Search Results for author: Ming Li

Found 225 papers, 61 papers with code

Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering

1 code implementation Findings (EMNLP) 2021 Minghan Li, Ming Li, Kun Xiong, Jimmy Lin

Our method reaches state-of-the-art performance on 5 benchmark QA datasets, with up to 10% improvement in top-100 accuracy compared to a joint-training multi-task DPR on SQuAD.

Open-Domain Question Answering Retrieval

Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach

1 code implementation Findings (EMNLP) 2021 Anup Anand Deshmukh, Qianqiu Zhang, Ming Li, Jimmy Lin, Lili Mou

In this paper, we address unsupervised chunking as a new task of syntactic structure induction, which is helpful for understanding the linguistic structures of human languages as well as processing low-resource languages.

Chunking Transfer Learning

Where to Begin? From Random to Foundation Model Instructed Initialization in Federated Learning for Medical Image Segmentation

no code implementations27 Nov 2023 Ming Li, Guang Yang

In medical image analysis, Federated Learning (FL) stands out as a key technology that enables privacy-preserved, decentralized data processing, crucial for handling sensitive medical data.

Federated Learning Image Segmentation +2

Ethical implications of ChatGPT in higher education: A scoping review

no code implementations24 Nov 2023 Ming Li, Ariunaa Enkhtur, Fei Cheng, Beverley Anne Yamamoto

This scoping review explores the ethical challenges of using ChatGPT in education, focusing particularly on issues related to higher education.


Potential Societal Biases of ChatGPT in Higher Education: A Scoping Review

no code implementations24 Nov 2023 Ming Li, Ariunaa Enkhtur, Beverley Anne Yamamoto, Fei Cheng

In this scoping review, we clarify the ways in which biases related to GAI in higher education settings have been discussed in recent academic publications and identify what type of potential biases are commonly reported in this body of literature.

Joint Sensing and Communication Optimization in Target-Mounted STARS-Assisted Vehicular Networks: A MADRL Approach

no code implementations17 Nov 2023 Haocheng Zhang, Rang Liu, Ming Li, Wei Wang, Qian Liu

Extensive experimental results confirm the effectiveness of our proposed MADRL framework in improving both sensing and communication performance through the utilization of target-mounted STARS.

Decision Making

Instant3D: Instant Text-to-3D Generation

no code implementations14 Nov 2023 Ming Li, Pan Zhou, Jia-Wei Liu, Jussi Keppo, Min Lin, Shuicheng Yan, Xiangyu Xu

Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network.

Text to 3D

Data-Free Distillation Improves Efficiency and Privacy in Federated Thorax Disease Analysis

no code implementations22 Oct 2023 Ming Li, Guang Yang

Thorax disease analysis in large-scale, multi-centre, and multi-scanner settings is often limited by strict privacy policies.

Federated Learning Privacy Preserving

Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model

1 code implementation Nature Machine Intelligence 2023 Zeping Mao, Ruixue Zhang, Lei Xin, Ming Li

Here we reveal that in the process of peptide prediction, missing fragmentation results in the generation of incorrect amino acids within those regions and causes error accumulation thereafter.

de novo peptide sequencing

Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning

1 code implementation18 Oct 2023 Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Heng Huang, Jiuxiang Gu, Tianyi Zhou

Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation.

Natural Language Understanding

End-to-end Online Speaker Diarization with Target Speaker Tracking

no code implementations12 Oct 2023 Weiqing Wang, Ming Li

During the inference process, we employ a front-end model to extract the frame-level speaker embeddings for each coming block of a signal.

Action Detection Activity Detection +3

Multi-objective Progressive Clustering for Semi-supervised Domain Adaptation in Speaker Verification

no code implementations7 Oct 2023 Ze Li, Yuke Lin, Ning Jiang, Xiaoyi Qin, Guoqing Zhao, Haiying Wu, Ming Li

Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks.

Clustering Denoising +3

Haha-Pod: An Attempt for Laughter-based Non-Verbal Speaker Verification

1 code implementation25 Sep 2023 Yuke Lin, Xiaoyi Qin, Ning Jiang, Guoqing Zhao, Ming Li

It is widely acknowledged that discriminative representation for speaker verification can be extracted from verbal speech.

Speaker Verification Test

BiSinger: Bilingual Singing Voice Synthesis

no code implementations25 Sep 2023 Huali Zhou, Yueqian Lin, Yao Shi, Peng Sun, Ming Li

We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data.

Singing Voice Synthesis Voice Conversion

Semi-supervised News Discourse Profiling with Contrastive Learning

no code implementations20 Sep 2023 Ming Li, Ruihong Huang

News Discourse Profiling seeks to scrutinize the event-related role of each sentence in a news article and has been proven useful across various downstream applications.

Contrastive Learning

Cramer-Rao Bound Optimization for Active RIS-Empowered ISAC Systems

no code implementations17 Sep 2023 Qi Zhu, Ming Li, Rang Liu, Qian Liu

In this paper, we investigate the deployment of active RIS-empowered ISAC systems to enhance radar echo signal quality as well as communication performance.

RST-style Discourse Parsing Guided by Document-level Content Structures

no code implementations8 Sep 2023 Ming Li, Ruihong Huang

Rhetorical Structure Theory based Discourse Parsing (RST-DP) explores how clauses, sentences, and large text spans compose a whole discourse and presents the rhetorical structure as a hierarchical tree.

Discourse Parsing

Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation

no code implementations6 Sep 2023 Danwei Cai, Ming Li

This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals.

Knowledge Distillation Speaker Verification +1

DLIP: Distilling Language-Image Pre-training

no code implementations24 Aug 2023 Huafeng Kuang, Jie Wu, Xiawu Zheng, Ming Li, Xuefeng Xiao, Rui Wang, Min Zheng, Rongrong Ji

Furthermore, DLIP succeeds in retaining more than 95% of the performance with 22. 4% parameters and 24. 8% FLOPs compared to the teacher model and accelerates inference speed by 2. 7x.

Image Captioning Knowledge Distillation +5

The DKU-DUKEECE System for the Manipulation Region Location Task of ADD 2023

no code implementations20 Aug 2023 Zexin Cai, Weiqing Wang, Yikang Wang, Ming Li

This paper introduces our system designed for Track 2, which focuses on locating manipulated regions, in the second Audio Deepfake Detection Challenge (ADD 2023).

