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72篇
【1】 Implementation of an Automated Learning System for Non-experts
标题：一种面向非专家的自动学习系统的实现
作者：Phoenix X. Huang,Zhiwei Zhao,Chao Liu,Jingyi Liu,Wenze Hu,Xiaoyu Wang
机构*：Lighthouse
链接：点击下载PDF文件
【2】 A Systematic Review on Interactive Virtual Reality Laboratory
标题：交互式虚拟现实实验室的系统评价
作者：Fozlur Rahman,Marium Sana Mim,Feekra Baset Baishakhi,Mahmudul Hasan,Md. Kishor Morol
机构*：Department of Computer Science and Engineering, American International University-Bangladesh, Dhaka, Bangladesh, th Md. Kishor Morol
备注：10 pages, 7 figures, 7 tables
链接：点击下载PDF文件
【3】 Deep Reinforcement Learning Aided Platoon Control Relying on V2X Information
标题：基于V2X信息的深度强化学习辅助排控
作者：Lei Lei,Tong Liu,Kan Zheng,Lajos Hanzo
链接：点击下载PDF文件
【4】 Adaptive Learning with Artificial Barriers Yielding Nash Equilibria in General Games
标题：具有人工障碍的自适应学习在一般博弈中产生纳什均衡
作者：Ismail Hassan,Anis Yazidi,B. John Oommen
机构*： School of Computer Science, Carleton University, This author is also an Adjunct Professor with the University of Agderin Grimstad
链接：点击下载PDF文件
【5】 Evaluating Prompts Across Multiple Choice Tasks In a Zero-Shot Setting
标题：在Zero-Shot设置下评估多项选择任务中的提示
作者：Gabriel Orlanski
备注：4 pages, 4 figures
链接：点击下载PDF文件
【6】 On Decoding Strategies for Neural Text Generators
标题：神经文本生成器的译码策略研究
作者：Gian Wiher,Clara Meister,Ryan Cotterell
机构*：ETH Zürich
链接：点击下载PDF文件
【7】 Towards Everyday Virtual Reality through Eye Tracking
标题：通过眼球跟踪走向日常虚拟现实
作者：Efe Bozkir
机构*：aus Kar¸sıyaka, Türkei, Tübingen, arXiv:,.,v, [cs.HC] , Mar
备注：PhD Thesis, University of T"ubingen
链接：点击下载PDF文件
【8】 Forecasting with Economic News
标题：用经济新闻进行预测
作者：Luca Barbaglia,Sergio Consoli,Sebastiano Manzan
机构*：a Joint Research Centre, European Commission, b Zicklin School of Business, Baruch College
备注：46 pages, 11 figures, to be published in Journal of Business & Economic Statistics
链接：点击下载PDF文件
【9】 EnvEdit: Environment Editing for Vision-and-Language Navigation
标题：EnvEdit：视觉和语言导航的环境编辑
作者：Jialu Li,Hao Tan,Mohit Bansal
机构*：UNC Chapel Hill
备注：CVPR 2022 (17 pages)
链接：点击下载PDF文件
【10】 Synthesis and Execution of Communicative Robotic Movements with Generative Adversarial Networks
标题：基于产生式对抗性网络的通信机器人运动综合与执行
作者：Linda Lastrico,Luca Garello,Alessandra Sciutti,Nicoletta Noceti,Fulvio Mastrogiovanni,Francesco Rea
机构*：∥MaLGa-DIBRIS, University of Genoa, §Robotics, Brain and Cognitive Science Department (RBCS), Italian Institute of Technology, Genoa, Italy, †Department of Informatics, Bioengineering, Robotics, and Systems Engineering (DIBRIS), University of Genoa, Italy
备注：Submitted to the Special Issue on Emerging Topics on Development and Learning, IEEE TCDS. Unpublished, review process ongoing. Luca Garello and Linda Lastrico contributed equally to this work, hence they share the first name
链接：点击下载PDF文件
【11】 Cross-Media Scientific Research Achievements Retrieval Based on Deep Language Model
标题：基于深层语言模型的跨媒体科研成果检索
作者：Benzhi Wang,Meiyu Liang,Feifei Kou,Mingying Xu
