重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdaily.com每日更新更及时。

人工智能cs.AI 方向，今日共计104篇

【1】 Full-Spectrum Out-of-Distribution Detection
标题：全频谱分布外检测
作者：Jingkang Yang,Kaiyang Zhou,Ziwei Liu
机构*：Received: date Accepted: date
备注：Code and benchmarks are integrated in OpenOOD: this https URL, a unified codebase for OOD detection
链接：点击下载PDF文件

【2】 Survey of Aspect-based Sentiment Analysis Datasets
标题：基于方面的情感分析数据集综述
作者：Siva Uday Sampreeth Chebolu,Franck Dernoncourt,Nedim Lipka,Thamar Solorio
机构*：University of Houston,Adobe Research, Calhoun Rd, Houston, TX , USA , Park Ave San Jose, CA , USA
链接：点击下载PDF文件

【3】 Towards Generalizeable Semantic Product Search by Text Similarity Pre-training on Search Click Logs
标题：基于文本相似度的通用化语义产品搜索基于搜索点击日志的预训练
作者：Zheng Liu,Wei Zhang,Yan Chen,Weiyi Sun,Michael Du,Benjamin Schroeder
机构*：Wayfair LLC, Copley Place, Boston, MA USA
Journal-ref：ECNLP 2021
链接：点击下载PDF文件

【4】 The self-learning AI controller for adaptive power beaming with fiber-array laser transmitter system
标题：用于光纤阵列激光发射系统自适应功率传输的自学习人工智能控制器
作者：A. M. Vorontsov,G. A. Filimonov
机构*： School of Engineering, University of Dayton
备注：21 pages, 11 figures
链接：点击下载PDF文件

【5】 Persona-driven DominantSubmissive Map (PDSM) Generation for Tutorials
标题：角色驱动的主导服从地图(PDSM)生成教程
作者：Michael Cerny Green,Ahmed Khalifa,M Charity,Julian Togelius
机构*：New York University, New York, New York, USA, University of Malta, Msida, Malta
备注：10 pages, 7 figures, 2 tables
链接：点击下载PDF文件

【6】 Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling
标题：弥合语言模型和跨语言序列标注之间的差距
作者：Nuo Chen,Linjun Shou,Ming Gong,Jian Pei,Daxin Jiang
机构*：ADSPLAB, School of ECE, Peking University, China, STCA NLP Group, Microsoft, Beijing, School of Computing Science, Simon Fraser University
备注：15 pages
链接：点击下载PDF文件

【7】 Access to care: analysis of the geographical distribution of healthcare using Linked Open Data
标题：获得医疗服务：使用链接的开放数据分析医疗保健的地理分布
作者：Selene Baez Santamaria,Emmanouil Manousogiannis,Guusje Boomgaard,Linh P. Tran,Zoltan Szlavik,Robert-Jan Sips
机构*：Correspondence:, Vrije Universiteit Amsterdam, De, Boelelaan , HN, Amsterdam, The Netherlands, Full list of author information is, available at the end of the article, Work produced while affiliated at, MyTomorrows
链接：点击下载PDF文件

【8】 Correcting Robot Plans with Natural Language Feedback
标题：利用自然语言反馈修正机器人规划
作者：Pratyusha Sharma,Balakumar Sundaralingam,Valts Blukis,Chris Paxton,Tucker Hermans,Antonio Torralba,Jacob Andreas,Dieter Fox
机构*： NVIDIA, § MIT, University of Utah, University of Washington, Correction: By adding constraint, Stay away, from the, yellow bottle., Go from under, the bottle of, bleach., Motion Planner (with language feedback cost), Plnner Failure
备注：10 pages, 13 figures
链接：点击下载PDF文件

【9】 Towards Painless Policy Optimization for Constrained MDPs
标题：面向受限MDP的无痛策略优化
作者：Arshi Jain,Sharan Vaswani,Reza Babanezhad,Csaba Szepesvari,Doina Precup
机构*：Csaba Szepesvári, Mila, McGill University, Simon Fraser University, SAIT AI Lab, Montreal, Amii, University of Alberta, DeepMind
备注：Paper under submission. 27 pages, 12 figures
链接：点击下载PDF文件

【10】 Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding
标题：实现对话历史的端到端整合，提高口语理解能力
作者：Vishal Sunder,Samuel Thomas,Hong-Kwang J. Kuo,Jatin Ganhotra,Brian Kingsbury,Eric Fosler-Lussier
机构*： The Ohio State University, Columbus, OH, USA, IBM Research AI, Yorktown Heights, NY, USA
备注：5 pages, 1 figure
链接：点击下载PDF文件

【11】 The Principle of Least Sensing: A Privacy-Friendly Sensing Paradigm for Urban Big Data Analytics
标题：最小感知原则：一种隐私友好的城市大数据分析感知范式
作者：Leye Wang
机构*： Peking University
Journal-ref：XRDS: Crossroads, The ACM Magazine for Students, Volume 28, Issue 3, Spring 2022, pp 56-59
链接：点击下载PDF文件

【12】 SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles
标题：SF-Pate：可扩展、公平和私有的教师群体聚合
作者：Cuong Tran,Keyu Zhu,Ferdinando Fioretto,Pascal Van Hentenryck
机构*： Syracuse University, Georgia Institute of Technology
链接：点击下载PDF文件