Boundary Detection DeepFake Detection +1

VoxBlink: A Large Scale Speaker Verification Dataset on Camera

no code implementations14 Aug 2023 Yuke Lin, Xiaoyi Qin, Guoqing Zhao, Ming Cheng, Ning Jiang, Haiyang Wu, Ming Li

In this paper, we introduce a large-scale and high-quality audio-visual speaker verification dataset, named VoxBlink.

Speaker Recognition Speaker Verification

Approximating Human-Like Few-shot Learning with GPT-based Compression

no code implementations14 Aug 2023 Cynthia Huang, Yuqing Xie, Zhiying Jiang, Jimmy Lin, Ming Li

Leveraging the approximated information distance, our method allows the direct application of GPT models in quantitative text similarity measurements.

Data Compression Few-Shot Learning +6

A Novel Joint Angle-Range-Velocity Estimation Method for MIMO-OFDM ISAC Systems

no code implementations7 Aug 2023 Zichao Xiao, Rang Liu, Ming Li, Qian Liu

Therefore, the proposed joint estimation algorithm can achieve larger processing gains and higher resolution by fully exploiting echo signals and jointly estimating the angle-range-velocity information.

Masked and Swapped Sequence Modeling for Next Novel Basket Recommendation in Grocery Shopping

1 code implementation2 Aug 2023 Ming Li, Mozhdeh Ariannezhad, Andrew Yates, Maarten de Rijke

In next basket recommendation (NBR), it is useful to distinguish between repeat items, i. e., items that a user has consumed before, and explore items, i. e., items that a user has not consumed before.

Next-basket recommendation

AlignDet: Aligning Pre-training and Fine-tuning in Object Detection

1 code implementation ICCV 2023 Ming Li, Jie Wu, Xionghui Wang, Chen Chen, Jie Qin, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan

To this end, we propose AlignDet, a unified pre-training framework that can be adapted to various existing detectors to alleviate the discrepancies.

object-detection Object Detection

Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix

no code implementations5 Jul 2023 Shaogao Lv, Gang Wen, Shiyu Liu, Linsen Wei, Ming Li

Overall, our research highlights the importance of integrating feature and graph information alignment in GSL, as inspired by our derived theoretical result, and showcases the superiority of our approach in handling noisy graph structures through comprehensive experiments on real-world datasets.

Graph structure learning

Thompson Sampling under Bernoulli Rewards with Local Differential Privacy

no code implementations3 Jul 2023 Bo Jiang, Tianchi Zhao, Ming Li

This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee.

Thompson Sampling

First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment

1 code implementation23 Jun 2023 Tom Tongjia Chen, Hongshan Yu, Zhengeng Yang, Ming Li, Zechuan Li, Jingwen Wang, Wei Miao, Wei Sun, Chen Chen

Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions.

Human-Object Interaction Detection

Permutation Equivariant Graph Framelets for Heterophilous Graph Learning

1 code implementation7 Jun 2023 Jianfei Li, Ruigang Zheng, Han Feng, Ming Li, Xiaosheng Zhuang

The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network models and suggests aggregations beyond the 1-hop neighborhood.

Graph Learning

A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution

1 code implementation2 Jun 2023 Xiaoyong Mei, Yi Yang, Ming Li, Changqin Huang, Kai Zhang, Pietro Lió

In this study, we propose a feature reuse framework that guides the step-by-step texture reconstruction process through different stages, reducing the negative impacts of perceptual and adversarial loss.

Image Super-Resolution Reference-based Super-Resolution

Low-Range-Sidelobe Waveform Design for MIMO-OFDM ISAC Systems

no code implementations30 May 2023 Peishi Li, Zichao Xiao, Ming Li, Rang Liu, Qian Liu

Integrated sensing and communication (ISAC) is a promising technology in future wireless systems owing to its efficient hardware and spectrum utilization.

AUC Optimization from Multiple Unlabeled Datasets

no code implementations25 May 2023 Zheng Xie, Yu Liu, Ming Li

In this paper, we study the problem of building an AUC (area under ROC curve) optimization model from multiple unlabeled datasets, which maximizes the pairwise ranking ability of the classifier.

Weakly-supervised Learning

Weakly Supervised AUC Optimization: A Unified Partial AUC Approach

no code implementations23 May 2023 Zheng Xie, Yu Liu, Hao-Yuan He, Ming Li, Zhi-Hua Zhou

Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision.

Stability and Generalization of lp-Regularized Stochastic Learning for GCN

no code implementations20 May 2023 Shiyu Liu, Linsen Wei, Shaogao Lv, Ming Li

For a single-layer GCN, we establish an explicit theoretical understanding of GCN with the $\ell_p$-regularized stochastic learning by analyzing the stability of our SGD proximal algorithm.

Graph Learning

Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation

no code implementations18 May 2023 Xin-Ye Li, Jiang-Tian Xue, Zheng Xie, Ming Li

We demonstrate that Brainstorm significantly enhances the ability of LLMs to solve competition-level programming problems, resulting in a more than 50% increase in the pass@$k$ metrics for ChatGPT on the CodeContests benchmark, achieving state-of-the-art performance.

Code Generation

A Unified Framework for Exploratory Learning-Aided Community Detection in Networks with Unknown Topology

no code implementations10 Apr 2023 Yu Hou, Cong Tran, Ming Li, Won-Yong Shin

In social networks, the discovery of community structures has received considerable attention as a fundamental problem in various network analysis tasks.

Community Detection

FAN: Fatigue-Aware Network for Click-Through Rate Prediction in E-commerce Recommendation

1 code implementation10 Apr 2023 Ming Li, Naiyin Liu, Xiaofeng Pan, Yang Huang, Ningning Li, Yingmin Su, Chengjun Mao, Bo Cao

Then the frequency spectrum is modulated by category information of the target item to model the bias that both the upper bound of fatigue and users' patience is different for different categories.

Click-Through Rate Prediction Time Series

Moving Obstacle Collision Avoidance via Chance-Constrained MPC with CBF

no code implementations4 Apr 2023 Ming Li, Zhiyong Sun, Zirui Liao, Siep Weiland

Model predictive control (MPC) with control barrier functions (CBF) is a promising solution to address the moving obstacle collision avoidance (MOCA) problem.

Collision Avoidance

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

no code implementations CVPR 2023 Jie Qin, Jie Wu, Pengxiang Yan, Ming Li, Ren Yuxi, Xuefeng Xiao, Yitong Wang, Rui Wang, Shilei Wen, Xin Pan, Xingang Wang

Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios.

