Search Results for author: Bin Hu

Found 74 papers, 23 papers with code

糖尿病电子病历实体及关系标注语料库构建(Construction of Corpus for Entity and Relation Annotation of Diabetes Electronic Medical Records)

no code implementations CCL 2021 Yajuan Ye, Bin Hu, Kunli Zhang, Hongying Zan

“电子病历是医疗信息的重要来源, 包含大量与医疗相关的领域知识。本文从糖尿病电子病历文本入手, 在调研了国内外已有的电子病历语料库的基础上, 参考坉圲坂圲实体及关系分类, 建立了糖尿病电子病历实体及实体关系分类体系, 并制定了标注规范。利用实体及关系标注平台, 进行了实体及关系预标注及多轮人工校对工作, 形成了糖尿病电子病历实体及关系标注语料库(Diabetes Electronic Medical Record entity and Related Corpus DEMRC)。所构建的DEMRC包含8899个实体、456个实体修饰及16564个关系。对DEMRC进行一致性评价和分析, 标注结果达到了较高的一致性。针对实体识别和实体关系抽取任务, 分别采用基于迁移学习的Bi-LSTM-CRF模型和RoBERTa模型进行初步实验, 并对语料库中的各类实体及关系进行评估, 为后续糖尿病电子病历实体识别及关系抽取研究以及糖尿病知识图谱构建打下基础。”

NN-Defined Modulator: Reconfigurable and Portable Software Modulator on IoT Gateways

no code implementations14 Mar 2024 Jiazhao Wang, Wenchao Jiang, Ruofeng Liu, Bin Hu, Demin Gao, Shuai Wang

A physical-layer modulator is a vital component for an IoT gateway to map the symbols to signals.

Benchmarking Micro-action Recognition: Dataset, Methods, and Applications

1 code implementation8 Mar 2024 Dan Guo, Kun Li, Bin Hu, Yan Zhang, Meng Wang

It offers insights into the feelings and intentions of individuals and is important for human-oriented applications such as emotion recognition and psychological assessment.

Action Recognition Benchmarking +1

Model-Free $μ$-Synthesis: A Nonsmooth Optimization Perspective

no code implementations18 Feb 2024 Darioush Keivan, Xingang Guo, Peter Seiler, Geir Dullerud, Bin Hu

Built upon such a policy optimization persepctive, our paper extends these subgradient-based search methods to a model-free setting.

COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

1 code implementation13 Feb 2024 Xingang Guo, Fangxu Yu, huan zhang, Lianhui Qin, Bin Hu

Based on this connection, we adapt the Energy-based Constrained Decoding with Langevin Dynamics (COLD), a state-of-the-art, highly efficient algorithm in controllable text generation, and introduce the COLD-Attack framework which unifies and automates the search of adversarial LLM attacks under a variety of control requirements such as fluency, stealthiness, sentiment, and left-right-coherence.

Text Generation

A new method for optical steel rope non-destructive damage detection

no code implementations6 Feb 2024 Yunqing Bao, Bin Hu

Datasets containing images of steel ropes in different scenarios are created for the training and testing of both the segmentation and detection models.

Segmentation

Integration of cognitive tasks into artificial general intelligence test for large models

no code implementations4 Feb 2024 Youzhi Qu, Chen Wei, Penghui Du, Wenxin Che, Chi Zhang, Wanli Ouyang, Yatao Bian, Feiyang Xu, Bin Hu, Kai Du, Haiyan Wu, Jia Liu, Quanying Liu

During the evolution of large models, performance evaluation is necessarily performed to assess their capabilities and ensure safety before practical application.

STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition

no code implementations2 Feb 2024 Yi Chang, Zhao Ren, Zixing Zhang, Xin Jing, Kun Qian, Xi Shao, Bin Hu, Tanja Schultz, Björn W. Schuller

Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction.

Adversarial Attack Speech Emotion Recognition

Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations

no code implementations25 Jan 2024 Patricia Pauli, Aaron Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu

However, a direct application of LipSDP to the resultant residual ReLU networks is conservative and even fails in recovering the well-known fact that the MaxMin activation is 1-Lipschitz.

IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models

no code implementations25 Dec 2023 Zhihao Chen, Bin Hu, Chuang Niu, Tao Chen, Yuxin Li, Hongming Shan, Ge Wang

Second, we fine-tune the image quality captioning VLM on the CT-IQA dataset to generate quality descriptions.

Image Quality Assessment

Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents

1 code implementation22 Nov 2023 ZiHao Zhou, Bin Hu, Chenyang Zhao, Pu Zhang, Bin Liu

By incorporating the guidance from the teacher agent, the student agent can distill the prior knowledge of the LLM into its own model.

Decision Making Language Modelling +2

Expression Syntax Information Bottleneck for Math Word Problems

1 code implementation24 Oct 2023 Jing Xiong, Chengming Li, Min Yang, Xiping Hu, Bin Hu

To this end, we design an Expression Syntax Information Bottleneck method for MWP (called ESIB) based on variational information bottleneck, which extracts essential features of expression syntax tree while filtering latent-specific redundancy containing syntax-irrelevant features.

Math

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability

1 code implementation NeurIPS 2023 Haotian Xue, Alexandre Araujo, Bin Hu, Yongxin Chen

Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models.

Multi-Feature Integration for Perception-Dependent Examination-Bias Estimation

1 code implementation27 Feb 2023 Xiaoshu Chen, Xiangsheng Li, Kunliang Wei, Bin Hu, Lei Jiang, Zeqian Huang, Zhanhui Kang

Eliminating examination bias accurately is pivotal to apply click-through data to train an unbiased ranking model.

Uniform tensor clustering by jointly exploring sample affinities of various orders

no code implementations3 Feb 2023 Hongmin Cai, Fei Qi, Junyu Li, Yu Hu, Yue Zhang, Yiu-ming Cheung, Bin Hu

Conventional clustering methods based on pairwise affinity usually suffer from the concentration effect while processing huge dimensional features yet low sample sizes data, resulting in inaccuracy to encode the sample proximity and suboptimal performance in clustering.

Clustering

Learning the Kalman Filter with Fine-Grained Sample Complexity

no code implementations30 Jan 2023 Xiangyuan Zhang, Bin Hu, Tamer Başar

We develop the first end-to-end sample complexity of model-free policy gradient (PG) methods in discrete-time infinite-horizon Kalman filtering.

Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential

no code implementations20 Oct 2022 Xingang Guo, Bin Hu

In this work, we show that direct policy search is guaranteed to find the global solution of the robust $\mathcal{H}_\infty$ state-feedback control design problem.

Continuous Control

Weight-based Channel-model Matrix Framework provides a reasonable solution for EEG-based cross-dataset emotion recognition

no code implementations13 Sep 2022 Huayu Chen, Huanhuan He, Jing Zhu, Shuting Sun, Jianxiu Li, Xuexiao Shao, Junxiang Li, Xiaowei Li, Bin Hu

Cross-dataset emotion recognition as an extremely challenging task in the field of EEG-based affective computing is influenced by many factors, which makes the universal models yield unsatisfactory results.

EEG Electroencephalogram (EEG) +1

Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Łojasiewicz Functions when the Non-Convexity is Averaged-Out

no code implementations22 Jun 2022 Jun-Kun Wang, Chi-Heng Lin, Andre Wibisono, Bin Hu

An additional condition needs to be satisfied for the acceleration result of HB beyond quadratics in this work, which naturally holds when the dimension is one or, more broadly, when the Hessian is diagonal.

Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation

no code implementations20 Apr 2022 Xingang Guo, Bin Hu

In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD) learning with linear function approximation.

Multi-agent Reinforcement Learning

Audio Self-supervised Learning: A Survey

no code implementations2 Mar 2022 Shuo Liu, Adria Mallol-Ragolta, Emilia Parada-Cabeleiro, Kun Qian, Xin Jing, Alexander Kathan, Bin Hu, Bjoern W. Schuller

Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which is an expensive and time consuming task.