【13】 Metaethical Perspectives on 'Benchmarking' AI Ethics
标题：“标杆”人工智能伦理的元伦理学透视
作者：Travis LaCroix,Alexandra Sasha Luccioni
机构*： there is presently no community-accepted standard for measuring the 1Department of Philosophy, Dalhousie University 2Hugging FaceE-mail address
备注：39 Pages
链接：点击下载PDF文件

【14】 The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink
标题：机器学习训练的碳足迹将停滞不前，然后缩小
作者：David Patterson,Joseph Gonzalez,Urs Hlzle,Quoc Le,Chen Liang,Lluis-Miquel Munguia,Daniel Rothchild,David So,Maud Texier,Jeff Dean
机构*： 2 University of California
链接：点击下载PDF文件

【15】 Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning
标题：基于近邻对比学习的语音序列嵌入
作者：Algayres Robin,Adel Nabli,Benoit Sagot,Emmanuel Dupoux
机构*：ENS-PSL, EHESS, CNRS, Paris ,Inria, Paris,Facebook AI Research
链接：点击下载PDF文件

【16】 Learning Object-Centered Autotelic Behaviors with Graph Neural Networks
标题：用图神经网络学习以对象为中心的自动行为
作者：Ahmed Akakzia,Olivier Sigaud
机构*：Sorbonne Universite
备注：13 pages, 9 figures, published at the workshop on Agent learning in Open-Endedness (ALOE) at ICLR 2022
链接：点击下载PDF文件

【17】 On the link between conscious function and general intelligence in humans and machines
标题：论人类和机器的意识功能和一般智力之间的联系
作者：Arthur Juliani,Kai Arulkumaran,Shuntaro Sasai,Ryota Kanai
机构*：Araya Inc. Tokyo, Japan
链接：点击下载PDF文件

【18】 ESCM$^2$: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation
标题：ESCM$^2$：用于后点击转换率估计的全空间反事实多任务模型
作者：Hao Wang,Tai-Wei Chang,Tianqiao Liu,Jianmin Huang,Zhichao Chen,Chao Yu,Ruopeng Li,Wei Chu
机构*：Ant Group, Hangzhou, China
Journal-ref：SIGIR 2022
链接：点击下载PDF文件

【19】 ReservoirComputing.jl: An Efficient and Modular Library for Reservoir Computing Models
标题：Reserve voirComputing.jl：一个高效的、模块化的水库计算模型库
作者：Francesco Martinuzzi,Chris Rackauckas,Anas Abdelrehim,Miguel D. Mahecha,Karin Mora
机构*：Remote Sensing Centre for Earth System Research, Center for Scalable Data Analytics and Artificial Intelligence, Julia Computing Inc., Massachusetts Institute of Technology, German Centre for Integrative Biodiversity Research (iDiv)
链接：点击下载PDF文件

【20】 Improved Training of Physics-Informed Neural Networks with Model Ensembles
标题：用模型集成改进物理信息神经网络的训练
作者：Katsiaryna Haitsiukevich,Alexander Ilin
机构*：Aalto University, Espoo, Finland
链接：点击下载PDF文件

【21】 Concept Drift Adaptation for CTR Prediction in Online Advertising Systems
标题：在线广告系统中用于CTR预测的概念漂移适应
作者：Congcong Liu,Yuejiang Li,Xiwei Zhao,Changping Peng,Zhangang Lin,Jingping Shao
机构*：Business Growth BU, JD.COM, Beijing, China, Tsinghua University
链接：点击下载PDF文件

【22】 Linguistic communication as (inverse) reward design
标题：作为(逆)奖励设计的语言传播
作者：Theodore R. Sumers,Robert D. Hawkins,Mark K. Ho,Thomas L. Griffiths,Dylan Hadfield-Menell
机构*：Princeton University, Princeton Neuroscience Institute, Computer Science, Psychology, EECS, CSAIL, MIT
备注：6 pages, 3 figures. Accepted at Learning from Natural Language Supervision workshop (ACL 2022)
链接：点击下载PDF文件

【23】 Semantic Exploration from Language Abstractions and Pretrained Representations
标题：从语言抽象和预先训练的表示中进行语义探索
作者：Allison C. Tam,Neil C. Rabinowitz,Andrew K. Lampinen,Nicholas A. Roy,Stephanie C. Y. Chan,DJ Strouse,Jane X. Wang,Andrea Banino,Felix Hill
机构*：DeepMind, London, UK
链接：点击下载PDF文件

【24】 Learning Trajectories of Hamiltonian Systems with Neural Networks
标题：哈密顿系统的神经网络学习轨迹
作者：Katsiaryna Haitsiukevich,Alexander Ilin
机构*：Aalto University, Espoo, Finland
链接：点击下载PDF文件

【25】 Pareto Conditioned Networks
标题：帕累托条件网络
作者：Mathieu Reymond,Eugenio Bargiacchi,Ann Nowé
机构*：Vrije Universiteit Brussel, Brussels, Belgium
备注：Accepted at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2022
链接：点击下载PDF文件

【26】 Assessing the communication gap between AI models and healthcare professionals: explainability, utility and trust in AI-driven clinical decision-making
标题：评估人工智能模型和医疗保健专业人员之间的沟通差距：人工智能驱动的临床决策中的可解释性、实用性和信任性
作者：Oskar Wysocki,Jessica Katharine Davies,Markel Vigo,Anne Caroline Armstrong,Dónal Landers,Rebecca Lee,André Freitas
机构*：Department of Computer Science, The University of Manchester, digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of Manchester, Idiap Research Institute
备注：supplementary information in the main pdf
链接：点击下载PDF文件