Image Segmentation Instance Segmentation +3

XVoxel-Based Parametric Design Optimization of Feature Models

no code implementations17 Mar 2023 Ming Li, Chengfeng Lin, Wei Chen, Yusheng Liu, Shuming Gao, Qiang Zou

As such, it can establish a direct mapping between design models and analysis models, which in turn enables automatic updates on simulation results for design modifications, and vice versa -- effectively a closed loop between CAD and CAE.

AERK: Aligned Entropic Reproducing Kernels through Continuous-time Quantum Walks

no code implementations4 Mar 2023 Lixin Cui, Ming Li, Yue Wang, Lu Bai, Edwin R. Hancock

For pairwise graphs, the proposed AERK kernel is defined by computing a reproducing kernel based similarity between the quantum Shannon entropies of their each pair of aligned vertices.

Graph Classification

RIS-Aided Integrated Sensing and Communication: Joint Beamforming and Reflection Design

no code implementations22 Feb 2023 Honghao Luo, Rang Liu, Ming Li, Qian Liu

Integrated sensing and communication (ISAC) has been envisioned as a promising technique to alleviate the spectrum congestion problem.

Joint Transceiver Beamforming and Reflecting Design for Active RIS-Aided ISAC Systems

no code implementations21 Feb 2023 Qi Zhu, Ming Li, Rang Liu, Qian Liu

Integrated sensing and communication (ISAC) is recognized as a promising technology with great potential in saving hardware and spectrum resources, since it simultaneously realizes radar detection and user communication functions in the fully-shared platform.

Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)

1 code implementation5 Feb 2023 Ming Li, Xinming Huang, Ziming Zhang

To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors.

Representation Learning Self-Supervised Learning +1

SNR/CRB-Constrained Joint Beamforming and Reflection Designs for RIS-ISAC Systems

no code implementations26 Jan 2023 Rang Liu, Ming Li, Qian Liu, A. Lee Swindlehurst

Two optimization problems are formulated for maximizing the achievable sum-rate of the multi-user communications under an SNR constraint for target detection or a CRB constraint for parameter estimation, the transmit power budget, and the unit-modulus constraint of the RIS reflection coefficients.

STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition

no code implementations ICCV 2023 Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan

For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i. e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective.

Action Recognition Facial Expression Recognition (FER) +2

Deep Learning-Based UAV Aerial Triangulation without Image Control Points

no code implementations7 Jan 2023 Jiageng Zhong, Ming Li, Jiangying Qin, Hanqi Zhang

The emerging drone aerial survey has the advantages of low cost, high efficiency, and flexible use.

Image Registration POS

A Theory of Human-Like Few-Shot Learning

no code implementations3 Jan 2023 Zhiying Jiang, Rui Wang, Dongbo Bu, Ming Li

We aim to bridge the gap between our common-sense few-sample human learning and large-data machine learning.

Common Sense Reasoning Few-Shot Learning

Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning

no code implementations CVPR 2023 Ming Li, Qingli Li, Yan Wang

The second key element is that we design class balanced adaptive thresholds via considering the empirical distribution of all training data in local clients, to encourage a balanced training process.

An operational framework to automatically evaluate the quality of weather observations from third-party stations

no code implementations5 Dec 2022 Quanxi Shao, Ming Li, Joel Janek Dabrowski, Shuvo Bakar, Ashfaqur Rahman, Andrea Powell, Brent Henderson

With increasing number of crowdsourced private automatic weather stations (called TPAWS) established to fill the gap of official network and obtain local weather information for various purposes, the data quality is a major concern in promoting their usage.

Joint Secure Transmit Beamforming Designs for Integrated Sensing and Communication Systems

no code implementations1 Dec 2022 Jinjin Chu, Rang Liu, Ming Li, Yang Liu, Qian Liu

Integrated sensing and communication (ISAC), which allows individual radar and communication systems to share the same spectrum bands, is an emerging and promising technique for alleviating spectrum congestion problems.

HAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classification

no code implementations5 Nov 2022 Lu Bai, Lixin Cui, Yue Wang, Ming Li, Edwin R. Hancock

In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs.

Graph Classification

Waveform Boundary Detection for Partially Spoofed Audio

no code implementations1 Nov 2022 Zexin Cai, Weiqing Wang, Ming Li

The present paper proposes a waveform boundary detection system for audio spoofing attacks containing partially manipulated segments.

Boundary Detection

Laugh Betrays You? Learning Robust Speaker Representation From Speech Containing Non-Verbal Fragments

no code implementations28 Oct 2022 Yuke Lin, Xiaoyi Qin, Huahua Cui, Zhenyi Zhu, Ming Li

We collect a set of clips with laughter components by conducting a laughter detection script on VoxCeleb and part of the CN-Celeb dataset.

Speaker Verification

Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction

no code implementations28 Oct 2022 Ming Cheng, Weiqing Wang, Yucong Zhang, Xiaoyi Qin, Ming Li

Target-speaker voice activity detection is currently a promising approach for speaker diarization in complex acoustic environments.

Action Detection Activity Detection +2

End-to-End Learning for Symbol-Level Precoding and Detection with Adaptive Modulation

no code implementations25 Oct 2022 Rang Liu, Zhu Bo, Ming Li, Qian Liu

To overcome the performance bottleneck of these approaches, in this letter we propose an end-to-end learning based approach to jointly optimize the modulation orders, the transmit precoding and the receive detection for an SLP communication system.

RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction

1 code implementation18 Oct 2022 Liang Jin, Shixuan Gu, Donglai Wei, Jason Ken Adhinarta, Kaiming Kuang, Yongjie Jessica Zhang, Hanspeter Pfister, Bingbing Ni, Jiancheng Yang, Ming Li

Based on the RibSeg v2, we develop a pipeline including deep learning-based methods for rib labeling, and a skeletonization-based method for centerline extraction.


Deepfake Detection System for the ADD Challenge Track 3.2 Based on Score Fusion

no code implementations13 Oct 2022 Yuxiang Zhang, Jingze Lu, Xingming Wang, Zhuo Li, Runqiu Xiao, Wenchao Wang, Ming Li, Pengyuan Zhang

The overfitting of the model to the training set leads to extreme values of the scores and low correlation of the score distributions, which makes score fusion difficult.

Data Augmentation DeepFake Detection +1

Joint Beamforming Designs for Active Reconfigurable Intelligent Surface: A Sub-Connected Array Architecture

no code implementations5 Oct 2022 Qi Zhu, Ming Li, Rang Liu, Yang Liu, Qian Liu

Affected by the "double fading" effect, however, conventional passive RIS cannot bring considerable performance improvement when users are not close enough to RIS.