机构*：（School of Computer Science, Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, Beijing University of, Posts and Telecommunications, Beijing , China）
链接：点击下载PDF文件
【12】 Deep Multi-modal Fusion of Image and Non-image Data in Disease Diagnosis and Prognosis: A Review
标题：图像和非图像数据的深度多模式融合在疾病诊断和预后中的研究进展
作者：Can Cui,Haichun Yang,Yaohong Wang,Shilin Zhao,Zuhayr Asad,Lori A. Coburn,Keith T. Wilson,Bennett A. Landman,Yuankai Huo
机构*：Department of Computer Science, Vanderbilt University, Nashville, TN , USA, b Department of Pathology, Microbiology and Immunology, Vanderbilt University Medical Center, c Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN , USA
链接：点击下载PDF文件
【13】 Core Risk Minimization using Salient ImageNet
标题：使用Salient ImageNet将核心风险降至最低
作者：Sahil Singla,Mazda Moayeri,Soheil Feizi
机构*： features that are notEqual contribution 1University of Maryland
链接：点击下载PDF文件
【14】 Wildfire risk forecast: An optimizable fire danger index
标题：野火风险预测：一种可优化的火灾危险指数
作者：Eduardo Rodrigues,Bianca Zadrozny,Campbell Watson
机构*：IBM Research, Brazil, Campbell D. Watson, IBM Research, USA
备注：6 pages, 5 figures
链接：点击下载PDF文件
【15】 ME-CapsNet: A Multi-Enhanced Capsule Networks with Routing Mechanism
标题：ME-CapsNet：一种具有路由机制的多增强型胶囊网络
作者：Jerrin Bright,Suryaprakash R,Arockia Selvakumar Arockia Doss
机构*：School of Mechanical Engineering, Vellore Institute of Technology, Chennai, India, †These Authors Contributed Equally To This Work
备注：6 pages, 4 figures
链接：点击下载PDF文件
【16】 Graph Neural Networks are Dynamic Programmers
标题：图形神经网络是动态程序员
作者：Andrew Dudzik,Petar Veličković
机构*：DeepMind, Petar Veliˇckovi´c∗
备注：9 pages, 1 figure. To appear at the ICLR 2022 GroundedML and GTRL Workshops. Work in progress -- comments welcome!
链接：点击下载PDF文件
【17】 Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search
标题：电子商务搜索中点击率预测的用户情景页面反馈建模
作者：Zhifang Fan,Dan Ou,Yulong Gu,Bairan Fu,Xiang Li,Wentian Bao,Xin-Yu Dai,Xiaoyi Zeng,Tao Zhuang,Qingwen Liu
机构*：Alibaba Group, China, Nanjing University, China
链接：点击下载PDF文件
【18】 BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information
标题：BARC：通过利用品种信息学习从图像中回归3D狗的形状
作者：Nadine Rueegg,Silvia Zuffi,Konrad Schindler,Michael J. Black
机构*：ETH Z¨urich, Switzerland, Max Planck Institute for Intelligent Systems, T¨ubingen, Germany, IMATI-CNR, Milan, Italy
备注：accepted for publication at CVPR 2022
链接：点击下载PDF文件
【19】 Treatment Learning Transformer for Noisy Image Classification
标题：用于含噪图像分类的治疗学习转换器
作者：Chao-Han Huck Yang,I-Te Danny Hung,Yi-Chieh Liu,Pin-Yu Chen
机构*：Georgia Institute of Technology, Columbia University, IBM Research
备注：Preprint. The first version was finished in May 2018
链接：点击下载PDF文件
【20】 Collision-Free Navigation using Evolutionary Symmetrical Neural Networks
标题：基于进化对称神经网络的无碰撞导航
作者：Hesham M. Eraqi,Mena Nagiub,Peter Sidra
机构*：Department of Computer Science, The American University in Cairo, New Cairo, Egypt, Valeo Schalter und Sensoren GmbH, Bietigheim-Bissingen, Germany
Journal-ref：2022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS 2022), Larnaca, Cyprus
链接：点击下载PDF文件