【27】 Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning
标题：基于强化学习的新冠肺炎多目标缓解政策的帕累托前沿研究
作者：Mathieu Reymond,Conor F. Hayes,Lander Willem,Roxana Rdulescu,Steven Abrams,Diederik M. Roijers,Enda Howley,Patrick Mannion,Niel Hens,Ann Nowé,Pieter Libin
机构*：Vrije Universiteit Brussel, Brussels, Belgium, National University of Ireland Galway, Galway, Ireland, University of Antwerp, Antwerp, Belgium, Roxana Radulescu, Hasselt University, Hasselt, Belgium, HU University of Applied Sciences Utrecht, Utrecht, the Netherlands
链接：点击下载PDF文件

【28】 gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach
标题：GTLO：一种推广的非线性多目标深度强化学习方法
作者：Johannes Dornheim
机构*： In contrast tosingle-policy MORL algorithms which use the reward vectorsJohannesDornheimiswiththeInstituteforAppliedMaterials-ComputationalMaterialsScience(IAM-CMS), KarlsruheInstituteof Technology, Karlsruhe University of Applied Sciences
链接：点击下载PDF文件

【29】 Regularization-based Pruning of Irrelevant Weights in Deep Neural Architectures
标题：深层神经网络中基于正则化的无关权重剪枝
作者：Giovanni Bonetta,Matteo Ribero,Rossella Cancelliere
机构*：Computer Science Department, University of Turin, Via Pessinetto, Turin, Italy.
链接：点击下载PDF文件

【30】 Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data
标题：自然图像的共性拯救了GAN：使用通用和无隐私的合成数据对GAN进行预训练
作者：Kyungjune Baek,Hyunjung Shim
机构*：Yonsei University
备注：CVPR 2022 accepted
链接：点击下载PDF文件

【31】 Value-based Practical Reasoning: Modal Logic + Argumentation
标题：基于价值的实践推理：模态逻辑+论证
作者：Jieting Luo,Beishui Liao,Dov Gabbay
机构*：University of Bern, Zhejiang University, King’s College London
链接：点击下载PDF文件

【32】 When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
标题：当NAS遇到树：一种高效的神经结构搜索算法
作者：Guocheng Qian,Xuanyang Zhang,Guohao Li,Chen Zhao,Yukang Chen,Xiangyu Zhang,Bernard Ghanem,Jian Sun
机构*： King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia, MEGVII Technology, The Chinese University of Hong Kong
备注：4 pages, accepted at CVPR Workshop 2022 (ECV2022)
链接：点击下载PDF文件

【33】 Zero-shot Cross-lingual Conversational Semantic Role Labeling
标题：零命中跨语言会话语义角色标注
作者：Han Wu,Haochen Tan,Kun Xu,Shuqi Liu,Lianwei Wu,Linqi Song
机构*：City University of Hong Kong Shenzhen Research Institute, Department of Computer Science, City University of Hong Kong,Huawei, National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology
备注：NAACL 2022 findings
链接：点击下载PDF文件

【34】 JORLDY: a fully customizable open source framework for reinforcement learning
标题：JORLDY：一个完全可定制的开源强化学习框架
作者：Kyushik Min,Hyunho Lee,Kwansu Shin,Taehak Lee,Hojoon Lee,Jinwon Choi,Sungho Son
机构*：Kakao Enterprise, seongnam, South Korea
备注：12 pages, 6 figures
链接：点击下载PDF文件

【35】 Methods of Informational Trends Analytics and Fake News Detection on Twitter
标题：推特上的信息趋势分析与假新闻检测方法
作者：Bohdan M. Pavlyshenko
机构*：Ivan Franko National University of Lviv, Ukraine
链接：点击下载PDF文件

【36】 Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academic Conferences
标题：知识图谱与科技学术会议的准确画像构建
作者：Runyu Yu,Zhe Xue,Ang Li
机构*：(School of Computer Science (National Pilot School of Software Engineering), Beijing University of Posts and, Telecommunications, Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing, China ,)
备注：14 pages
链接：点击下载PDF文件

【37】 Research on Cross-media Science and Technology Information Data Retrieval
标题：跨媒体科技信息数据检索研究
作者：Yang Jiang,Zhe Xue,Ang Li
机构*：（School of Computer Science (National Pilot School of Software Engineering), Beijing University of Posts and Telecommunications, Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing, China ,）
备注：7 pages
链接：点击下载PDF文件

【38】 Accurate Portraits of Scientific Resources and Knowledge Service Components
标题：准确描绘科学资源和知识服务组成部分
作者：Yue Wang,Zhe Xue,Ang Li
机构*：（School of Computer Science (National Pilot School of Software Engineering), Beijing University of Posts and Telecommunications, Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing, China ,）
备注：9 pages
链接：点击下载PDF文件

【39】 How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
标题：如何找到你的友好邻里：自我监督的图形注意设计
作者：Dongkwan Kim,Alice Oh
机构*：KAIST, Republic of Korea
备注：ICLR 2021
链接：点击下载PDF文件