The DKU-DukeECE Diarization System for the VoxCeleb Speaker Recognition Challenge 2022

no code implementations4 Oct 2022 Weiqing Wang, Xiaoyi Qin, Ming Cheng, Yucong Zhang, Kangyue Wang, Ming Li

This paper discribes the DKU-DukeECE submission to the 4th track of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22).

Action Detection Activity Detection +2

Data-driven and machine-learning based prediction of wave propagation behavior in dam-break flood

no code implementations19 Sep 2022 Changli Li, Zheng Han, Yange Li, Ming Li, Weidong Wang

To show the performance of the RC-ESN model, we also provide a sensitivity analysis of the prediction accuracy concerning the key parameters including training set size, reservoir size, and spectral radius.

Multi-frequency PolSAR Image Fusion Classification Based on Semantic Interactive Information and Topological Structure

no code implementations5 Sep 2022 Yice Cao, Yan Wu, Ming Li, Mingjie Zheng, Peng Zhang, Jili Wang

Finally, an adaptive weighting fusion (AWF) strategy is proposed to merge inference from different bands, so as to make the MF joint classification decisions of SIC and TPC.

Classification Image Classification +1

Optimization for Reflection and Transmission Dual-Functional Active RIS-Assisted Systems

no code implementations5 Sep 2022 Yanan Ma, Ming Li, Yang Liu, Qingqing Wu, Qian Liu

Reconfigurable intelligent surface (RIS) has been deemed as one of potential components of future wireless communication systems because it can adaptively manipulate the wireless propagation environment with low-cost passive devices.

Joint Beamforming Design for Intelligent Omni Surface Assisted Wireless Communication Systems

no code implementations1 Sep 2022 Wenhao Cai, Ming Li, Yang Liu, Qingqing Wu, Qian Liu

Intelligent reflecting surface (IRS) has been widely considered as one of the key enabling techniques for future wireless communication networks owing to its ability of dynamically controlling the phase shift of reflected electromagnetic (EM) waves to construct a favorable propagation environment.

Non-Cooperative Resource Management for Intelligent Reflecting Surface Aided Networks

no code implementations1 Sep 2022 Wenhao Cai, Ming Li, Qian Liu

Intelligent reflecting surface (IRS) has emerged as a promising and revolutionizing technology for future wireless networks.


Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

1 code implementation22 Aug 2022 Jie Qin, Jie Wu, Ming Li, Xuefeng Xiao, Min Zheng, Xingang Wang

Consequently, we offer the first attempt to provide lightweight SSSS models via a novel multi-granularity distillation (MGD) scheme, where multi-granularity is captured from three aspects: i) complementary teacher structure; ii) labeled-unlabeled data cooperative distillation; iii) hierarchical and multi-levels loss setting.

Knowledge Distillation Semi-Supervised Semantic Segmentation

Reduced Implication-bias Logic Loss for Neuro-Symbolic Learning

no code implementations14 Aug 2022 Haoyuan He, WangZhou Dai, Ming Li

Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems.

Logical Reasoning

Partially Distributed Beamforming Design for RIS-Aided Cell-Free Networks

no code implementations10 Aug 2022 Pengfei Ni, Ming Li, Rang Liu, Qian Liu

Cell-free networks are regarded as a promising technology to meet higher rate requirements for beyond fifth-generation (5G) communications.

User Association and Hybrid Beamforming Designs for Cooperative mmWave MIMO Systems

no code implementations10 Aug 2022 Pengfei Ni, Rang Liu, Ming Li, Qian Liu

In an effort to further exploit multiple-antenna diversities, we also consider the dynamic subarray architecture and propose a novel antenna design algorithm for the analog beamforming design.

Joint Beamforming Design for RIS-Assisted Integrated Sensing and Communication Systems

no code implementations3 Aug 2022 Honghao Luo, Rang Liu, Ming Li, Yang Liu, Qian Liu

Integrated sensing and communication (ISAC) has been envisioned as a promising technology to tackle the spectrum congestion problem for future networks.

The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challenge

no code implementations15 Jul 2022 Xingming Wang, Xiaoyi Qin, Yikang Wang, Yunfei Xu, Ming Li

For CM systems, we propose two methods on top of the challenge baseline to further improve the performance, namely Embedding Random Sampling Augmentation (ERSA) and One-Class Confusion Loss(OCCL).

Speaker Verification

Online Target Speaker Voice Activity Detection for Speaker Diarization

no code implementations13 Jul 2022 Weiqing Wang, Qingjian Lin, Ming Li

We iteratively extract the results for each block and update the target speaker embedding until reaching the end of the signal.

Action Detection Activity Detection +3

Cross-Age Speaker Verification: Learning Age-Invariant Speaker Embeddings

1 code implementation13 Jul 2022 Xiaoyi Qin, Na Li, Chao Weng, Dan Su, Ming Li

In this paper, we mine cross-age test sets based on the VoxCeleb dataset and propose our age-invariant speaker representation(AISR) learning method.

Age Estimation Speaker Verification +1

Discriminator-Guided Model-Based Offline Imitation Learning

no code implementations1 Jul 2022 Wenjia Zhang, Haoran Xu, Haoyi Niu, Peng Cheng, Ming Li, Heming Zhang, Guyue Zhou, Xianyuan Zhan

In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations.

Imitation Learning

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning

1 code implementation27 Jun 2022 Haoyi Niu, Shubham Sharma, Yiwen Qiu, Ming Li, Guyue Zhou, Jianming Hu, Xianyuan Zhan

This brings up a new question: is it possible to combine learning from limited real data in offline RL and unrestricted exploration through imperfect simulators in online RL to address the drawbacks of both approaches?

Offline RL reinforcement-learning +1

Few-Shot Non-Parametric Learning with Deep Latent Variable Model

no code implementations23 Jun 2022 Zhiying Jiang, Yiqin Dai, Ji Xin, Ming Li, Jimmy Lin

Most real-world problems that machine learning algorithms are expected to solve face the situation with 1) unknown data distribution; 2) little domain-specific knowledge; and 3) datasets with limited annotation.

Classification Image Classification

Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

no code implementations22 Jun 2022 Ming Li, Jie Wu, Jinhang Cai, Jie Qin, Yuxi Ren, Xuefeng Xiao, Min Zheng, Rui Wang, Xin Pan

Recently, Synthetic data-based Instance Segmentation has become an exceedingly favorable optimization paradigm since it leverages simulation rendering and physics to generate high-quality image-annotation pairs.

