計算機視覺/圖像處理學術速遞[12.18]

2021-01-18 arXiv每日學術速遞

www.arxivdaily.com上線啦,論文摘要、多學科、收藏、評論、搜索……,點擊文末「閱讀原文」即可訪問

cs.CV 方向,今日共計73篇

[檢測分類相關]:

【1】 Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions

標題:基於卷積神經網絡的槍枝檢測:語義分割模型與端到端解決方案的比較

作者:Alexander Egiazarov,Fabio Massimo Zennaro,Vasileios Mavroeidis

機構:Digital Security Group, University of Oslo, Oslo, Norway

備註:10 pages, 5 figures, presented at CyberHunt workshop at IEEE Big Data Conference

連結:https://arxiv.org/abs/2012.09662

【2】 Detection and Prediction of Nutrient Deficiency Stress using Longitudinal Aerial Imagery

作者:Saba Dadsetan,Gisele Rose,Naira Hovakimyan,Jennifer Hobbs

機構:IntelinAir, Inc., Champaign, IL , University of Pittsburgh, Pittsburgh, PA , University of Illinois at Urbana Champaign, Urbana, IL

連結:https://arxiv.org/abs/2012.09654

【3】 Trajectory saliency detection using consistency-oriented latent codes from a recurrent auto-encoder

標題:基於遞歸自動編碼器的面向一致性潛碼的軌跡顯著性檢測

作者:L. Maczyta,P. Bouthemy,O. Le Meur

連結:https://arxiv.org/abs/2012.09573

【4】 PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection

標題:PanoNet3D:結合語義和幾何理解的雷射雷達點雲檢測

作者:Xia Chen,Jianren Wang,David Held,Martial Hebert

機構:Robotics Institute, Carnegie Mellon University, Forbes Ave, Pittsburgh, Pennsylvania

備註:3DV2020

連結:https://arxiv.org/abs/2012.09418

【5】 Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter

標題:基於卷積神經網絡和卡爾曼過濾的高效高爾夫球檢測與跟蹤

作者:Tianxiao Zhang,Xiaohan Zhang,Yiju Yang,Zongbo Wang,Guanghui Wang

機構:University of Kansas, Lawrence, KS , USA, Ainstein Inc., Lawrence, Kansas, USA, Ryerson University, Toronto, ON, Canada M,B ,K

連結:https://arxiv.org/abs/2012.09393

【6】 Learning to Recognize Patch-Wise Consistency for Deepfake Detection

作者:Tianchen Zhao,Xiang Xu,Mingze Xu,Hui Ding,Yuanjun Xiong,Wei Xia

機構:AmazonAWS AI

備註:13 pages, 7 figures

連結:https://arxiv.org/abs/2012.09311

【7】 Kernelized Classification in Deep Networks

作者:Sadeep Jayasumana,Srikumar Ramalingam,Sanjiv Kumar

機構:Google Research, New York

連結:https://arxiv.org/abs/2012.09607

【8】 MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification

標題:Melinda:一種用於生物醫學實驗方法分類的多模態數據集

作者:Te-Lin Wu,Shikhar Singh,Sayan Paul,Gully Burns,Nanyun Peng

機構: University of California, Los Angeles, University of Southern California, Intuit Inc., Chan Zuckerberg Initiative

備註:In The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021

連結:https://arxiv.org/abs/2012.09216

[分割/語義相關]:

【1】 Embodied Visual Active Learning for Semantic Segmentation

作者:David Nilsson,Aleksis Pirinen,Erik Gärtner,Cristian Sminchisescu

機構:Google Research

備註:Accepted to AAAI 2021

連結:https://arxiv.org/abs/2012.09503

【2】 Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation

作者:Hongxiao Wang,Hao Zheng,Jianxu Chen,Lin Yang,Yizhe Zhang,Danny Z. Chen

機構:Jianxu chen, University of Notre Dame, Allen Institute for Cell Science, Notre Dame, IN , USA, Seattle, WA , USA

備註:Accepted paper for the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

連結:https://arxiv.org/abs/2012.09373

【3】 S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds

標題:S3CNet:一種面向LiDAR點雲的稀疏語義場景補全網絡

作者:Ran Cheng,Christopher Agia,Yuan Ren,Xinhai Li,Liu Bingbing

備註:14 pages

連結:https://arxiv.org/abs/2012.09242

【4】 A Contrast Synthesized Thalamic Nuclei Segmentation Scheme using Convolutional Neural Networks

標題:一種基於卷積神經網絡的對比合成丘腦核團分割方法

作者:Lavanya Umapathy,Mahesh Bharath Keerthivasan,Natalie M. Zahr,Ali Bilgin,Manojkumar Saranathan