【40】 Adapting BigScience Multilingual Model to Unseen Languages
标题：BigScience多语言模型在未知语言中的应用
作者：Zheng-Xin Yong,Vassilina Nikoulina
机构*：Brown University, NAVER LAB Europe
链接：点击下载PDF文件

【41】 SUMD: Super U-shaped Matrix Decomposition Convolutional neural network for Image denoising
标题：SUMD：超U形矩阵分解卷积神经网络图像去噪
作者：QiFan Li
链接：点击下载PDF文件

【42】 Fusion of Self-supervised Learned Models for MOS Prediction
标题：用于MOS预测的自监督学习模型融合
作者：Zhengdong Yang,Wangjin Zhou,Chenhui Chu,Sheng Li,Raj Dabre,Raphael Rubino,Yi Zhao
机构*：Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan, National Institute of Information and Communications Technology (NICT), Kyoto, Japan, Kuaishou Technology, Beijing, China
备注：MOS 2022 shared task system description paper
链接：点击下载PDF文件

【43】 Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification
标题：面向同质通道学习和多粒度信息探索的可见光-红外人体再识别
作者：Haojie Liu,Daoxun Xia,Wei Jiang,Chao Xu
机构*： Zhejiang University
备注：15 pages, 9figures
链接：点击下载PDF文件

【44】 Autonomous Mobile Clinics: Empowering Affordable Anywhere Anytime Healthcare Access
标题：自主移动诊所：支持随时随地提供经济实惠的医疗服务
作者：Shaoshan Liu,Yuzhang Huang,Leiyu Shi
机构*：Summary:
备注：5 pages, 1 figure
链接：点击下载PDF文件

【45】 Markov categories, causal theories, and the do-calculus
标题：马尔可夫范畴、因果理论和DO演算
作者：Yimu Yin,Jiji Zhang
链接：点击下载PDF文件

【46】 Effective Mutation Rate Adaptation through Group Elite Selection
标题：基于群体精英选择的有效突变率自适应
作者：Akarsh Kumar,Bo Liu,Risto Miikkulainen,Peter Stone
机构*：The University of Texas at Austin, Austin, Texas, USA, and Cognizant AI Labs, and Sony AI
备注：14 pages, 9 figures, GECCO 2022
链接：点击下载PDF文件

【47】 Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning
标题：基于预训练语言模型的解释图生成：基于对比学习的实证研究
作者：Swarnadeep Saha,Prateek Yadav,Mohit Bansal
机构*：UNC Chapel Hill
备注：ACL 2022 (19 pages)
链接：点击下载PDF文件

【48】 OutfitTransformer: Learning Outfit Representations for Fashion Recommendation
标题：OutfitTransformer：学习时尚推荐的服装表示法
作者：Rohan Sarkar,Navaneeth Bodla,Mariya Vasileva,Yen-Liang Lin,Anurag Beniwal,Alan Lu,Gerard Medioni
机构*：Purdue University, West Lafayette, Amazon
链接：点击下载PDF文件

【49】 SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition
标题：求救！自我中心动作再认中处理对象集的自我监督学习
作者：Victor Escorcia,Ricardo Guerrero,Xiatian Zhu,Brais Martinez
机构*：Samsung AI Center Cambridge
备注：CVPR2022 submission. Guess the decision, and email it to 1st author ;P
链接：点击下载PDF文件

【50】 DILEMMA: Self-Supervised Shape and Texture Learning with Transformers
标题：困境：使用Transformer进行自我监督的形状和纹理学习
作者：Sepehr Sameni,Simon Jenni,Paolo Favaro
机构*：Institute of Computer Science, University of Bern, Adobe Research
链接：点击下载PDF文件

【51】 Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations
标题：具有低阶和模型不可知表示的时态知识图推理
作者：Ioannis Dikeoulias,Saadullah Amin,Günter Neumann
机构*：Department of Computer Science, Department of Language Science and Technology, Saarland Informatics Campus, D,., Saarland University, Saarbrücken, Germany, German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany
备注：Accepted by RepL4NLP'22
链接：点击下载PDF文件

【52】 A Fully Polynomial Time Approximation Scheme for Fixed-Horizon Constrained Stochastic Shortest Path Problem under Local Transitions
标题：局部转移下定域约束随机最短路问题的全多项式时间逼近方法
作者：Majid Khonji
链接：点击下载PDF文件

【53】 Analysis of Power-Oriented Fault Injection Attacks on Spiking Neural Networks
标题：尖峰神经网络面向能量的故障注入攻击分析
作者：Karthikeyan Nagarajan,Junde Li,Sina Sayyah Ensan,Mohammad Nasim Imtiaz Khan,Sachhidh Kannan,Swaroop Ghosh
机构*：School of EECS, Pennsylvania State University, Univeristy Park, PA, USA, Intel Corporation, Folsom, CA, USA, Ampere Computing, Portland, OR, USA
备注：Design, Automation and Test in Europe Conference (DATE) 2022
链接：点击下载PDF文件

【54】 A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understanding
标题：多模式驾驶员行为理解的决策层融合方法比较分析
作者：Alina Roitberg,Kunyu Peng,Zdravko Marinov,Constantin Seibold,David Schneider,Rainer Stiefelhagen
机构*：Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Accepted at IV , IEEE. Personal use is permitted, but republicationredistribution requires IEEE permission. Permission from IEEE must be
备注：Accepted at Intelligent Vehicles Symposium 2022, IEEE
链接：点击下载PDF文件