Instance Segmentation Segmentation +1

Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios

no code implementations17 Jun 2022 Bang Zeng, Hongbing Suo, Yulong Wan, Ming Li

The common target speech separation directly estimate the target source, ignoring the interrelationship between different speakers at each frame.

Action Detection Activity Detection +3

Integrated Sensing and Communication with Reconfigurable Intelligent Surfaces: Opportunities, Applications, and Future Directions

no code implementations17 Jun 2022 Rang Liu, Ming Li, Honghao Luo, Qian Liu, A. Lee Swindlehurst

Integrated sensing and communication (ISAC) is emerging as a key enabler to address the growing spectrum congestion problem and satisfy increasing demands for ubiquitous sensing and communication.

Collaborative Knowledge Graph Fusion by Exploiting the Open Corpus

no code implementations15 Jun 2022 Yue Wang, Yao Wan, Lu Bai, Lixin Cui, Zhuo Xu, Ming Li, Philip S. Yu, Edwin R Hancock

To alleviate the challenges of building Knowledge Graphs (KG) from scratch, a more general task is to enrich a KG using triples from an open corpus, where the obtained triples contain noisy entities and relations.

Event Extraction Knowledge Graphs

Embedding Graphs on Grassmann Manifold

1 code implementation30 May 2022 Bingxin Zhou, Xuebin Zheng, Yu Guang Wang, Ming Li, Junbin Gao

Learning efficient graph representation is the key to favorably addressing downstream tasks on graphs, such as node or graph property prediction.

Graph Embedding Graph Property Prediction +2

MealRec: A Meal Recommendation Dataset

1 code implementation24 May 2022 Ming Li, Lin Li, Qing Xie, Jingling Yuan, Xiaohui Tao

A publicly available dataset specialising in meal recommendation research for the research community is in urgent demand.

Recommendation Systems

IRS-assisted Multi-cell Multi-band Systems: Practical Reflection Model and Joint Beamforming Design

no code implementations13 Apr 2022 Wenhao Cai, Rang Liu, Ming Li, Yang Liu, Qingqing Wu, Qian Liu

Intelligent reflecting surface (IRS) has been regarded as a promising and revolutionary technology for future wireless communication systems owing to its capability of tailoring signal propagation environment in an energy/spectrum/hardware-efficient manner.

Joint Beamforming and Reflection Design for RIS-assisted ISAC Systems

no code implementations1 Mar 2022 Rang Liu, Ming Li, A. Lee Swindlehurst

In this paper, we investigate the potential of employing reconfigurable intelligent surface (RIS) in integrated sensing and communication (ISAC) systems.

Fully-integrated multipurpose microwave frequency identification system on a single chip

no code implementations17 Feb 2022 Yuhan Yao, Yuhe Zhao, Yanxian Wei, Feng Zhou, Daigao Chen, Yuguang Zhang, Xi Xiao, Ming Li, Jianji Dong, Shaohua Yu, Xinliang Zhang

We demonstrate a fully-integrated multipurpose microwave frequency identification system on silicon-on-insulator platform.

Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels

1 code implementation11 Feb 2022 Ming Li, Yingying Fang, Zeyu Tang, Chibudom Onuorah, Jun Xia, Javier Del Ser, Simon Walsh, Guang Yang

We demonstrate the effectiveness of our model with the combination of limited labelled data and sufficient unlabelled data or weakly-labelled data.

Computed Tomography (CT) Decision Making +1

Invertible Voice Conversion

no code implementations26 Jan 2022 Zexin Cai, Ming Li

In this paper, we propose an invertible deep learning framework called INVVC for voice conversion.

Voice Conversion

pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing

1 code implementation23 Jan 2022 Jiasi Weng, Jian Weng, Gui Tang, Anjia Yang, Ming Li, Jia-Nan Liu

First, a CNN model to be tested is strategically partitioned into a private part kept locally by the model developer, and a public part outsourced to an outside server.

Privacy Preserving

CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization

no code implementations3 Jan 2022 Ming Li

Therefore, we propose Clustering and Filter of Tokens (CaFT) with Vision Transformer (ViT) backbone to solve this problem in another way.

Clustering Weakly-Supervised Object Localization

MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios

no code implementations27 Dec 2021 Xiaofeng Pan, Ming Li, Jing Zhang, Keren Yu, Luping Wang, Hong Wen, Chengjun Mao, Bo Cao

At last, we develop an Ensemble Prediction Network (EPN) which incorporates the output of FRN and DMN to make the final CVR prediction.


Joint Transmit Waveform and Passive Beamforming Design for RIS-Aided DFRC Systems

no code implementations16 Dec 2021 Rang Liu, Ming Li, Yang Liu, Qingqing Wu, Qian Liu

Reconfigurable intelligent surface (RIS) is a promising technology for 6G networks owing to its superior ability to enhance the capacity and coverage of wireless communications by smartly creating a favorable propagation environment.

Low-Latency Online Speaker Diarization with Graph-Based Label Generation

no code implementations27 Nov 2021 Yucong Zhang, Qinjian Lin, Weiqing Wang, Lin Yang, Xuyang Wang, Junjie Wang, Ming Li

To ensure the low latency in the online setting, we introduce a variant of AHC, namely chkpt-AHC, to cluster the speakers.

Clustering speaker-diarization +1

Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming

no code implementations20 Nov 2021 Yizhen Zheng, Ming Jin, Shirui Pan, Yuan-Fang Li, Hao Peng, Ming Li, Zhao Li

To overcome the aforementioned problems, we introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming, namely G-Zoom, to learn node representations by leveraging the proposed adjusted zooming scheme.

Contrastive Learning Graph Representation Learning +1

PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy

no code implementations22 Oct 2021 Xiaolan Gu, Ming Li, Li Xiong

In this paper, we develop a framework called PRECAD, which simultaneously achieves differential privacy (DP) and enhances robustness against model poisoning attacks with the help of cryptography.

Federated Learning Model Poisoning +1

The Sigma-Max System Induced from Randomness and Fuzziness

no code implementations12 Oct 2021 Wei Mei, Ming Li, Yuanzeng Cheng, Limin Liu

This paper managed to induce probability theory (sigma system) and possibility theory (max system) respectively from randomness and fuzziness, through which the premature theory of possibility is expected to be well founded.

Automatic annotation of visual deep neural networks

no code implementations8 Oct 2021 Ming Li, Chenhao Guo

Computer vision is widely used in the fields of driverless, face recognition and 3D reconstruction as a technology to help or replace human eye perception images or multidimensional data through computers.