【21】 Rich Feature Construction for the Optimization-Generalization Dilemma
标题：优化-泛化困境的丰富特征构造
作者：Jianyu Zhang,David Lopez-Paz,Léon Bottou
机构*： It also changes nature when 1New York University
备注：15 pages
链接：点击下载PDF文件
【22】 Human Response to an AI-Based Decision Support System: A User Study on the Effects of Accuracy and Bias
标题：人类对基于人工智能的决策支持系统的反应：一项关于准确性和偏差影响的用户研究
作者：David Solans,Andrea Beretta,Manuel Portela,Carlos Castillo,Anna Monreale
机构*：University Pompeu Fabra, Barcelona, Spain, National Research Council, Pisa, Italy, University of Pisa, Pisa, Italy
链接：点击下载PDF文件
【23】 Explaining random forest prediction through diverse rulesets
标题：用不同的规则集解释随机森林预测
作者：Klest Dedja,Felipe Kenji Nakano,Konstantinos Pliakos,Celine Vens
机构*：Department of Primary Care, Kortrijk, KU Leuven, Itec, imec research group, Kortrijk, KU Leuven, Department of Management, Strategy, and Innovation, KU Leuven
链接：点击下载PDF文件
【24】 Improving Contrastive Learning with Model Augmentation
标题：用模型增强改进对比学习
作者：Zhiwei Liu,Yongjun Chen,Jia Li,Man Luo,Philip S. Yu,Caiming Xiong
机构*：Salesforce Research, CA, USA
备注：Preprint. Still under reivew
链接：点击下载PDF文件
【25】 Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
标题：深度学习中突破后门攻击防御的特洛伊木马训练
作者：Arezoo Rajabi,Bhaskar Ramasubramanian,Radha Poovendran
机构*： Department of Electrical and Computer Engi-neering, University of Washington
备注：Submitted to conference
链接：点击下载PDF文件
【26】 Analysis of OODA Loop based on Adversarial for Complex Game Environments
标题：复杂博弈环境下基于对抗性的Ooda环路分析
作者：Xiangri Lu,Hongbin Ma,Zhanqing Wang
机构*：State Key Laboratory of Intelligent Decision and Control for Complex Systems, Automated Institute, Beijing Institute of Technology, Beijing, China‡
链接：点击下载PDF文件
【27】 Deep Learning for Encrypted Traffic Classification and Unknown Data Detection
标题：基于深度学习的加密流量分类和未知数据检测
作者：Madushi H. Pathmaperuma,Yogachandran Rahulamathavan,Safak Dogan,Ahmet M. Kondoz,Rongxing Lu
链接：点击下载PDF文件
【28】 Powerful Physical Adversarial Examples Against Practical Face Recognition Systems
标题：针对实用人脸识别系统的强大物理对抗实例
作者：Inderjeet Singh,Toshinori Araki,Kazuya Kakizaki
机构*：NEC Corporation, Kawasaki, Kanagawa, Japan
备注：Accepted at IEEECVF WACV 2022 MAP
链接：点击下载PDF文件
【29】 Quality Assurance of Generative Dialog Models in an Evolving Conversational Agent Used for Swedish Language Practice
标题：用于瑞典语实践的进化会话Agent中生成对话模型的质量保证
作者：Markus Borg,Johan Bengtsson,Harald Österling,Alexander Hagelborn,Isabella Gagner,Piotr Tomaszewski
机构*：RISE Research Institutes of Sweden, Lund, Sweden, Lund University, NordAxon AB, Malmö, Sweden
备注：Accepted for publication in the Proc. of the 1st International Conference on AI Engineering, 2022
链接：点击下载PDF文件
【30】 AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement
标题：AutoCoMet：通过协同调节整形强化的智能神经结构搜索
作者：Mayukh Das,Brijraj Singh,Harsh Kanti Chheda,Pawan Sharma,Pradeep NS
机构*：∗Microsoft Research; †Sony Research; ‡JP Morgan & Chase; §Microsoft; ¶Samsung R&D Institute, Bangalore
备注：ICPR 2022
链接：点击下载PDF文件