【55】 TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning
标题：TOV：一种基于自监督学习的光学遥感图像理解视觉模型
作者：Chao Tao,Ji Qia,Guo Zhang,Qing Zhu,Weipeng Lu,Haifeng Li
机构*：School of Geosciences and Info-Physics, Central South University, Changsha, Hunan, PR, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote, Sensing, Wuhan University, Wuhan, Hubei, PR China, Southwest Jiaotong University
备注：38 pages, 5 figures, 8 Tables
链接：点击下载PDF文件

【56】 Data Augmentation for Biomedical Factoid Question Answering
标题：面向生物医学事实问答的数据增强
作者：Dimitris Pappas,Prodromos Malakasiotis,Ion Androutsopoulos
机构*：Department of Informatics, Athens University of Economics and Business, Greece, Institutefor Language and Speech Processing, Research Center ‘Athena’, Greece, Institute of Informatics and Telecommunications, NCSR ‘Demokritos’, Greece
链接：点击下载PDF文件

【57】 SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems
标题：分裂网：在头盔系统上设计高效分布式计算的神经体系结构
作者：Xin Dong,Barbara De Salvo,Meng Li,Chiao Liu,Zhongnan Qu,H. T. Kung,Ziyun Li
机构*：Harvard University, Meta Reality Labs, ETH Zurich, On-Sensor Inference, Aggregator Inference, Fusion, Prediction, Mul-layer, stacked camera, with AI processing, Mulple Cameras, Light-weight, ARVR processor
备注：IEEECVF Conference on Computer Vision and Pattern Recognition 2022
链接：点击下载PDF文件

【58】 An Efficient Pattern Mining Convolution Neural Network (CNN) algorithm with Grey Wolf Optimization (GWO)
标题：一种带灰狼优化的高效模式挖掘卷积神经网络(CNN)算法
作者：Aatif Jamshed,Bhawna Mallick,Rajendra Kumar Bharti
机构*：,Research scholar, Department of Computer Science and Engineering, Uttarakhand Technical, University, Dehradun, Uttarakhand, India., Senior consultant at Maverick Quality Advisory services Pvt, Ltd, Uttar Pradesh, India.
链接：点击下载PDF文件

【59】 DISK: Domain-constrained Instance Sketch for Math Word Problem Generation
标题：DISK：用于数学应用题生成的域约束实例草图
作者：Tianyang Cao,Shuang Zeng,Xiaodan Xu,Mairgup Mansur,Baobao Chang
机构*： Key Laboratory of Computational Linguistics, Peking University, MOE, China, School of Software and Microelectronics, Peking University, China, Sogou Technology Inc.
链接：点击下载PDF文件

【60】 Enhancing the Robustness, Efficiency, and Diversity of Differentiable Architecture Search
标题：增强差异化架构搜索的稳健性、效率和多样性
作者：Chao Li,Jia Ning,Han Hu,Kun He
机构*：Huazhong University of Science and Technology, Microsoft Research Asia
链接：点击下载PDF文件

【61】 FedCorr: Multi-Stage Federated Learning for Label Noise Correction
标题：FedCorr：用于标签噪声校正的多阶段联合学习
作者：Jingyi Xu,Zihan Chen,Tony Q. S. Quek,Kai Fong Ernest Chong
机构*：Tony Q.S. Quek, Singapore University of Technology and Design, National University of Singapore
备注：Accepted at IEEECVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022. 18 pages, 10 figures (including supplementary material). First two authors contributed equally. Code is available at: this https URL
链接：点击下载PDF文件

【62】 Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates
标题：我的驾驶员观察模型是不是过于自信了？用于可靠和可解释的置信度估计的输入引导校准网络
作者：Alina Roitberg,Kunyu Peng,David Schneider,Kailun Yang,Marios Koulakis,Manuel Martinez,Rainer Stiefelhagen
机构*：Authors are with Institute for Anthropomatics and Robotics, KarlsruheInstitute of Technology
链接：点击下载PDF文件

【63】 "That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks
作者：Edoardo Mosca,Shreyash Agarwal,Javier Rando-Ramirez,Georg Groh
机构*：TU Munich, Department of Informatics, Germany, ETH Zurich, Department of Computer Science, Switzerland
备注：ACL 2022
链接：点击下载PDF文件

【64】 Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching
标题：基于强化学习的电网调度中长期可再生能源预测的置信度估计Transformer
作者：Xinhang Li,Zihao Li,Nan Yang,Zheng Yuan,Qinwen Wang,Yiying Yang,Yupeng Huang,Xuri Song,Lei Li,Lin Zhang
链接：点击下载PDF文件

【65】 Decay No More: A Persistent Twitter Dataset for Learning Social Meaning
标题：不再衰败：学习社交意义的持久Twitter数据集
作者：Chiyu Zhang,Muhammad Abdul-Mageed,El Moatez Billah Nagoudi
机构*：Deep Learning & Natural Language Processing Group, The University of British Columbia
备注：Under review. arXiv admin note: text overlap with arXiv:2108.00356
链接：点击下载PDF文件

【66】 Self-Supervised Video Representation Learning with Motion-Contrastive Perception
标题：基于运动对比感知的自监督视频表征学习
作者：Jinyu Liu,Ying Cheng,Yuejie Zhang,Rui-Wei Zhao,Rui Feng
机构*：School of Computer Science, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, Academy for Engineering and Technology, Fudan University, China
备注：Accepted by ICME 2022
链接：点击下载PDF文件

