浏览arxivdaily.com，获得带引言学术速递，更跨学科、个人收藏、评价、检索……一应俱全。同歩微信公众号(arXiv每日学术研究速递)，请关注
【1】 Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
标题：吹狗哨：中国常识与世界基本常识了解数据
作者：Canwen Xu,Wangchunshu Zhou,Tao Ge,Ke Xu,Julian McAuley,Furu Wei
机构*： University of California, San Diego , Beihang University , Microsoft Research Asia
备注：NAACL 2021
连接：https://arxiv.org/abs/2104.02704
【2】 Strumming to the Beat: Audio-Conditioned Contrastive Video Textures
标题：伴随着节奏演奏：声频情况下的饱和度短视频纹路
作者：Medhini Narasimhan,Shiry Ginosar,Andrew Owens,Alexei A. Efros,Trevor Darrell
机构*：University of California, Berkeley ,University of Michigan
备注：Project website at this https URL
连接：https://arxiv.org/abs/2104.02687
【3】 Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning
标题：根据模仿和加强学习的网络约车服务项目数字驱动模拟仿真
作者：Haritha Jayasinghe,Tarindu Jayatilaka,Ravin Gunawardena,Uthayasanker Thayasivam
机构*：University of Moratuwa, Moratuwa , Sri Lanka
连接：https://arxiv.org/abs/2104.02661
【4】 Collaborative Learning to Generate Audio-Video Jointly
标题：合作式学习协同形成音频视频
作者：Vinod K Kurmi,Vipul Bajaj,Badri N Patro,K S Venkatesh,Vinay P Namboodiri,Preethi Jyothi
机构*：Indian Institute of Technology Kanpur University of Bath Indian Institute of Technology Bombay
备注：ICASSP 2021 (Accepted)
连接：https://arxiv.org/abs/2104.02656
【5】 gradSim: Differentiable simulation for system identification and visuomotor control
标题：gradSim：用以系统辨识和视觉运动控制系统的求微分模拟仿真
作者：Krishna Murthy Jatavallabhula,Miles Macklin,Florian Golemo,Vikram Voleti,Linda Petrini,Martin Weiss,Breandan Considine,Jerome Parent-Levesque,Kevin Xie,Kenny Erleben,Liam Paull,Florian Shkurti,Derek Nowrouzezahrai,Sanja Fidler
机构*：Montreal Robotics and Embodied AI Lab,NVIDIA, Mila,Universite de Montreal,McGill., University of Toronto,Vector Institute,University of Copenhagen
备注：ICLR 2021. Project page (and a dynamic web version of the article): this https URL
连接：https://arxiv.org/abs/2104.02646
【6】 How to Accelerate Capsule Convolutions in Capsule Networks
标题：怎样在胶囊网络中加快胶襄卷积和
作者：Zhenhua Chen,Xiwen Li,Qian Lou,David Crandall
连接：https://arxiv.org/abs/2104.02621
【7】 Are GAN generated images easy to detect? A critical analysis of the state-of-the-art
标题：GaN形成的影像非常容易检验吗B体育官方入口？对前沿技术的批判性分析
作者：Diego Gragnaniello,Davide Cozzolino,Francesco Marra,Giovanni Poggi,Luisa Verdoliva
备注：7 pages, 5 figures, conference
连接：https://arxiv.org/abs/2104.02617
【8】 PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information
标题：PointShuffleNet：学习具备同伦等额的和互信息非欧几里得特点
作者：Linchao He,Mengting Luo,Dejun Zhang,Xiao Yang,Hu Chen,Yi Zhang
备注：15 pages
连接：https://arxiv.org/abs/2104.02611
【9】 An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information
标题：一种基于文本文档级构造数据的无监督取样图句匹配方法
作者：Zejun Li,Zhongyu Wei,Zhihao Fan,Haijun Shan,Xuanjing Huang
机构*：School of Data Science, Fudan University, China, Zhejiang Lab, China, School of Computer Science, Fudan University, China, Research Institute of Intelligent and Complex Systems, Fudan University, China
备注：To be published in AAAI2021
连接：https://arxiv.org/abs/2104.02605
【10】 Future of work: ethics
标题：工作中未来的发展：伦理学研究
作者：David Pastor-Escuredo
机构*：UCL, UK, LifeD Lab, Spain
连接：https://arxiv.org/abs/2104.02580
【11】 Neurons learn slower than they think
标题：神经细胞学习的速度比他们想像的慢
作者：Ilona Kulikovskikh
备注：7 pages, 3 figures
连接：https://arxiv.org/abs/2104.02578
【12】 Learnable Dynamic Temporal Pooling for Time Series Classification
标题：用以时间序列分析分类可学习动态性时长池
作者：Dongha Lee,Seonghyeon Lee,Hwanjo Yu
机构*：Institute of Artificial Intelligence, POSTECH, Republic of Korea, Dept. of Computer Science and Engineering POSTECH, Republic of Korea
备注：AAAI 2021. 7 pages references (2 pages). 8 figures
连接：https://arxiv.org/abs/2104.02577
【13】 Prediction of Solar Radiation Using Artificial Neural Network
标题：运用神经网络算法预测分析太阳辐射量
作者：Shahriar Rahman,Shazzadur Rahman,A K M Bahalul Haque
机构*：View the article online for updates and enhancements.