【31】 Learning to act: a Reinforcement Learning approach to recommend the best next activities
标题：学会行动：一种推荐最佳下一步活动的强化学习方法
作者：Stefano Branchi,Chiara Di Francescomarino,Chiara Ghidini,David Massimo,Francesco Ricci,Massimiliano Ronzani
机构*： Fondazione Bruno Kessler, Trento, Italy, Free University of Bozen-Bolzano, Bolzano, Italy
备注：16 pages, 3 figures
链接：点击下载PDF文件
【32】 ReIL: A Framework for Reinforced Intervention-based Imitation Learning
标题：REIL：一种基于强化干预的模仿学习框架
作者：Rom Parnichkun,Matthew N. Dailey,Atsushi Yamashita
机构*：asia)Atsushi Yamashita is with the Department of Precision Engineering, TheUniversity of Tokyo
链接：点击下载PDF文件
【33】 A Principle-based Ethical Assurance Argument for AI and Autonomous Systems
标题：基于原则的人工智能和自治系统的伦理保障论证
作者：Zoe Porter,Ibrahim Habli,John McDermid
机构*： Department of Computer Science, University of York
链接：点击下载PDF文件
【34】 Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
标题：任务边界模糊的污染数据流上的在线持续学习
作者：Jihwan Bang,Hyunseo Koh,Seulki Park,Hwanjun Song,Jung-Woo Ha,Jonghyun Choi
机构*：NAVER CLOVA, NAVER AI Lab, GIST, Seoul National Univ., Yonsei Univ.
备注：Accepted paper at CVPR 2022
链接：点击下载PDF文件
【35】 Balanced Multimodal Learning via On-the-fly Gradient Modulation
标题：基于即时梯度调制的平衡多模式学习
作者：Xiaokang Peng,Yake Wei,Andong Deng,Dong Wang,Di Hu
机构*：Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, Shanghai Jiao Tong University, Shanghai, Shanghai Artificial Intelligence Laboratory, Shanghai
备注：Accepted by CVPR 2022 (ORAL)
链接：点击下载PDF文件
【36】 Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information
标题：基于共同注意的多级声学信息语音情感识别
作者：Heqing Zou,Yuke Si,Chen Chen,Deepu Rajan,Eng Siong Chng
机构*：Nanyang Technological University, Singapore, Tianjin University, China
备注：Accepted by ICASSP 2022
链接：点击下载PDF文件
【37】 Evolving Multi-Label Fuzzy Classifier
标题：进化多标签模糊分类器
作者：Edwin Lughofer
机构*：Institute for Mathematical Methods in Medicine and Data Based Modeling, Johannes Kepler University Linz, Austria
链接：点击下载PDF文件
【38】 Agreement or Disagreement in Noise-tolerant Mutual Learning?
标题：在容忍噪音的相互学习中是一致或是不一致？
作者：Jiarun Liu,Daguang Jiang,Yukun Yang,Ruirui Li
机构*：Information Science and Technical Institute, Beijing University of Chemical Technology, Beijing, China
链接：点击下载PDF文件
【39】 Accelerating Code Search with Deep Hashing and Code Classification
标题：利用深度散列和代码分类加速代码搜索
作者：Wenchao Gu,Yanlin Wang,Lun Du,Hongyu Zhang,Shi Han,Dongmei Zhang,Michael R. Lyu
机构*： Department of Computer Science and Engineering, The Chinese University of Hong Kong, China., Microsoft Research Asia, Beijing, China, The University of Newcastle, Australia
链接：点击下载PDF文件
【40】 Finding Structure and Causality in Linear Programs
标题：线性规划中结构和因果关系的求法
作者：Matej Zečević,Florian Peter Busch,Devendra Singh Dhami,Kristian Kersting
机构*：Computer Science Department, TU Darmstadt,Centre for Cognitive Science, TU Darmstadt
备注：Main paper: 5 pages, References: 2 pages, Appendix: 1 page. Figures: 8 main, 1 appendix. Tables: 1 appendix
链接：点击下载PDF文件
【41】 Enabling hand gesture customization on wrist-worn devices
标题：在手腕佩戴的设备上启用手势定制