3D Reconstruction Face Recognition

A Time-Varying Endogenous Random Coefficient Model with an Application to Production Functions

no code implementations3 Oct 2021 Ming Li

This paper proposes a random coefficient panel model where the regressors are correlated with the time-varying random coefficients in each period, a critical feature in many economic applications.

Two Birds, One Stone: Achieving both Differential Privacy and Certified Robustness for Pre-trained Classifiers via Input Perturbation

no code implementations29 Sep 2021 Pengfei Tang, Wenjie Wang, Xiaolan Gu, Jian Lou, Li Xiong, Ming Li

To solve this challenge, a reconstruction network is built before the public pre-trained classifiers to offer certified robustness and defend against adversarial examples through input perturbation.

Image Classification

A Next Basket Recommendation Reality Check

1 code implementation29 Sep 2021 Ming Li, Sami Jullien, Mozhdeh Ariannezhad, Maarten de Rijke

We propose a set of metrics that measure the repeat/explore ratio and performance of NBR models.

Next-basket recommendation

The DKU-DukeECE System for the Self-Supervision Speaker Verification Task of the 2021 VoxCeleb Speaker Recognition Challenge

no code implementations7 Sep 2021 Danwei Cai, Ming Li

Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding obtained from the previous speaker network and use the subsequent class assignments as pseudo labels to train a new DNN.

Pseudo Label Representation Learning +2

Dual-Functional Radar-Communication Waveform Design: A Symbol-Level Precoding Approach

no code implementations11 Aug 2021 Rang Liu, Ming Li, Qian Liu, A. Lee Swindlehurst

In this paper, we consider multi-input multi-output (MIMO) DFRC systems and focus on transmit beamforming designs to provide both radar sensing and multi-user communications.

Reflection and Relay Dual-Functional RIS Assisted MU-MISO Systems

no code implementations24 Jul 2021 Yanan Ma, Rang Liu, Yang Liu, Ming Li, Qian Liu

Reconfigurable intelligent surfaces (RISs) have been deemed as one of potential components of future wireless communication systems because they can adaptively manipulate the wireless propagation environment with low-cost passive devices.

A Data-Driven Method for Recognizing Automated Negotiation Strategies

no code implementations3 Jul 2021 Ming Li, Pradeep K. Murukannaiah, Catholijn M. Jonker

Our approach includes a data generation method for an agent to generate domain-independent sequences by negotiating with a variety of opponents across domains, a feature engineering method for representing negotiation data as time series with time-step features and overall features, and a hybrid (recurrent neural network-based) deep learning method for recognizing an opponent's strategy from the time series of bids.

Feature Engineering Time Series +1

BS-RIS-User Association and Beamforming Designs for RIS-aided Cellular Networks

no code implementations27 Jun 2021 Sifan Liu, Pengfei Ni, Rang Liu, Yang Liu, Ming Li, Qian Liu

During the dynamical access process, an iterative algorithm is proposed to alternatively obtain the active and passive beamforming.

A Feature Fusion-Net Using Deep Spatial Context Encoder and Nonstationary Joint Statistical Model for High Resolution SAR Image Classification

no code implementations11 May 2021 Wenkai Liang, Yan Wu, Ming Li, Peng Zhang, Yice Cao, Xin Hu

To address this problem, a novel end-to-end supervised classification method is proposed for HR SAR images by considering both spatial context and statistical features.

Image Classification

Building Bilingual and Code-Switched Voice Conversion with Limited Training Data Using Embedding Consistency Loss

1 code implementation22 Apr 2021 Yaogen Yang, Haozhe Zhang, Xiaoyi Qin, Shanshan Liang, Huahua Cui, Mingyang Xu, Ming Li

We achieve cross-lingual VC between Mandarin speech with multiple speakers and English speech with multiple speakers by applying bilingual bottleneck features.

Voice Cloning Voice Conversion

End-to-End Mandarin Tone Classification with Short Term Context Information

no code implementations12 Apr 2021 Jiyang Tang, Ming Li

In this paper, we propose an end-to-end Mandarin tone classification method from continuous speech utterances utilizing both the spectrogram and the short-term context information as the input.

General Classification

Binary Neural Network for Speaker Verification

no code implementations6 Apr 2021 Tinglong Zhu, Xiaoyi Qin, Ming Li

Although deep neural networks are successful for many tasks in the speech domain, the high computational and memory costs of deep neural networks make it difficult to directly deploy highperformance Neural Network systems on low-resource embedded devices.

Binarization Quantization +1

Grassmann Graph Embedding

no code implementations ICLR Workshop GTRL 2021 Bingxin Zhou, Xuebin Zheng, Yu Guang Wang, Ming Li, Junbin Gao

Geometric deep learning that employs the geometric and topological features of data has attracted increasing attention in deep neural networks.

Dimensionality Reduction Graph Embedding

How Framelets Enhance Graph Neural Networks

1 code implementation13 Feb 2021 Xuebin Zheng, Bingxin Zhou, Junbin Gao, Yu Guang Wang, Pietro Lio, Ming Li, Guido Montufar

The graph neural networks with the proposed framelet convolution and pooling achieve state-of-the-art performance in many node and graph prediction tasks.


First Saturation Correction in High Energy Proton-Nucleus Collisions: I. Time evolution of classical Yang-Mills fields beyond leading order

no code implementations2 Feb 2021 Ming Li, Vladimir V. Skokov

This paper is the first in a series of papers towards analytically completing the first saturation correction to physical observables in high energy proton-nucleus collisions.

High Energy Physics - Phenomenology Nuclear Theory

Intelligent reflecting surface assisted multi-cell multi-band wireless networks

no code implementations5 Jan 2021 Wenhao Cai, Rang Liu, Yang Liu, Ming Li, Qian Liu

Therefore, the practical phase shift model, which can describe the difference of IRS phase shift responses for the signals with different frequencies, should be utilized in the IRS optimization for wideband and multi-band systems.

Channel Estimation for Practical IRS-Assisted OFDM Systems

no code implementations25 Dec 2020 Wanning Yang, Hongyu Li, Ming Li, Yang Liu, Qian Liu

Different from the prior works which assume that IRS has an ideal reflection model, we perform channel estimation by considering amplitude-phase shift-frequency relationship for the response of practical IRS.

A Unified Deep Speaker Embedding Framework for Mixed-Bandwidth Speech Data

no code implementations1 Dec 2020 Weicheng Cai, Ming Li

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates.