备注：Published as open access, 12 pages, 13 images and 2 tables
连接：https://arxiv.org/abs/2104.02573
【14】 Proof Complexity of Symbolic QBF Reasoning
标题：标记QBF逻辑推理的相关证明多元性
作者：Stefan Mengel,Friedrich Slivovsky
机构*： CNRS, UMR , Centre de Recherche en Informatique de Lens (CRIL), Lens, Univ. Artois, UMR , Lens, F-, France, TU Wien, Vienna, Austria
连接：https://arxiv.org/abs/2104.02563
【15】 White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks
标题：分类任务任务时神经网络解释的黑盒方式
作者：Meghna P Ayyar,Jenny Benois-Pineau,Akka Zemmari
机构*：University of Bordeaux, LaBRI,umr, Crs de la Liberation,Talence, France
备注：Submitted to Journal of Electronic Imaging (JEI)
连接：https://arxiv.org/abs/2104.02548
【16】 Data-driven Design of Context-aware Monitors for Hazard Prediction in Artificial Pancreas Systems
标题：人工肝胀系统内用以风险评估的上下文感知监控的数字驱动设计方案
作者：Xugui Zhou,Bulbul Ahmed,James H. Aylor,Philip Asare,Homa Alemzadeh
备注：13 pages, 9 figures, to appear in the 51st IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2021
连接：https://arxiv.org/abs/2104.02545
【17】 Instantaneous Stereo Depth Estimation of Real-World Stimuli with a Neuromorphic Stereo-Vision Setup
标题：用神经系统形状立体视觉设备可能真正刺激的游戏瞬间立体式深层
作者：Nicoletta Risi,Enrico Calabrese,Giacomo Indiveri
机构*：Institute of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland
连接：https://arxiv.org/abs/2104.02541
【18】 On the Basis of Sex: A Review of Gender Bias in Machine Learning Applications
标题：根据胎儿性别：机器学习应用里的性别偏见研究述评
作者：Tal Feldman,Ashley Peake
机构*：Wake Forest University, Winston Salem, USA
备注：7 pages, 2 figures
连接：https://arxiv.org/abs/2104.02532
【19】 Nonlinear Model Based Guidance with Deep Learning Based Target Trajectory Prediction Against Aerial Agile Attack Patterns
标题：基于大数据的非线性模型制导技术上空灵巧进攻模式的总体目标轨迹预测
作者：A. Sadik Satir,Umut Demir,Gulay Goktas Sever,N. Kemal Ure
备注：Accepted for the 2021 American Control Conference (ACC)
连接：https://arxiv.org/abs/2104.02491
【20】 OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation
标题：OodGAN：境外数据生成的生成性竞技性互联网
作者：Petr Marek,Vishal Ishwar Naik,Vincent Auvray,Anuj Goyal
机构*：Czech Technical University in Prague, Amazon Alexa Al, Prague, Czech Republic, Sunnyvale, California
备注：NAACL 2021 Industry track
连接：https://arxiv.org/abs/2104.02484
【21】 Topological Regularization for Graph Neural Networks Augmentation
标题：图神经网络强化的拓扑结构正则化方法
作者：Rui Song,Fausto Giunchiglia,Ke Zhao,Hao Xu
机构*：School of Artificial Intelligence, Jilin University, Changchun , China, b College of Software, Jilin University, Changchun , China, College of Computer Science and Technology, Jilin University, Changchun , China, University of Trento, Italy
备注：20 pages, 5 figures
连接：https://arxiv.org/abs/2104.02478
【22】 Fast Design Space Exploration of Nonlinear Systems: Part II
标题：非线性系统的快速建模空间探索：第二部分
作者：Prerit Terway,Kenza Hamidouche,Niraj K. Jha
备注：14 pages, 24 figures. arXiv admin note: substantial text overlap with arXiv:2009.10214
连接：https://arxiv.org/abs/2104.02464
【23】 Contrastive Explanations for Explaining Model Adaptations
标题：解释实体模型融入的比较解释
作者：André Artelt,Fabian Hinder,Valerie Vaquet,Robert Feldhans,Barbara Hammer
连接：https://arxiv.org/abs/2104.02459