機構:Electrical and Computer Engineering, University of Arizona, Tucson, AZ, United States, Medical Imaging, University of Arizona, Tucson, AZ, United States, Psychiatry Behavioral Sciences, Stanford University, Menlo Park, CA, United States, Biomedical Engineering, University of Arizona, Tucson, AZ, United States, Corresponding Author:, Associate Professor, University of Arizona, Tucson, AZ , SUBMITTED TO NEUROINFORMA DECEMBER,

備註:24 pages, 7 figures, submitted to Neuroinformatics December 2020

連結:https://arxiv.org/abs/2012.09386

【5】 Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation

作者:Hao Tang,Xingwei Liu,Kun Han,Shanlin Sun,Narisu Bai,Xuming Chen,Huang Qian,Yong Liu,Xiaohui Xie

備註:Accepted WACV 2021

連結:https://arxiv.org/abs/2012.09279

【6】 Transfer Learning Through Weighted Loss Function and Group Normalization for Vessel Segmentation from Retinal Images

標題:基於加權損失函數和分組歸一化的轉移學習在視網膜圖像血管分割中的應用

作者:Abdullah Sarhan,Jon Rokne,Reda Alhajj,Andrew Crichton

機構:University of Calgary, Alberta, Canada, Istanbul Medipol University, Istanbul, Turkey, University of Southern Denmark, Odense, Denmark

備註:Accepted by ICPR. arXiv admin note: text overlap with arXiv:2010.00583

連結:https://arxiv.org/abs/2012.09250

[人臉相關]:

【1】 Incremental Learning from Low-labelled Stream Data in Open-Set Video Face Recognition

作者:Eric Lopez-Lopez,Carlos V. Regueiro,Xose M. Pardo

機構:CITIC, Universidade da Coruna, CiTIUS, Universidade de Santiago de Compostela, December

備註:17 pages, 10 figures

連結:https://arxiv.org/abs/2012.09571

【2】 Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation

標題:Shape My Face:通過面間平移註冊3D人臉掃描

作者:Mehdi Bahri,Eimear O' Sullivan,Shunwang Gong,Feng Liu,Xiaoming Liu,Michael M. Bronstein,Stefanos Zafeiriou

機構:Received: dateAccepted:date

備註:In review with International Journal of Computer Vision (IJCV)

連結:https://arxiv.org/abs/2012.09235

[GAN/對抗式/生成式相關]:

【1】 A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks

作者:Qingsong Yao,Zecheng He,Yi Lin,Kai Ma,Yefeng Zheng,S. Kevin Zhou

機構:ICT, CAS, Princeton University, Tencent Jarvis Lab, Shaohua Kevin Zhou

連結:https://arxiv.org/abs/2012.09501

【2】 Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses

標題:Roof-GAN:學習生成住宅的屋頂幾何圖形和關係

作者:Yiming Qian,Hao Zhang,Yasutaka Furukawa

機構:Simon Fraser University, Canada

連結:https://arxiv.org/abs/2012.09340

【3】 Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues

標題:GaN訓練中抗模式崩潰:基於Hessian特徵值的實證分析

作者:Ricard Durall,Avraam Chatzimichailidis,Peter Labus,Janis Keuper

機構:Fraunhofer ITWM, Germany, IWR, University of Heidelberg, Germany, Chair for Scientific Computing, TU Kaiserslautern, Germany, Fraunhofer Center Machine Learning, Germany, Institute for Machine Learning and Analytics, Offenburg University,Germany, Keywords: Generative Adversarial Network Second-Order Optimization, Mode Collapse, Stability, Eigenvalues.

連結:https://arxiv.org/abs/2012.09673

【4】 On the Limitations of Denoising Strategies as Adversarial Defenses

作者:Zhonghan Niu,Zhaoxi Chen,Linyi Li,Yubin Yang,Bo Li,Jinfeng Yi

機構:Nanjing University, Tsinghua University, UIUC, JD AI Research

連結:https://arxiv.org/abs/2012.09384

[行為/時空/光流/姿態/運動]:

【1】 End-to-End Human Pose and Mesh Reconstruction with Transformers

標題:基於Transformer的端到端人體姿勢和網格重建

作者:Kevin Lin,Lijuan Wang,Zicheng Liu

機構:Microsoft

連結:https://arxiv.org/abs/2012.09760

【2】 Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN

標題:基於三維CNN全局-局部注意力的弱監督動作定位與動作識別

作者:Novanto Yudistira,Muthu Subash Kavitha,Takio Kurita

機構:Intelligent System laboratory, Brawijaya University, Indonesia, Hiroshima University, Higashi-hiroshima, Japan

連結:https://arxiv.org/abs/2012.09542

【3】 Exploiting Learnable Joint Groups for Hand Pose Estimation

作者:Moran Li,Yuan Gao,Nong Sang

機構: Key Laboratory of Image Processing and Intelligent Control, Huazhong University of Science and Technology, Wuhan, China, Tencent AI Lab