作者：Xuhai Xu,Jun Gong,Carolina Brum,Lilian Liang,Bongsoo Suh,Kumar Gupta,Yash Agarwal,Laurence Lindsey,Runchang Kang,Behrooz Shahsavari,Tu Nguyen,Heriberto Nieto,Scott E. Hudson,Charlie Maalouf,Seyed Mousavi,Gierad Laput
机构*：Apple Inc. and UW, Apple Inc. and CMU
备注：Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems
链接：点击下载PDF文件
【42】 Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
标题：等方差允许在分析汇集的神经成像数据集时处理多个讨厌的变量
作者：Vishnu Suresh Lokhande,Rudrasis Chakraborty,Sathya N. Ravi,Vikas Singh
备注：Accepted at 2022 IEEECVF Conference on Computer Vision and Pattern Recognition (CVPR)
链接：点击下载PDF文件
【43】 Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth
标题：无监督多帧单目深度解缠目标运动与遮挡
作者：Ziyue Feng,Liang Yang,Longlong Jing,Haiyan Wang,YingLi Tian,Bing Li
机构*： Clemson University, City University of New York
链接：点击下载PDF文件
【44】 Practical Aspects of Zero-Shot Learning
标题：零投篮学习的实践方面
作者：Elie Saad,Marcin Paprzycki,Maria Ganzha
机构*： Warsaw University of Technology, Warsaw, Poland, Systems Research Institute Polish Academy of Sciences
链接：点击下载PDF文件
【45】 Learning to Synthesize Volumetric Meshes from Vision-based Tactile Imprints
标题：从基于视觉的触觉印记学习合成体网格
作者：Xinghao Zhu,Siddarth Jain,Masayoshi Tomizuka,Jeroen van Baar
备注：To appear in the Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2022), Philadelphia (PA), USA
链接：点击下载PDF文件
【46】 CMGAN: Conformer-based Metric GAN for Speech Enhancement
标题：CMGAN：基于Conform的语音增强度量GaN
作者：Ruizhe Cao,Sherif Abdulatif,Bin Yang
机构*：University of Stuttgart, Institute of Signal Processing and System Theory, Stuttgart, Germany
备注：5 pages, 1 figure, 2 tables, submitted to INTERSPEECH 2022
链接：点击下载PDF文件
【47】 An Online Approach to Solve the Dynamic Vehicle Routing Problem with Stochastic Trip Requests for Paratransit Services
标题：一种在线求解辅助服务随机出行动态车辆路径问题的方法
作者：Michael Wilbur,Salah Uddin Kadir,Youngseo Kim,Geoffrey Pettet,Ayan Mukhopadhyay,Philip Pugliese,Samitha Samaranayake,Aron Laszka,Abhishek Dubey
机构*：Vanderbilt University, Nashville TN, United States, University of Houston, Houston TX, United States, Cornell University, Ithaca NY, United States, Chattanooga Area Regional Transportation Authority (CARTA), Chattanooga TN, United States
链接：点击下载PDF文件
【48】 Domain Knowledge Driven Pseudo Labels for Interpretable Goal-Conditioned Interactive Trajectory Prediction
标题：领域知识驱动的可解释目标条件交互式弹道预测的伪标签
作者：Lingfeng Sun,Chen Tang,Yaru Niu,Enna Sachdeva,Chiho Cho,Teruhisa Misu,Masayoshi Tomizuka,Wei Zhan
机构*： 1 Department of Mechanical Engineering, University of California Berke-ley, USA 2 School of Electrical and Computer Engineering, Georgia Institute ofTechnology, USA 3 Honda Research Institute
链接：点击下载PDF文件
【49】 Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
标题：对抗性运动先验是复杂奖励函数的良好替代品
作者：Alejandro Escontrela,Xue Bin Peng,Wenhao Yu,Tingnan Zhang,Atil Iscen,Ken Goldberg,Pieter Abbeel
机构*：γ: UC Berkeley, σ: Google Brain
备注：8 pages, 6 figures, 3 tables
链接：点击下载PDF文件
【50】 Federated Named Entity Recognition
标题：联合命名实体识别
作者：Joel Mathew,Dimitris Stripelis,José Luis Ambite