【24】 CodeTrans: Towards Cracking the Language of Silicone's Code Through Self-Supervised Deep Learning and High Performance Computing
标题：CodeTrans：根据自我管理的深度学习和大数据处理破译硅橡胶程序代码语言表达
作者：Ahmed Elnaggar,Wei Ding,Llion Jones,Tom Gibbs,Tamas Feher,Christoph Angerer,Silvia Severini,Florian Matthes,Burkhard Rost
机构*：AHMED.ELNAGGARQTUM.DE, WEI. DINGQTUM. DE, TUM (Technical University of Munich), Boltzmannstrasse , Garching, Germany, Google AI, Amphitheatre Parkway, Mountain View, CA , USA, TFEHERONVIDIA.COM, CANGERERONVIDIA.COM, Nvidia
备注：28 pages, 6 tables and 1 figure
连接：https://arxiv.org/abs/2104.02443
【25】 The Duo of Artificial Intelligence and Big Data forIndustry 4.0: Review of Applications, Techniques,Challenges, and Future Research Directions
标题：工业生产4.0的人工智能化与大数据技术二人组：运用、技术性、挑战未来探索方位具体描述
作者：Senthil Kumar Jagatheesaperuma,Mohamed Rahouti,Kashif Ahmad,Mohsen Guizani,Ala Al-Fuqaha
机构*：Mepco Schlenk Engineering College, Sivakasi., Tamil Nadu, India., Fordham University, Bronx, NY, USA., Information and Computing Technologies (ICT) Division, College of Science and Engineering (CSE), Hamad, Bin Khalifa University, Doha, Qatar., §
备注：33 pages, 10 figures, 7 tables
连接：https://arxiv.org/abs/2104.02425
【26】 Ensemble deep learning: A review
标题：集成深度学习：综述
作者：M. A. Ganaie,Minghui Hu,M. Tanveer,P. N. Suganthan
组织*：Indian Institute of Technology Indore, Simrol, Indore, India, School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore
连接：https://arxiv.org/abs/2104.02395
【27】 Backdoor Attack in the Physical World
标题：物理学世界里的后门攻击
作者：Yiming Li,Tongqing Zhai,Yong Jiang,Zhifeng Li,Shu-Tao Xia
组织*：Tsinghua Shenzhen International Graduate School, Tsinghua University, Tencent Lab
备注：This work was done when Yiming Li was an intern at Tencent AI Lab, supported by the Tencent Rhino-Bird Elite Training Program (2020). This is a 6-pages short version of our ongoing work, `Rethinking the Trigger of Backdoor Attack' (arXiv:2004.04692). It is accepted by the non-archival ICLR 2021 workshop on Robust and Reliable Machine Learning in the Real World
连接：https://arxiv.org/abs/2104.02361
【28】 Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
标题：弱监督时长姿势精准定位的自适应互相激励
作者：Chen Ju,Peisen Zhao,Siheng Chen,Ya Zhang,Xiaoyun Zhang,Qi Tian
连接：https://arxiv.org/abs/2104.02357
【29】 Multiple instance active learning for object detection
标题：用以物体检测的多实例自主学习
作者：Tianning Yuan,Fang Wan,Mengying Fu,Jianzhuang Liu,Songcen Xu,Xiangyang Ji,Qixiang Ye
组织*：University of Chinese Academy of Sciences, Beijing, China, FNoah's Ark Lab, Huawei Technologies Shenzhen, China. STsinghua University, Beijing, China, Image Uncertainty
备注：10 pages, 7 figures, 5 tables. Code is available at this https URL
连接：https://arxiv.org/abs/2104.02324
【30】 Efficient Video Compression via Content-Adaptive Super-Resolution
标题：根据具体内容响应式超分辨率的有效视频压缩
作者：Mehrdad Khani,Vibhaalakshmi Sivaraman,Mohammad Alizadeh
组织*：MIT CSAIL
连接：https://arxiv.org/abs/2104.02322
【31】 Exploration of Hardware Acceleration Methods for an XNOR Traffic Signs Classifier
标题：XNOR交通标识分类算法硬件加速器方式讨论
作者：Dominika Przewlocka-Rus,Marcin Kowalczyk,Tomasz Kryjak
组织*：AGH University of Science and Technology in Krakow, Poland