【67】 Towards efficient representation identification in supervised learning
标题：有监督学习中的有效表征识别
作者：Kartik Ahuja,Divyat Mahajan,Vasilis Syrgkanis,Ioannis Mitliagkas
机构*：Mila - Quebec AI Institute, Universite de Montreal., Microsoft Research, New England, Editors: Bernhard Sch¨olkopf, Caroline Uhler and Kun Zhang
备注：Proceedings of the First Conference on Causal Learning and Reasoning
链接：点击下载PDF文件

【68】 Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention
标题：基于潜在视觉语义过滤注意的深层卷积神经网络解释
作者：Yu Yang,Seungbae Kim,Jungseock Joo
机构*：University of California, Los Angeles
备注：To appear in CVPR 2022 (oral presentation)
链接：点击下载PDF文件

【69】 Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering
标题：用于开放领域问答的QA记忆扩充预训练语言模型
作者：Wenhu Chen,Pat Verga,Michiel de Jong,John Wieting,William Cohen
机构*：Google Research, University of Southern California
链接：点击下载PDF文件

【70】 Self-Labeling Refinement for Robust Representation Learning with Bootstrap Your Own Latent
标题：基于Bootstrap潜在学习的自标记精化方法
作者：Siddhant Garg,Dhruval Jain
链接：点击下载PDF文件

【71】 Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learning
标题：基于多任务学习的C-Spine影像报告中病理组织的高效提取
作者：Arijit Sehanobish,Nathaniel Brown,Ishita Daga,Jayashri Pawar,Danielle Torres,Anasuya Das,Murray Becker,Richard Herzog,Benjamin Odry,Ron Vianu
机构*：Covera Health, NYC, New York, danielle.torres,anasuya.das,murray.becker,rherzog
备注：Accepted at 6th International Workshop on Health Intelligence, AAAI-2022. To appear in as a book chapter published by Springer in Studies in Computational Intelligence
链接：点击下载PDF文件

【72】 Extending the Scope of Out-of-Domain: Examining QA models in multiple subdomains
标题：扩展域外的范围：检查多个子域中的QA模型
作者：Chenyang Lyu,Jennifer Foster,Yvette Graham
机构*： School of Computing, Dublin City University, Dublin, Ireland, School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland
备注：14 pages, 6 figures, 29 tables, to appear at ACL 2022 Workshop on Insights from Negative Results in NLP, code available in this https URL
链接：点击下载PDF文件

【73】 Applying machine learning to predict behavior of bus transport in Warsaw, Poland
标题：应用机器学习预测波兰华沙公交出行行为
作者：ukasz Pays,Maria Ganzha,Marcin Paprzycki
机构*：Paprzycki,[,,,,], Warsaw University of Technology, Warsaw, Poland, Systems Research Institute Polish Academy of Sciences
备注：18 pages, full version of paper for ICCS conference
链接：点击下载PDF文件

【74】 Efficient Representation Learning of Subgraphs by Subgraph-To-Node Translation
标题：基于子图到节点转换的子图表示学习
作者：Dongkwan Kim,Alice Oh
机构*：School of Computing, KAIST
备注：ICLR 2022 Workshop GTRL
链接：点击下载PDF文件

【75】 Why did I fail? A Causal-based Method to Find Explanations for Robot Failures
标题：为什么我会失败？一种基于因果关系的机器人故障解释方法
作者：Maximilian Diehl,Karinne Ramirez-Amaro
机构*： Chalmers University of Technology
备注：submitted to IEEE Robotics and Automation Letters (February 2022)
链接：点击下载PDF文件

【76】 FoundationLayerNorm: Scaling BERT and GPT to 1,000 Layers
标题：FoundationLayerNorm：将BERT和GPT扩展到1,000层
作者：Dezhou Shen
备注：7 pages, 5 tables
链接：点击下载PDF文件

【77】 Adaptive Differential Filters for Fast and Communication-Efficient Federated Learning
标题：用于快速高效通信的联邦学习的自适应差分滤波
作者：Daniel Becking,Heiner Kirchhoffer,Gerhard Tech,Paul Haase,Karsten Müller,Heiko Schwarz,Wojciech Samek
机构*：Karsten M¨uller, Fraunhofer Heinrich Hertz Institute (HHI), Berlin
备注：CVPR 2022 FedVision Workshop (CVPRW), 12 pages, 5 figures, 2 tables, supplementary material
链接：点击下载PDF文件

【78】 Unbiased Directed Object Attention Graph for Object Navigation
标题：用于对象导航的无偏有向对象注意图
作者：Ronghao Dang,Zhuofan Shi,Liuyi Wang,Zongtao He,Chengju Liu,Qijun Chen
机构*：Tongji University, Shanghai, China, ETH Zürich, Zürich, Switzerland
备注：13 pages, ready to ACM Mutimedia, under review
链接：点击下载PDF文件

【79】 PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
标题：PSP：用于Few-Shot摘要的预训练软提示
作者：Xiaochen Liu,Yu Bai,Jiawei Li,Yinan Hu,Yang Gao
机构*：Beijing Institute of Technology
备注：12 pages
链接：点击下载PDF文件

