstructured way.

Link Prediction

Few-Shot Partial-Label Learning

no code implementations2 Jun 2021 Yunfeng Zhao, Guoxian Yu, Lei Liu, Zhongmin Yan, Lizhen Cui, Carlotta Domeniconi

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label.

Few-Shot Learning Metric Learning +1

Extending Isolation Forest for Anomaly Detection in Big Data via K-Means

no code implementations27 Apr 2021 Md Tahmid Rahman Laskar, Jimmy Huang, Vladan Smetana, Chris Stewart, Kees Pouw, Aijun An, Stephen Chan, Lei Liu

Moreover, we evaluate our proposed model on the live streaming data and find that our proposed system can be used for real-time anomaly detection in the industrial setup.

Anomaly Detection Intrusion Detection

Pinpointing the Memory Behaviors of DNN Training

no code implementations1 Apr 2021 Jiansong Li, Xiao Dong, Guangli Li, Peng Zhao, Xueying Wang, Xiaobing Chen, Xianzhi Yu, Yongxin Yang, Zihan Jiang, Wei Cao, Lei Liu, Xiaobing Feng

The training of deep neural networks (DNNs) is usually memory-hungry due to the limited device memory capacity of DNN accelerators.

An Interpretable Mapping from a Communication System to a Neural Network for Optimal Transceiver-Joint Equalization

no code implementations23 Mar 2021 Zhiqun Zhai, Hexun Jiang, Mengfan Fu, Lei Liu, Lilin Yi, Weisheng Hu, Qunbi Zhuge

In this paper, we propose a scheme that utilizes the optimization ability of artificial intelligence (AI) for optimal transceiver-joint equalization in compensating for the optical filtering impairments caused by wavelength selective switches (WSS).

Efficient electrochemical reduction of CO2 to CO by soft functional materials

no code implementations9 Feb 2021 Yanjie Hu, Jiaqi Feng, Xiangping Zhang, Hongshuai Gao, Saimeng Jin, Lei Liu, Weifeng Shen

This work provides a new strategy to design novel ILs for high efficiency electrochemical reduction of CO2 to CO.

Materials Science

A molecular dynamics simulation study on the frustrated Lewis pairs in ionic liquids

no code implementations21 Jan 2021 Xiaoqing Liu, XiaoJing Wang, Tianhao Yu, Weizhen Zhao, Lei Liu

Spatial distribution function (SDF) results show that toluene formed a continuum solvation shell, which hinders the interactions of (tBu)3P and B(C6F5)3 , while [Cnmim][NTf2] leave a relatively large empty space, which is accessible by (tBu3)P molecules, resulting in a higher probability of Lewis acids and bases interactions.

Chemical Physics

An LSTM-Aided Hybrid Random Access Scheme for 6G Machine Type Communication Networks

no code implementations25 Dec 2020 Wenchao Zhai, Huimei Han, Lei Liu, Jun Zhao

In this paper, an LSTM-aided hybrid random access scheme (LSTMH-RA) is proposed to support diverse quality of service (QoS) requirements in 6G machine-type communication (MTC) networks, where massive MTC (mMTC) devices and ultra-reliable low latency communications (URLLC) devices coexist.

Topological Transformations in Pentagonal 2D Materials Induced by Stone-Wales Defects

no code implementations22 Dec 2020 Yu Zheng, Duyu Chen, Lei Liu, Houlong Zhuang, Yang Jiao

We discover two distinct topological pathways through which the pentagonal Cairo tiling (P5), a structural model for single-layer $AB_2$ pyrite materials, respectively transforms into a crystalline rhombus-hexagon (C46) tiling and random rhombus-pentagon-hexagon (R456) tilings, by continuously introducing the Stone-Wales (SW) topological defects.

Soft Condensed Matter Disordered Systems and Neural Networks Materials Science

Memory AMP

1 code implementation20 Dec 2020 Lei Liu, Shunqi Huang, Brian M. Kurkoski

To asymptotically characterize the performance of BO-MAMP, a state evolution is derived.

Denoising

Theory of polymer diffusion in polymer-nanoparticle mixtures: effect of nanoparticle concentration and polymer length

no code implementations22 Nov 2020 Bokai Zhang, Jian Li, Juan-mei Hu, Lei Liu

The dynamics of polymer-nanoparticle (NP) mixtures, which involves multiple scales and system-specific variables, has posed a long-standing challenge on its theoretical description.

Soft Condensed Matter

Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

no code implementations30 Oct 2020 Guangli Li, Xiu Ma, Xueying Wang, Lei Liu, Jingling Xue, Xiaobing Feng

The increasing computational cost of deep neural network models limits the applicability of intelligent applications on resource-constrained edge devices.