Bandwidth Extension Image Classification

Intelligent Reflecting Surface Aided MISO Uplink Communication Network: Feasibility and Power Minimization for Perfect and Imperfect CSI

no code implementations22 Nov 2020 Yang Liu, Jun Zhao, Ming Li, Qingqing Wu

In this paper, we consider the weighted sum-power minimization under quality-of-service (QoS) constraints in the multi-user multi-input-single-output (MISO) uplink wireless network assisted by intelligent reflecting surface (IRS).

Training Wake Word Detection with Synthesized Speech Data on Confusion Words

no code implementations3 Nov 2020 Yan Jia, Zexin Cai, Murong Ma, Zeqing Zhao, Xuyang Wang, Junjie Wang, Ming Li

Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords.

Data Augmentation Keyword Spotting +1

Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond

1 code implementation ICCV 2021 Ming Li, Xinming Huang, Ziming Zhang

To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors.

Representation Learning Self-Supervised Learning +2

PointIso: Point Cloud Based Deep Learning Model for Detecting Arbitrary-Precision Peptide Features in LC-MS Map through Attention Based Segmentation

1 code implementation15 Sep 2020 Fatema Tuz Zohora, M Ziaur Rahman, Ngoc Hieu Tran, Lei Xin, Baozhen Shan, Ming Li

A promising technique of discovering disease biomarkers is to measure the relative protein abundance in multiple biofluid samples through liquid chromatography with tandem mass spectrometry (LC-MS/MS) based quantitative proteomics.

Temporal optical neurons for serial deep learning

no code implementations4 Sep 2020 Zhixing Lin, Shuqian Sun, Jose Azana, Wei Li, Ninghua Zhu, Ming Li

This concept represents a novel one-dimensional realization of artificial neural networks, enabling an efficient application of optical deep learning methods to the analysis and processing of serial data signals, while offering a new overall perspective for the temporal signal processing.

LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimation

no code implementations1 Sep 2020 Ce Zheng, Yecheng Lyu, Ming Li, Ziming Zhang

Deep learning based LiDAR odometry (LO) estimation attracts increasing research interests in the field of autonomous driving and robotics.

Autonomous Driving

Don't Change Me! User-Controllable Selective Paraphrase Generation

no code implementations EACL 2021 Mohan Zhang, Luchen Tan, Zhengkai Tu, Zihang Fu, Kun Xiong, Ming Li, Jimmy Lin

The contribution of this work is a novel data generation technique using distant supervision that allows us to start with a pretrained sequence-to-sequence model and fine-tune a paraphrase generator that exhibits this behavior, allowing user-controllable paraphrase generation.

Paraphrase Generation

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?

no code implementations19 Aug 2020 Ming Li, Sho Sonoda, Feilong Cao, Yu Guang Wang, Jiye Liang

Despite the well-known fact that a neural network is a universal approximator, in this study, we mathematically show that when hidden parameters are distributed in a bounded domain, the network may not achieve zero approximation error.

Learning Theory

Synergy between Machine/Deep Learning and Software Engineering: How Far Are We?

no code implementations12 Aug 2020 Simin Wang, LiGuo Huang, Jidong Ge, Tengfei Zhang, Haitao Feng, Ming Li, He Zhang, Vincent Ng

To improve the applicability and generalizability of research results, we analyzed what ingredients in a study would facilitate an understanding of why a ML/DL technique was selected for a specific SE problem.

Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling

no code implementations12 Aug 2020 Haiwei Wu, Lin Zhang, Lin Yang, Xuyang Wang, Jun-Jie Wang, Dong Zhang, Ming Li

This paper introduces our approaches for the Mask and Breathing Sub-Challenge in the Interspeech COMPARE Challenge 2020.

Data Augmentation

Intelligent Reflecting Surface based Passive Information Transmission: A Symbol-Level Precoding Approach

no code implementations29 Jul 2020 Rang Liu, Ming Li, Qian Liu, A. Lee Swindlehurst, Qingqing Wu

Intelligent reflecting surfaces (IRS) have been proposed as a revolutionary technology owing to its capability of adaptively reconfiguring the propagation environment in a cost-effective and hardware-efficient fashion.

Intelligent reflecting surface enhanced wideband MIMO-OFDM communications: From practical model to reflection optimization

no code implementations26 Jul 2020 Hongyu Li, Wenhao Cai, Yang Liu, Ming Li, Qian Liu, Qingqing Wu

Simulation results demonstrate that the proposed algorithm can offer significant average sum-rate enhancement compared to that achieved using the ideal IRS reflection model, which confirms the importance of the use of the practical model for the design of wideband systems.

MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning

no code implementations22 Jul 2020 Xuebin Zheng, Bingxin Zhou, Ming Li, Yu Guang Wang, Junbin Gao

In this paper, we propose a framework for graph neural networks with multiresolution Haar-like wavelets, or MathNet, with interrelated convolution and pooling strategies.

Graph Classification

Demo: iJam with Channel Randomization

no code implementations7 Jul 2020 Jordan L. Melcher, Yao Zheng, Dylan Anthony, Matthew Troglia, Yanjun Pan, Ming Li, Thomas Yang, Alvin Yang, Samson Aggelopoulos

Their secrecy rate (bit generation rate) depends heavily on the randomness of the channel, which may reduce significantly in a stable environment.

Intelligent Reflecting Surface Aided MISO Uplink Communication Network: Feasibility and Power Minimization for Perfect and Imperfect CSI

no code implementations3 Jul 2020 Yang Liu, Jun Zhao, Ming Li, Qingqing Wu

In this paper, we consider the weighted sum-power minimization under quality-of-service (QoS) constraints in the multi-user multi-input-single-output (MISO) uplink wireless network assisted by intelligent reflecting surface (IRS).

Path Integral Based Convolution and Pooling for Graph Neural Networks

1 code implementation NeurIPS 2020 Zheng Ma, Junyu Xuan, Yu Guang Wang, Ming Li, Pietro Lio

Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for classification and regression tasks on graphs.

Graph Classification Graph Regression +1

Learning to Utilize Correlated Auxiliary Noise: A Possible Quantum Advantage

no code implementations8 Jun 2020 Aida Ahmadzadegan, Petar Simidzija, Ming Li, Achim Kempf

In effect, the network learns to use the correlated auxiliary noise as an approximate key to decipher its noisy input data.