备注：12 pages, 2 figures, 6 tables. Submitted for the CORES 2021 conference
连接：https://arxiv.org/abs/2104.02303
【32】 Shapley Explanation Networks
标题：沙普利表述互联网
作者：Rui Wang,Xiaoqian Wang,David I. Inouye
组织*：School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN
备注：26 pages, 11 figures, accepted to ICLR 2021
连接：https://arxiv.org/abs/2104.02297
【33】 Preferential Structures for Comparative Probabilistic Reasoning
标题：较为几率逻辑推理的喜好构造
作者：Matthew Harrison-Trainor,Wesley H. Holliday,Thomas F. Icard III
备注：Postprint of AAAI 2017 paper, corrected to include a distinguished set of states in Definitions 2-3 and 5 (resp. before Theorem 3) to match the appropriate special case of the semantics of Holliday and Icard 2013 (resp. van der Hoek 1996)
连接：https://arxiv.org/abs/2104.02287
【34】 Text-guided Legal Knowledge Graph Reasoning
标题：文字指导的法律法规知识图逻辑推理
作者：Luoqiu Li,Zhen Bi,Hongbin Ye,Shumin Deng,Hui Chen,Huaixiao Tou,Ningyu Zhang,Huajun Chen
组织*： Zhejiang University, China, AZFT Joint Lab for Knowledge Engine, China, Alibaba Group, China
备注：work in progress
连接：https://arxiv.org/abs/2104.02284
b体育下载app
【35】 Attribute-Based Robotic Grasping with One-Grasp Adaptation
标题：一次爬取自适应的根据属性机器人抓取
作者：Yang Yang,Yuanhao Liu,Hengyue Liang,Xibai Lou,Changhyun Choi
备注：Accepted to the IEEE International Conference on Robotics and Automation (ICRA 2021). Project page: this https URL
连接：https://arxiv.org/abs/2104.02271
【36】 Multi-Scale Context Aggregation Network with Attention-Guided for Crowd Counting
标题：根据专注力正确引导得多尺寸前后文汇聚互联网人群计数
作者：Xin Wang,Yang Zhao,Tangwen Yang,Qiuqi Ruan
组织*：IInstitute of Information Science, School of Computer and Information Technology, Beijing Jiaotong University, Beijing , China, Guangdong Key Laboratory of Intelligent Information processing, Shenzhen University, Shenzhen, Guangdong , China
备注：None
连接：https://arxiv.org/abs/2104.02245
【37】 TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT
标题：户外帐篷：锥型没动点微边沿上神经网络的合理量化分析
作者：Hamed F. Langroudi,Vedant Karia,Tej Pandit,Dhireesha Kudithipudi
机构*：Neuromorphic AI Lab, University of Texas at San Antonio, TX, USA
备注：poster presented at the first tinyML Research Symposium, March 26, 2021
连接：https://arxiv.org/abs/2104.02233
【38】 Beyond Categorical Label Representations for Image Classification
标题：超过分类标签表述的图像分类
作者：Boyuan Chen,Yu Li,Sunand Raghupathi,Hod Lipson
机构*：Columbia University
备注：International Conference on Learning Representations (ICLR 2021). Project page is at \url{this https URL}
连接：https://arxiv.org/abs/2104.02226
【39】 When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes
标题：当猪翱翔：生成与自然场景下的情境逻辑推理
作者：Philipp Bomatter,Mengmi Zhang,Dimitar Karev,Spandan Madan,Claire Tseng,Gabriel Kreiman
连接：https://arxiv.org/abs/2104.02215
【40】 Intelligent Building Control Systems for Thermal Comfort and Energy-Efficiency: A Systematic Review of Artificial Intelligence-Assisted Techniques
标题：面对热舒适和节能的智能建筑自动控制系统--人工智能技术协助技术性的软件论述
作者：Ghezlane Halhoul Merabet,Mohamed Essaaidi,Mohamed Ben Haddou,Basheer Qolomany,Junaid Qadir,Muhammad Anan,Ala Al-Fuqaha,Mohamed Riduan Abid,Driss Benhaddou