【80】 Divergence-aware Federated Self-Supervised Learning
标题：发散性感知的联合自监督学习
作者：Weiming Zhuang,Yonggang Wen,Shuai Zhang
机构*：S-Lab, NTU, Singapore ,NTU, Singapore ,SenseTime Research
备注：ICLR'22
链接：点击下载PDF文件

【81】 Federated Unsupervised Domain Adaptation for Face Recognition
标题：用于人脸识别的联合无监督区域自适应
作者：Weiming Zhuang,Xin Gan,Yonggang Wen,Xuesen Zhang,Shuai Zhang,Shuai Yi
机构*：S-Lab, NTU, Singapore ,NTU, Singapore ,SenseTime Research
备注：ICME'22. arXiv admin note: substantial text overlap with arXiv:2105.07606
链接：点击下载PDF文件

【82】 Channel Pruning In Quantization-aware Training: An Adaptive Projection-gradient Descent-shrinkage-splitting Method
标题：量化感知训练中的信道剪枝：一种自适应投影梯度下降收缩分裂方法
作者：Zhijian Li,Jack Xin
机构*：University of California, Irvine, Department of Mathematics
链接：点击下载PDF文件

【83】 A Siren Song of Open Source Reproducibility
标题：开放源码可重复性的警歌
作者：Edward Raff,Andrew L. Farris
机构*：Booz Allen Hamilton, University of Maryland, Baltimore County
备注：To be presented at the ML Evaluation Standards Workshop at ICLR 2022
链接：点击下载PDF文件

【84】 Should we tweet this? Generative response modeling for predicting reception of public health messaging on Twitter
标题：我们应该把这个发到推特上吗？用于预测Twitter上公共卫生消息接收的生成性响应建模
作者：Abraham Sanders,Debjani Ray-Majumder,John S. Erickson,Kristin P. Bennett
机构*：Rensselaer Polytechnic Institute, Troy, New York, USA
备注：Accepted at ACM WebSci 2022
链接：点击下载PDF文件

【85】 On the Importance of Karaka Framework in Multi-modal Grounding
标题：论卡拉卡框架在多式联运接地中的重要性
作者：Sai Kiran Gorthi,Radhika Mamidi
机构*：IIIT Hyderabad
链接：点击下载PDF文件

【86】 Fuzzy temporal convolutional neural networks in P300-based Brain-computer interface for smart home interaction
标题：基于P300的智能家居交互脑机接口中的模糊时间卷积神经网络
作者：Christian Flores Vega,Jonathan Quevedo,Elmer Escandón,Mehrin Kiani,Weiping Ding,Javier Andreu-Perez
机构*：Universidad de Ingeniera y Tecnologa - UTEC, Lima, Peru, University of Campinas, Sao Paulo, Brazil, University of Essex, Colchester, United Kingdom, Nantong University, Jiangsu, China, University of Jaen, Jaen, Spain
Journal-ref：Applied Soft Computing 117 (2022) 108359
链接：点击下载PDF文件

【8】 Iterative Depth-First Search for Fully Observable Non-Deterministic Planning
标题：完全可观测不确定性规划的迭代深度优先搜索
作者：Ramon Fraga Pereira,André G. Pereira,Frederico Messa,Giuseppe De Giacomo
机构*：Sapienza University of Rome, Rome, Italy, Federal University of Rio Grande do Sul, Porto Alegre, Brazil
链接：点击下载PDF文件

【88】 Grounding Hindsight Instructions in Multi-Goal Reinforcement Learning for Robotics
标题：机器人多目标强化学习中的后见之明指导
作者：Frank Rder,Manfred Eppe,Stefan Wermter
机构*：Institute for Data Science Foundations, Hamburg University of Technology, Hamburg, Germany, Knowledge Technology, University of Hamburg
备注：Preprint ICDL 2022
链接：点击下载PDF文件

【89】 MMTAfrica: Multilingual Machine Translation for African Languages
标题：MMTAfrica：面向非洲语言的多语言机器翻译
作者：Chris C. Emezue,Bonaventure F. P. Dossou
机构*：Technical University of Munich, Mila Quebec AI Institute, Masakhane, Jacobs University Bremen
Journal-ref：Proceedings of the Sixth Conference on Machine Translation (2021) 398-411, Association for Computational Linguistics
链接：点击下载PDF文件

【90】 Preliminary Results on Using Abstract AND-OR Graphs for Generalized Solving of Stochastic Shortest Path Problems
标题：抽象与或图用于随机最短路问题广义求解的初步结果
作者：Rushang Karia,Rashmeet Kaur Nayyar,Siddharth Srivastava
机构*：School of Computing and Augmented Intelligence, Arizona State University, U.S.A.
链接：点击下载PDF文件

【91】 Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models
标题：在预先训练和微调的语言模型中理解大规模语篇结构
作者：Patrick Huber,Giuseppe Carenini
机构*：Department of Computer Science, University of British Columbia, Vancouver, BC, Canada, V,T ,Z
Journal-ref：In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
链接：点击下载PDF文件

【92】 On Improving Cross-dataset Generalization of Deepfake Detectors
标题：关于改进深伪检测器交叉数据集泛化的研究
作者：Aakash Varma Nadimpalli,Ajita Rattani
机构*：School of Computing, Wichita State University, Wichita, USA
备注：2022 Conference on Computer Vision and Pattern Recognition Workshops | New Orleans, Louisiana
链接：点击下载PDF文件