Self-Supervised Learning

Revisiting PGD Attacks for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control

no code implementations3 Jan 2022 Aaron Havens, Darioush Keivan, Peter Seiler, Geir Dullerud, Bin Hu

We show that the ROA analysis can be approximated as a constrained maximization problem whose goal is to find the worst-case initial condition which shifts the terminal state the most.

Model-Free $μ$ Synthesis via Adversarial Reinforcement Learning

no code implementations30 Nov 2021 Darioush Keivan, Aaron Havens, Peter Seiler, Geir Dullerud, Bin Hu

We build a connection between robust adversarial RL and $\mu$ synthesis, and develop a model-free version of the well-known $DK$-iteration for solving state-feedback $\mu$ synthesis with static $D$-scaling.

reinforcement-learning Reinforcement Learning (RL)

Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration

no code implementations15 Nov 2021 Wenhao Li, Qisen Xu, Chuyun Shen, Bin Hu, Fengping Zhu, Yuxin Li, Bo Jin, Xiangfeng Wang

Based on the confidential information, a self-adaptive reward function is designed to provide more detailed feedback, and a simulated label generation mechanism is proposed on unsupervised data to reduce over-reliance on labeled data.

Image Segmentation Interactive Segmentation +4

Major Depressive Disorder Recognition and Cognitive Analysis Based on Multi-layer Brain Functional Connectivity Networks

no code implementations2 Nov 2021 Xiaofang Sun, Xiangwei Zheng, Yonghui Xu, Lizhen Cui, Bin Hu

On the increase of major depressive disorders (MDD), many researchers paid attention to their recognition and treatment.

Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image Translation

1 code implementation6 Jul 2021 Kai Ye, Yinru Ye, Minqiang Yang, Bin Hu

To address this issue, we propose a novel architecture, termed as IEGAN, which removes the encoder of each network and introduces an encoder that is independent of other networks.

Translation Unsupervised Image-To-Image Translation

SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification

1 code implementation5 Jul 2021 Haocong Rao, Xiping Hu, Jun Cheng, Bin Hu

In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID.

Person Re-Identification Relation Network

Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification

1 code implementation6 Jun 2021 Haocong Rao, Shihao Xu, Xiping Hu, Jun Cheng, Bin Hu

To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID.

Person Re-Identification Relation

Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

no code implementations CVPR 2021 Xinggang Wang, Jiapei Feng, Bin Hu, Qi Ding, Longjin Ran, Xiaoxin Chen, Wenyu Liu

Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation.

Ranked #5 on Box-supervised Instance Segmentation on COCO test-dev (using extra training data)

Box-supervised Instance Segmentation Multi-Task Learning +5

On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions

no code implementations24 Mar 2021 Aaron Havens, Bin Hu

When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and incorporate such control-theoretic prior knowledge explicitly into the learning process.

Imitation Learning

Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity

no code implementations NeurIPS 2021 Kaiqing Zhang, Xiangyuan Zhang, Bin Hu, Tamer Başar

Direct policy search serves as one of the workhorses in modern reinforcement learning (RL), and its applications in continuous control tasks have recently attracted increasing attention.

Continuous Control Multi-agent Reinforcement Learning +2

Lensing magnification: gravitational waves from coalescing stellar-mass binary black holes

no code implementations15 Dec 2020 Xikai Shan, Bin Hu

The luminosity distance estimation error due to lensing for Einstein Telescope is about $\sigma(\hat{d})/\hat{d} \simeq 10\%$ for the luminosity distance $\gtrsim 25~\mathrm{Gpc}$.

Cosmology and Nongalactic Astrophysics High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology

On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems

no code implementations NeurIPS 2020 Kaiqing Zhang, Bin Hu, Tamer Basar

We find: i) the conventional RARL framework (Pinto et al., 2017) can learn a destabilizing policy if the initial policy does not enjoy the robust stability property against the adversary; and ii) with robustly stabilizing initializations, our proposed double-loop RARL algorithm provably converges to the global optimal cost while maintaining robust stability on-the-fly.