机构*：a Smart Systems Laboratory (SSL), ENSIAS, Mohammed V University in Rabat, Morocco, MENTIS Consulting SA, rue de Congres, Brussels, Belgium, College of Business and Technology, University of Nebraska at Kearney (UNK), Kearney, NE , USA
备注：arXiv admin note: text overlap with arXiv:2006.12559
连接：https://arxiv.org/abs/2104.02214
【41】 Hypothesis-driven Stream Learning with Augmented Memory
标题：根据拓展记忆力的假设推动流学习培训
作者：Mengmi Zhang,Rohil Badkundri,Morgan B. Talbot,Gabriel Kreiman
机构*：, Equal contribution, Children's Hospital, Harvard Medical School, Center for Brains, Minds and Machines, Harvard College, Harvard University, Harvard-MIT Health Sciences and Technology Harvard Medical School
连接：https://arxiv.org/abs/2104.02206
【42】 Designing Efficient and High-performance AI Accelerators with Customized STT-MRAM
标题：运用订制STT-MRAM设计方案高效率性能卓越AI网络加速器
作者：Kaniz Mishty,Mehdi Sadi
连接：https://arxiv.org/abs/2104.02199
【43】 Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purification
标题：用以竞技性图象过滤的鲁棒性词义表明的自适应聚类算法
作者：Samuel Henrique Silva,Arun Das,Ian Scarff,Peyman Najafirad
机构*：Secure Al Autonomy Laboratory
备注：11 pages, 5 figures, 4 tables
连接：https://arxiv.org/abs/2104.02155
【44】 A Concise Review of Transfer Learning
标题：迁移学习点评
作者：Abolfazl Farahani,Behrouz Pourshojae,Khaled Rasheed,Hamid R. Arabnia
机构*：University of Georgia, Road and Urban Development Organization, University of georgia, Athens, GA, USA, Arak, Iran
连接：https://arxiv.org/abs/2104.02144
【45】 ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities
标题：ASER：根据高级挑选喜好并非随机性迈向规模性常识知识获得
作者：Hongming Zhang,Xin Liu,Haojie Pan,Haowen Ke,Jiefu Ou,Tianqing Fang,Yangqiu Song
机构*：CSE, HKUST, HKSAR, China
连接：https://arxiv.org/abs/2104.02137
【46】 Discrete Reasoning Templates for Natural Language Understanding
标题：用以自然语言处理的离散变量逻辑推理模版
作者：Hadeel Al-Negheimish,Pranava Madhyastha,Alessandra Russo
机构*：Imperial College London
备注：Published at EACL 2021 SRW
连接：https://arxiv.org/abs/2104.02115
【47】 Compressing Visual-linguistic Model via Knowledge Distillation
标题：根据专业知识提炼的视觉元素模型压缩
作者：Zhiyuan Fang,Jianfeng Wang,Xiaowei Hu,Lijuan Wang,Yezhou Yang,Zicheng Liu
机构*：Arizona State University, Microsoft Corporation
连接：https://arxiv.org/abs/2104.02096
【48】 A non-asymptotic penalization criterion for model selection in mixture of experts models
标题：混和权威专家模型选择非渐行处罚规则
作者：TrungTin Nguyen,Hien Duy Nguyen,Faicel Chamroukhi,Florence Forbes
机构*：Forbes, Normandie Univ, UNICAEN, CNRS, LMNO, Caen, France., La Trobe University, Bundoora, Melbourne , Victoria Australia., BUniv. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Inria Grenoble, Rhone-Alpes, av. de l'Europe, Montbonnot, France.
连接：https://arxiv.org/abs/2104.02640
【49】 A Novel Approach for Semiconductor Etching Process with Inductive Biases
标题：一种新的带磁感应参考点的半导体材料离子注入工艺方法
作者：Sanghoon Myung,Hyunjae Jang,Byungseon Choi,Jisu Ryu,Hyuk Kim,Sang Wuk Park,Changwook Jeong,Dae Sin Kim
机构*：Data and Information Technology(DIT)Center, DIT Center, Samsung Electronics Samsung Electronics, Semiconductor&D Center Semiconductor R&D Center, DIT center
备注名称：5 pages; accepted to NeurIPS 2020 Workshop on Interpretable Inductive Biases and Physically Structured Learning
连接：https://arxiv.org/abs/2104.02468
计算机翻译，仅作参考；“组织”仅作参考