【93】 Evaluating the Adversarial Robustness for Fourier Neural Operators
标题：傅立叶神经算子的对抗性评价
作者：Abolaji D. Adesoji,Pin-Yu Chen
机构*：Department of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute (RPI), Troy, NY , USA, IBM Research, Yorktown, NY , USA
备注：Accepted to Workshop on Socially Responsible Machine Learning (SRML), co-located with ICLR 2022
链接：点击下载PDF文件

【94】 Interpretable AI for policy-making in pandemics
标题：可解释的人工智能在流行病中的政策制定
作者：Leonardo Lucio Custode,Giovanni Iacca
机构*：University of Trento, Trento, Italy
备注：6 pages, 3 figures, submitted to GECCO 2022
链接：点击下载PDF文件

【95】 Exploiting complex pattern features for interactive pattern mining
标题：利用复杂模式特征进行交互式模式挖掘
作者：Arnold Hien,Samir Loudni,Noureddine Aribi,Abdelkader Ouali,Albrecht Zimmermann
机构*：CNRS-UMR GREYC, Normandie Univ., UNICAEN, Caen, TASC (LS,N-CNRS), IMT Atlantique, rue Alfred Kastler, Nantes, France., LITIO, University of Oran, Oran, Algeria., These authors contributed equally to this work.
链接：点击下载PDF文件

【96】 Characterizing and Understanding the Behavior of Quantized Models for Reliable Deployment
标题：描述和了解量化模型的行为，以实现可靠部署
作者：Qiang Hu,Yuejun Guo,Maxime Cordy,Xiaofei Xie,Wei Ma,Mike Papadakis,Yves Le Traon
机构*：SnT, University of Luxembourg, Singapore Management University
备注：12 pages
链接：点击下载PDF文件

【97】 Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization
标题：采用精确激活裁剪和自适应批归一化的无数据量化
作者：Yefei He,Luoming Zhang,Weijia Wu,Hong Zhou
备注：submitted to ICML2022
链接：点击下载PDF文件

【98】 Structure-aware Protein Self-supervised Learning
标题：基于结构感知的蛋白质自监督学习
作者：Can Chen,Jingbo Zhou,Fan Wang,Xue Liu,Dejing Dou
机构*：McGill University ,Baidu Research ,Baidu Inc.
备注：7 pages and 4 figures
链接：点击下载PDF文件

【99】 CXR-FL: Deep Learning-based Chest X-ray Image Analysis Using Federated Learning
标题：CXR-FL：基于深度学习的联合学习胸片图像分析
作者：Filip lazyk,Przemysaw Jabecki,Aneta Lisowska,Maciej Malawski,Szymon Potka
机构*： Sano Centre for Computational Medicine, Krakow, Poland, AGH University of Science and Technology, Krakow, Poland, Warsaw University of Technology, Warsaw, Poland
备注：Accepted at International Conference on Computational Science (ICCS) 2022, London
链接：点击下载PDF文件

【100】 Artificial Intelligence Software Structured to Simulate Human Working Memory, Mental Imagery, and Mental Continuity
标题：人工智能软件被构建为模拟人类的工作记忆、心理意象和心理连续性
作者：Jared Edward Reser
机构*：Program Peace LLC, + ,-,-
链接：点击下载PDF文件

【101】 A Spiking Neural Network based on Neural Manifold for Augmenting Intracortical Brain-Computer Interface Data
标题：一种基于神经流形的增强皮层内脑机接口数据的尖峰神经网络
作者：Shengjie Zheng,Wenyi Li,Lang Qian,Chenggang He,Xiaojian Li
机构*： University of Chinese Academy of Sciences, Beijing, China, Brain Cognition and Brain Disease Institute (BCBDI), Shenzhen-Hong Kong Institute of, Brain Science, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
备注：12pages , 9 figures
链接：点击下载PDF文件

【102】 Comparative Survey of Multigraph Integration Methods for Holistic Brain Connectivity Mapping
标题：整体脑连接图多图集成方法的比较研
作者：Nada Chaari,Hatice Camgoz Akdag,Islem Rekik
机构*：BASIRA lab, Istanbul Technical University, Istanbul Technical University, Istanbul, Turkey, School of Science and Engineering, Computing, University of Dundee, UK
链接：点击下载PDF文件

【103】 A Novel Channel Identification Architecture for mmWave Systems Based on Eigen Features
标题：一种新的基于特征特征的毫米波系统信道识别结构
作者：Yibin Zhang,Jinlong Sun,Guan Gui,Haris Gacanin,Fumiyuki Adachi
机构*：College of Telecommunications and Information Engineering, NJUPT, Nanjing, China, Institute for Communication Technologies and Embedded Systems, RWTH Aachen University, Aachen, Germany
链接：点击下载PDF文件

【104】 Feature-enhanced Adversarial Semi-supervised Semantic Segmentation Network for Pulmonary Embolism Annotation
标题：特征增强型对抗性半监督语义分割网络肺栓塞标注
作者：Ting-Wei Cheng,Jerry Chang,Ching-Chun Huang,Chin Kuo,Yun-Chien Cheng
机构*：Chien Chenga, , a Department of Mechanical Engineering, College of Engineering, National Yang Ming Chiao Tung, b Department of Computer Science, College of Computer Science, National Yang Ming Chiao Tung
链接：点击下载PDF文件
机器翻译，仅供参考

重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdaily.com每日更新更及时。