机构*：USC Information Sciences Institute
链接：点击下载PDF文件
【51】 LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models
标题：LogicInference：一种教seq2seq模型逻辑推理的新数据集
作者：Santiago Ontanon,Joshua Ainslie,Vaclav Cvicek,Zachary Fisher
机构*：Google Research, Mountain View, CA , USA
备注：Accepted at ICLR 2022 OSC workshop
链接：点击下载PDF文件
【52】 Semantic Motion Correction Via Iterative Nonlinear Optimization and Animation
标题：基于迭代非线性优化和动画的语义运动校正
作者：Sairamvinay Vijayaraghavan,Jinxiao Song,Wan-Jhen Lin,Michael J Livanos
备注：13 pages
链接：点击下载PDF文件
【53】 User Driven Model Adjustment via Boolean Rule Explanations
标题：基于布尔规则解释的用户驱动模型平差
作者：Elizabeth M. Daly,Massimiliano Mattetti,Öznur Alkan,Rahul Nair
机构*：IBM Research, Dublin, Ireland
链接：点击下载PDF文件
【54】 Cycle-Consistent Counterfactuals by Latent Transformations
标题：基于潜在变换的周期相容反事实
作者：Saeed Khorram,Li Fuxin
机构*：Collaborative Robotics and Intelligent Systems (CoRIS) Institute, Oregon State University
链接：点击下载PDF文件
【55】 AUC Maximization in the Era of Big Data and AI: A Survey
标题：大数据和人工智能时代的AUC最大化：综述
作者：Tianbao Yang,Yiming Ying
机构*： The University of Iowa, University at Albany
链接：点击下载PDF文件
【56】 Learning Parameterized Task Structure for Generalization to Unseen Entities
标题：面向不可见实体泛化的学习参数化任务结构
作者：Anthony Z. Liu,Sungryull Sohn,Mahdi Qazwini,Honglak Lee
机构*： University of Michigan, LG AI Research
备注：Published in AAAI 2022
链接：点击下载PDF文件
【57】 Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks
标题：用树搜索和图神经网络求解时间可控性受限的不确定析取时态网络
作者：Kevin Osanlou,Jeremy Frank,Andrei Bursuc,Tristan Cazenave,Eric Jacopin,Christophe Guettier,J. Benton
机构*： NASA Ames Research Center, Valeo.ai,LAMSADE, Paris-Dauphine University,CREC Saint-Cyr Coetquidan, Safran
Journal-ref：Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022
链接：点击下载PDF文件
【58】 Few-Shot Object Detection with Fully Cross-Transformer
标题：基于全交叉Transformer的小镜头目标检测
作者：Guangxing Han,Jiawei Ma,Shiyuan Huang,Long Chen,Shih-Fu Chang
机构*：Columbia University
备注：Accepted by CVPR 2022
链接：点击下载PDF文件
【59】 Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
标题：基于自监督自适应图对齐的多语言知识图补全
作者：Zijie Huang,Zheng Li,Haoming Jiang,Tianyu Cao,Hanqing Lu,Bing Yin,Karthik Subbian,Yizhou Sun,Wei Wang
机构*： Wei Wang 1 1University of California
链接：点击下载PDF文件
【60】 Error Correction Code Transformer
标题：纠错码转换器
作者：Yoni Choukroun,Lior Wolf
机构*：Tel Aviv University
链接：点击下载PDF文件
【61】 Deep Learning and Artificial General Intelligence: Still a Long Way to Go
标题：深度学习与人工智能：仍然任重道远
作者：Maciej Świechowski
机构*： 2) Robot College Student Test [ 3] – ability to enroll in auniversity
备注：Accepted as a poster at 3rd Polish Conference on Artificial Intelligence (PP-RAI'2022)
链接：点击下载PDF文件
【62】 Domino: Discovering Systematic Errors with Cross-Modal Embeddings
标题：Domino：使用跨模态嵌入发现系统错误
作者：Sabri Eyuboglu,Maya Varma,Khaled Saab,Jean-Benoit Delbrouck,Christopher Lee-Messer,Jared Dunnmon,James Zou,Christopher Ré
机构*： Christopher R´eStanford University
备注：ICLR 2022 (Oral)
链接：点击下载PDF文件
【63】 Requirements Elicitation in Cognitive Service for Recommendation