Continuous Control Reinforcement Learning (RL)

Policy Optimization for Markovian Jump Linear Quadratic Control: Gradient-Based Methods and Global Convergence

no code implementations24 Nov 2020 Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud

In this paper, we investigate the global convergence of gradient-based policy optimization methods for quadratic optimal control of discrete-time Markovian jump linear systems (MJLS).

Policy Gradient Methods

Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition

1 code implementation14 Nov 2020 Shihao Xu, Haocong Rao, Xiping Hu, Bin Hu

Existing approaches usually learn action representations by sequential prediction but they suffer from the inability to fully learn semantic information.

Action Recognition Clustering +5

A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification

1 code implementation5 Sep 2020 Haocong Rao, Siqi Wang, Xiping Hu, Mingkui Tan, Yi Guo, Jun Cheng, Xinwang Liu, Bin Hu

This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.

Contrastive Learning Person Re-Identification +2

Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification

1 code implementation21 Aug 2020 Haocong Rao, Siqi Wang, Xiping Hu, Mingkui Tan, Huang Da, Jun Cheng, Bin Hu

Unlike previous methods, we for the first time propose a generic gait encoding approach that can utilize unlabeled skeleton data to learn gait representations in a self-supervised manner.

Person Re-Identification

Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition

2 code implementations1 Aug 2020 Haocong Rao, Shihao Xu, Xiping Hu, Jun Cheng, Bin Hu

In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner.

Action Recognition Contrastive Learning

EDGE COVID-19: A Web Platform to generate submission-ready genomes for SARS-CoV-2 sequencing efforts

1 code implementation15 Jun 2020 Chien-Chi Lo, Migun Shakya, Karen Davenport, Mark Flynn, Adán Myers y Gutiérrez, Bin Hu, Po-E Li, Elais Player Jackson, Yan Xu, Patrick S. G. Chain

Using an intuitive web-based interface, this workflow automates SARS-CoV-2 reference-based genome assembly, variant calling, lineage determination, and provides the ability to submit the consensus sequence and necessary metadata to GenBank or GISAID.

Decision Making

A study of resting-state EEG biomarkers for depression recognition

no code implementations23 Feb 2020 Shuting Sun, Jianxiu Li, Huayu Chen, Tao Gong, Xiaowei Li, Bin Hu

Results: Functional connectivity feature PLI is superior to the linear features and nonlinear features.

EEG Electroencephalogram (EEG) +1

A Novel Decision Tree for Depression Recognition in Speech

no code implementations22 Feb 2020 Zhenyu Liu, Dongyu Wang, Lan Zhang, Bin Hu

Depression is a common mental disorder worldwide which causes a range of serious outcomes.

Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems

no code implementations10 Feb 2020 Joao Paulo Jansch-Porto, Bin Hu, Geir Dullerud

Recently, policy optimization for control purposes has received renewed attention due to the increasing interest in reinforcement learning.

Supervised feature selection with orthogonal regression and feature weighting

no code implementations9 Oct 2019 Xia Wu, Xueyuan Xu, Jianhong Liu, Hailing Wang, Bin Hu, Feiping Nie

Effective features can improve the performance of a model, which can thus help us understand the characteristics and underlying structure of complex data.

feature selection regression

Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory

no code implementations NeurIPS 2019 Bin Hu, Usman Ahmed Syed

For both the IID and Markov noise cases, we show that the evolution of some augmented versions of the mean and covariance matrix of the TD estimation error exactly follows the trajectory of a deterministic linear time-invariant (LTI) dynamical system.

Identifying Illicit Accounts in Large Scale E-payment Networks -- A Graph Representation Learning Approach

no code implementations13 Jun 2019 Da Sun Handason Tam, Wing Cheong Lau, Bin Hu, Qiu Fang Ying, Dah Ming Chiu, Hong Liu

In the context of e-payment transaction graphs, the resultant node and edge embeddings can effectively characterize the user-background as well as the financial transaction patterns of individual account holders.