Image Classification

Practical Modeling and Beamforming for Intelligent Reflecting Surface Aided Wideband Systems

no code implementations2 Jun 2020 Wenhao Cai, Hongyu Li, Ming Li, Qian Liu

In this letter, we aim to investigate the phase-amplitude-frequency relationship of the reflected signals and propose a practical model of reflection coefficient for an IRS-aided wideband system.

Acoustic Word Embedding System for Code-Switching Query-by-example Spoken Term Detection

no code implementations24 May 2020 Murong Ma, Haiwei Wu, Xuyang Wang, Lin Yang, Jun-Jie Wang, Ming Li

In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection.

Word Embeddings

Cross-lingual Multispeaker Text-to-Speech under Limited-Data Scenario

no code implementations21 May 2020 Zexin Cai, Yaogen Yang, Ming Li

In addition, we investigate the model's performance on the cross-lingual synthesis, with and without a bilingual dataset during training.

Speech Synthesis

From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

1 code implementation10 May 2020 Zexin Cai, Chuxiong Zhang, Ming Li

The constraint is taken by an added loss related to the speaker identity, which is centralized to improve the speaker similarity between the synthesized speech and its natural reference audio.

Speaker Verification Speech Synthesis +1

Domain Aware Training for Far-field Small-footprint Keyword Spotting

no code implementations7 May 2020 Haiwei Wu, Yan Jia, Yuanfei Nie, Ming Li

In this paper, we focus on the task of small-footprint keyword spotting under the far-field scenario.

Multi-Task Learning

MV-RAN: Multiview recurrent aggregation network for echocardiographic sequences segmentation and full cardiac cycle analysis

no code implementations1 May 2020 Ming Li, Chengjia Wang, Heye Zhang, Guang Yang

In addition, for a better interpretation of pathophysiological processes, clinical decision-making and prognosis, such cardiac anatomy segmentation and quantitative analysis of various clinical indices should ideally be performed for the data covering the full cardiac cycle.

Anatomy Decision Making +1

Segatron: Segment-Aware Transformer for Language Modeling and Understanding

1 code implementation30 Apr 2020 He Bai, Peng Shi, Jimmy Lin, Yuqing Xie, Luchen Tan, Kun Xiong, Wen Gao, Ming Li

To verify this, we propose a segment-aware Transformer (Segatron), by replacing the original token position encoding with a combined position encoding of paragraph, sentence, and token.

Language Modelling Masked Language Modeling +1

Resource-Optimized Fermionic Local-Hamiltonian Simulation on Quantum Computer for Quantum Chemistry

no code implementations8 Apr 2020 Qingfeng Wang, Ming Li, Christopher Monroe, Yunseong Nam

This framework, based on perturbation theory, is capable of improving the energy estimate at each cycle of the VQE progression, by about a factor of three closer to the known ground-state energy compared to the standard VQE approach in the test-bed, classically-accessible system of the water molecule.

Quantum Physics Emerging Technologies

DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team

no code implementations23 Feb 2020 Qingjian Lin, Weicheng Cai, Lin Yang, Jun-Jie Wang, Jun Zhang, Ming Li

Our diarization system includes multiple modules, namely voice activity detection (VAD), segmentation, speaker embedding extraction, similarity scoring, clustering, resegmentation and overlap detection.

Action Detection Activity Detection +1

Wireless Federated Learning with Local Differential Privacy

no code implementations12 Feb 2020 Mohamed Seif, Ravi Tandon, Ming Li

In this paper, we study the problem of federated learning (FL) over a wireless channel, modeled by a Gaussian multiple access channel (MAC), subject to local differential privacy (LDP) constraints.

Cryptography and Security Information Theory Information Theory

Diversity-Achieving Slow-DropBlock Network for Person Re-Identification

no code implementations9 Feb 2020 Xiaofu Wu, Ben Xie, Shiliang Zhao, Suofei Zhang, Yong Xiao, Ming Li

In particular, we show that the feature diversity can be well achieved with the use of multiple dropping branches by setting individual dropping ratio for each branch.

Person Re-Identification

GhostImage: Remote Perception Attacks against Camera-based Image Classification Systems

1 code implementation21 Jan 2020 Yanmao Man, Ming Li, Ryan Gerdes

In vision-based object classification systems imaging sensors perceive the environment and machine learning is then used to detect and classify objects for decision-making purposes; e. g., to maneuver an automated vehicle around an obstacle or to raise an alarm to indicate the presence of an intruder in surveillance settings.

Autonomous Driving BIG-bench Machine Learning +4

Logical Differencing in Dyadic Network Formation Models with Nontransferable Utilities

no code implementations3 Jan 2020 Wayne Yuan Gao, Ming Li, Sheng Xu

This paper considers a semiparametric model of dyadic network formation under nontransferable utilities (NTU).

RWF-2000: An Open Large Scale Video Database for Violence Detection

1 code implementation14 Nov 2019 Ming Cheng, Kunjing Cai, Ming Li

In recent years, surveillance cameras are widely deployed in public places, and the general crime rate has been reduced significantly due to these ubiquitous devices.

Action Classification Action Recognition +1

Variational Quantum Algorithms for Dimensionality Reduction and Classification

no code implementations27 Oct 2019 Jin-Min Liang, Shu-Qian Shen, Ming Li, Lei LI

In this work, we present a quantum neighborhood preserving embedding and a quantum local discriminant embedding for dimensionality reduction and classification.

Classification Dimensionality Reduction +1

Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising

1 code implementation13 Oct 2019 Yu Gong, Hongming Shan, Yueyang Teng, Ning Tu, Ming Li, Guodong Liang, Ge Wang, Shan-Shan Wang

The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural details, and ii) a task-specific initialization based on transfer learning is developed to train PT-WGAN using trainable parameters transferred from a pretrained model, which significantly improves the training efficiency of PT-WGAN.

Image Denoising Transfer Learning

HaarPooling: Graph Pooling with Compressive Haar Basis

no code implementations25 Sep 2019 Yu Guang Wang, Ming Li, Zheng Ma, Guido Montufar, Xiaosheng Zhuang, Yanan Fan

The input of each pooling layer is transformed by the compressive Haar basis of the corresponding clustering.

Graph Classification

Haar Graph Pooling

1 code implementation ICML 2020 Yu Guang Wang, Ming Li, Zheng Ma, Guido Montufar, Xiaosheng Zhuang, Yanan Fan

Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks.

General Classification Graph Classification +1

Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data

1 code implementation ACL 2020 Hamidreza Shahidi, Ming Li, Jimmy Lin

We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively.

Question Generation <