Network Pruning

Challenge-Aware RGBT Tracking

no code implementations ECCV 2020 Chenglong Li, Lei Liu, Andong Lu, Qing Ji, Jin Tang

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking.

W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network

no code implementations11 Jun 2020 Hongwei Zhao, Chengtao Peng, Lei Liu, Bin Li

To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation.

Multi-Task Learning

Person Re-Identification via Active Hard Sample Mining

no code implementations10 Apr 2020 Xin Xu, Lei Liu, Weifeng Liu, Meng Wang, Ruimin Hu

To alleviate such a problem, we present an active hard sample mining framework via training an effective re-ID model with the least labeling efforts.

Person Re-Identification

Identification of splicing edges in tampered image based on Dichromatic Reflection Model

no code implementations9 Apr 2020 Zhe Shen, Peng Sun, Yubo Lang, Lei Liu, Silong Peng

Therefore we present a novel optic-physical method to discriminate splicing edges from natural edges in a tampered image.

PDANet: Pyramid Density-aware Attention Net for Accurate Crowd Counting

no code implementations16 Jan 2020 Saeed Amirgholipour, Xiangjian He, Wenjing Jia, Dadong Wang, Lei Liu

For this purpose, a classifier evaluates the density level of the input features and then passes them to the corresponding high and low crowded DAD modules.

Crowd Counting

Hyperspectral Image Classification Based on Adaptive Sparse Deep Network

no code implementations21 Oct 2019 Jingwen Yan, Zixin Xie, Jingyao Chen, Yinan Liu, Lei Liu

Sparse model is widely used in hyperspectral image classification. However, different of sparsity and regularization parameters has great influence on the classification results. In this paper, a novel adaptive sparse deep network based on deep architecture is proposed, which can construct the optimal sparse representation and regularization parameters by deep network. Firstly, a data flow graph is designed to represent each update iteration based on Alternating Direction Method of Multipliers (ADMM) algorithm. Forward network and Back-Propagation network are deduced. All parameters are updated by gradient descent in Back-Propagation. Then we proposed an Adaptive Sparse Deep Network. Comparing with several traditional classifiers or other algorithm for sparse model, experiment results indicate that our method achieves great improvement in HSI classification.

Classification General Classification +1

DENet: A Universal Network for Counting Crowd with Varying Densities and Scales

no code implementations17 Apr 2019 Lei Liu, Jie Jiang, Wenjing Jia, Saeed Amirgholipour, Michelle Zeibots, Xiangjian He

Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem.

Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

no code implementations16 Dec 2018 Guangli Li, Lei Liu, Xueying Wang, Xiao Dong, Peng Zhao, Xiaobing Feng

By analyzing the characteristics of layers in DNNs, an auto-tuning neural network quantization framework for collaborative inference is proposed.

Quantization

The localization of single pulse in VLBI observation

1 code implementation21 Oct 2018 Lei Liu, Wu Jiang, Weimin Zheng, Zhen Yan, Juan Zhang, Maoli Ma, Wentao Luo

The combination of cross spectrum based detection and the localization proposed in this work then provide a thorough solution for searching single pulse in VLBI observation.

Instrumentation and Methods for Astrophysics

TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks

no code implementations22 Aug 2018 Xinyue Liu, Xiangnan Kong, Lei Liu, Kuorong Chiang

To address these issues, we study the problem of syntax-aware sequence generation with GANs, in which a collection of real sequences and a set of pre-defined grammatical rules are given to both discriminator and generator.

Image Generation

Learning a Rotation Invariant Detector with Rotatable Bounding Box

4 code implementations26 Nov 2017 Lei Liu, Zongxu Pan, Bin Lei

The existing methods are not robust to angle varies of the objects because of the use of traditional bounding box, which is a rotation variant structure for locating rotated objects.

Random Forests of Interaction Trees for Estimating Individualized Treatment Effects in Randomized Trials

no code implementations14 Sep 2017 Xiaogang Su, Annette T. Peña, Lei Liu, Richard A. Levine

Assessing heterogeneous treatment effects has become a growing interest in advancing precision medicine.

Hybrid Dirac Semimetal in CaAgBi Materials Family

no code implementations13 Jun 2017 Cong Chen, Shan-Shan Wang, Lei Liu, Zhi-Ming Yu, Xian-Lei Sheng, Ziyu Chen, Shengyuan A. Yang

Based on their formation mechanisms, Dirac points in three-dimensional systems can be classified as accidental or essential.

Materials Science

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