Graph Embedding Graph Mining +2

Local Probabilistic Model for Bayesian Classification: a Generalized Local Classification Model

no code implementations13 Dec 2018 Chengsheng Mao, Lijuan Lu, Bin Hu

In this paper, with the insight that the distribution in a local sample space should be simpler than that in the whole sample space, a local probabilistic model established for a local region is expected much simpler and can relax the fundamental assumptions that may not be true in the whole sample space.

Classification General Classification

Local Distribution in Neighborhood for Classification

no code implementations7 Dec 2018 Chengsheng Mao, Bin Hu, Lei Chen, Philip Moore, Xiaowei Zhang

Additionally, based on the local distribution, we generate a generalized local classification form that can be effectively applied to various datasets through tuning the parameters.

Classification General Classification

Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs

no code implementations ICML 2018 Bin Hu, Stephen Wright, Laurent Lessard

Our combination of perspectives leads to a better understanding of accelerated variance-reduced stochastic methods for finite-sum problems.

Analysis of Biased Stochastic Gradient Descent Using Sequential Semidefinite Programs

no code implementations3 Nov 2017 Bin Hu, Peter Seiler, Laurent Lessard

We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors.

A Robust Accelerated Optimization Algorithm for Strongly Convex Functions

1 code implementation13 Oct 2017 Saman Cyrus, Bin Hu, Bryan Van Scoy, Laurent Lessard

This work proposes an accelerated first-order algorithm we call the Robust Momentum Method for optimizing smooth strongly convex functions.

Optimization and Control Systems and Control

A Joint Intrinsic-Extrinsic Prior Model for Retinex

no code implementations ICCV 2017 Bolun Cai, Xianming Xu, Kailing Guo, Kui Jia, Bin Hu, DaCheng Tao

We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image.

Learning Intrinsic Sparse Structures within Long Short-Term Memory

no code implementations ICLR 2018 Wei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang, Wenhan Wang, Fang Liu, Bin Hu, Yiran Chen, Hai Li

This work aims to learn structurally-sparse Long Short-Term Memory (LSTM) by reducing the sizes of basic structures within LSTM units, including input updates, gates, hidden states, cell states and outputs.

Language Modelling Model Compression +1

A Learning Based Optimal Human Robot Collaboration with Linear Temporal Logic Constraints

no code implementations31 May 2017 Bo Wu, Bin Hu, Hai Lin

This paper considers an optimal task allocation problem for human robot collaboration in human robot systems with persistent tasks.

An Interval-Based Bayesian Generative Model for Human Complex Activity Recognition

no code implementations4 Jan 2017 Li Liu, Yongzhong Yang, Lakshmi Narasimhan Govindarajan, Shu Wang, Bin Hu, Li Cheng, David S. Rosenblum

We propose in this paper an atomic action-based Bayesian model that constructs Allen's interval relation networks to characterize complex activities with structural varieties in a probabilistic generative way: By introducing latent variables from the Chinese restaurant process, our approach is able to capture all possible styles of a particular complex activity as a unique set of distributions over atomic actions and relations.

Activity Recognition

EFTCAMB/EFTCosmoMC: Numerical Notes v3.0

3 code implementations14 May 2014 Bin Hu, Marco Raveri, Noemi Frusciante, Alessandra Silvestri

EFTCAMB/EFTCosmoMC are publicly available patches to the CAMB/CosmoMC codes implementing the effective field theory approach to single scalar field dark energy and modified gravity models.

Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Theory Computational Physics

Effective Field Theory of Cosmic Acceleration: constraining dark energy with CMB data

3 code implementations5 May 2014 Marco Raveri, Bin Hu, Noemi Frusciante, Alessandra Silvestri

We introduce EFTCAMB/EFTCosmoMC as publicly available patches to the commonly used CAMB/CosmoMC codes.

Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Theory

Effective Field Theory of Cosmic Acceleration: an implementation in CAMB

3 code implementations19 Dec 2013 Bin Hu, Marco Raveri, Noemi Frusciante, Alessandra Silvestri

Second, we extract predictions for linear observables in some parametrized EFT models with a phantom-divide crossing equation of state for dark energy.

Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Theory

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