标题：面向推荐的认知服务中的需求获取
作者：Bolin Zhang,Zhiying Tu,Yunzhe Xu,Dianhui Chu,Xiaofei Xu
机构*： The existing works focus on single require-ments detection without considering generate the•All authors are with the School of Computer Science and Technology, Harbin Institute of Technology
链接：点击下载PDF文件
【64】 Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
标题：基于无监督自动语音识别的无监督文语合成
作者：Junrui Ni,Liming Wang,Heting Gao,Kaizhi Qian,Yang Zhang,Shiyu Chang,Mark Hasegawa-Johnson
机构*：Hasegawa-Johnson, University of Illinois at Urbana-Champaign, MIT-IBM Watson AI Lab ,University of California, Santa Barbara
备注：submitted to INTERSPEECH
链接：点击下载PDF文件
【65】 A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification
标题：一种基于被动相似度的CNN滤波剪枝算法
作者：Arshdeep Singh,Mark D. Plumbley
机构*：Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK
备注：Submitted to Interspeech 2022 conference
链接：点击下载PDF文件
【66】 Neural representation of a time optimal, constant acceleration rendezvous
标题：时间最优的恒加速度交会的神经表示
作者：Dario Izzo,Sebastien Origer
机构*：European Space Technology and Research Centre, AZ Noordwijk, The Netherlands
链接：点击下载PDF文件
【67】 Spatiotemporal Patterns in Neurobiology: An Overview for Future Artificial Intelligence
标题：神经生物学中的时空模式：未来人工智能的展望
作者：Sean Knight
备注：8 pages
链接：点击下载PDF文件
【68】 A Multi-size Kernel based Adaptive Convolutional Neural Network for Bearing Fault Diagnosis
标题：基于多尺度核的自适应卷积神经网络在轴承故障诊断中的应用
作者：Guangwei Yu,Gang Li,Xingtong Si,Zhuoyuan Song
机构*：School of Mechatronic Engineering and Automation, Shanghai University,-, Nanchen, Rd., Shanghai, China, Department of Mechanical Engineering, University of Hawai‘i at M¯anoa, Dole, St., Honolulu, HI, USA
备注：21 pages, 16 figures
链接：点击下载PDF文件
【69】 Separate What You Describe: Language-Queried Audio Source Separation
标题：分离您所描述的内容：语言查询的音频源分离
作者：Xubo Liu,Haohe Liu,Qiuqiang Kong,Xinhao Mei,Jinzheng Zhao,Qiushi Huang,Mark D. Plumbley,Wenwu Wang
机构*：School of Computer Science and Electronic Engineering, University of Surrey, UK, Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China
备注：Submitted to INTERSPEECH 2022, 5 pages, 3 figures
链接：点击下载PDF文件
【70】 Word Discovery in Visually Grounded, Self-Supervised Speech Models
标题：基于视觉的自监督语音模型中的单词发现
作者：Puyuan Peng,David Harwath
机构*：Department of Computer Science, The University of Texas at Austin, HuBERT, Ours
备注：submitted to Interspeech 2022
链接：点击下载PDF文件
【71】 Learning to segment fetal brain tissue from noisy annotations
标题：学习从嘈杂的注释中分割胎儿脑组织
作者：Davood Karimi,Caitlin K. Rollins,Clemente Velasco-Annis,Abdelhakim Ouaalam,Ali Gholipour
机构*：Member, IEEE
链接：点击下载PDF文件
【72】 On-the-fly Feature Based Speaker Adaptation for Dysarthric and Elderly Speech Recognition
标题：基于动态特征的步态和老年人语音识别中的说话人自适应
作者：Mengzhe Geng,Xurong Xie,Rongfeng Su,Jianwei Yu,Zi Ye,Xunying Liu,Helen Meng
机构*：The Chinese University of Hong Kong, Institute of Software, Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Tecent AI Lab
备注：In submission to Interspeech 2022
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。 |
用Deepseek满血版问问看