備註:Accepted by AAAI2021

連結:https://arxiv.org/abs/2012.09496

【4】 Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation

標題:無監督三維人體姿態估計的不變教師和等變學生算法

作者:Chenxin Xu,Siheng Chen,Maosen Li,Ya Zhang

機構:Cooperative Medianet Innovation Center, Shanghai Jiao Tong University

備註:Accepted in AAAI 2021

連結:https://arxiv.org/abs/2012.09398

【5】 Clique: Spatiotemporal Object Re-identification at the City Scale

作者:Tiantu Xu,Kaiwen Shen,Yang Fu,Humphrey Shi,Felix Xiaozhu Lin

機構:Purdue ece Purdue ECE UIUC University of Oregon University of Virginia

連結:https://arxiv.org/abs/2012.09329

[半/弱/無監督相關]:

【1】 Unsupervised Learning of Local Discriminative Representation for Medical Images

作者:Huai Chen,Jieyu Li,Renzhen Wang,Yijie Huang,Fanrui Meng,Deyu Meng,Qing Peng,Lisheng Wang

機構:Wang-,-, Institute of Image Processing and Pattern Recognition, Xi'an Jiaotong University, Xi'an, P. R. China., Shanghai Tenth People's Hospital, Tongji, University, Shanghai,P. R. China.

備註:13 pages, 4 figures

連結:https://arxiv.org/abs/2012.09333

【2】 Self-Supervised Sketch-to-Image Synthesis

作者:Bingchen Liu,Yizhe Zhu,Kunpeng Song,Ahmed Elgammal

機構:Playform- Artrendex Inc., USA, Rutgers University

備註:AAAI-2021

連結:https://arxiv.org/abs/2012.09290

【3】 ISD: Self-Supervised Learning by Iterative Similarity Distillation

作者:Ajinkya Tejankar,Soroush Abbasi Koohpayegani,Vipin Pillai,Paolo Favaro,Hamed Pirsiavash

機構:University of Maryland, Baltimore County ,University of Bern

連結:https://arxiv.org/abs/2012.09259

【4】 uBAM: Unsupervised Behavior Analysis and Magnification using Deep Learning

標題:uBAM:基於深度學習的無監督行為分析與放大

作者:Biagio Brattoli,Uta Buechler,Michael Dorkenwald,Philipp Reiser,Linard Filli,Fritjof Helmchen,Anna-Sophia Wahl,Bjoern Ommer

機構:Equal first and last authorship, Affiliations:, Interdisciplinary Center for Scientific Computing Heidelberg Collaboratory for Image Process-, ing, Heidelberg University, Germany., University Hospital and University of Zurich, Zurich, Switzerland., Spinal Cord Injury Center, Balgrist University Hospital, Zurich, Switzerland., Brain Research Institute, University of Zurich, Zurich, Switzerland., Neuroscience Center Zurich, Zurich, Switzerland., Central Institute of Mental Health, Heidelberg University, Mannheim, Germany, Correspondence to:

備註:under review

連結:https://arxiv.org/abs/2012.09237

【5】 A new semi-supervised self-training method for lung cancer prediction

作者:Kelvin Shak,Mundher Al-Shabi,Andrea Liew,Boon Leong Lan,Wai Yee Chan,Kwan Hoong Ng,Maxine Tan

機構:)Electrical and Computer Systems Engineering and Advanced Engineering Platform, Engineering, Monash University Malaysia, Bandar Sunway , Malaysia, University of Malaya, Kuala Lumpur, Malaysia, The University of Oklahoma, Norman, OK, USA

備註:23 pages, 6 figures

連結:https://arxiv.org/abs/2012.09472

[跟蹤相關]:

【1】 End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box

標題:基於圓形損失函數的旋轉包圍盒端到端深度目標跟蹤

作者:Vladislav Belyaev,Aleksandra Malysheva,Aleksei Shpilman

機構:JetBrains Research, National Research University, St. Petersburg, Russia

連結:https://arxiv.org/abs/2012.09771

[遷移學習/domain/主動學習/自適應]:

【1】 Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency

作者:Qiang Zhang,Tete Xiao,Alexei A. Efros,Lerrel Pinto,Xiaolong Wang

機構:Shanghai Jiao Tong University, UC Berkeley, New York University, UC San Diego

備註:Project page: this https URL

連結:https://arxiv.org/abs/2012.09811

[裁剪/量化/加速相關]:

【1】 Efficient CNN-LSTM based Image Captioning using Neural Network Compression

標題:基於CNN-LSTM的高效神經網絡壓縮圖像字幕

作者:Harshit Rampal,Aman Mohanty

機構:Carnegie Mellon University, amanmohaCandrew.cmu. edu

連結:https://arxiv.org/abs/2012.09708

【2】 Neural Pruning via Growing Regularization

作者:Huan Wang,Can Qin,Yulun Zhang,Yun Fu

機構:Northeastern University, Boston, MA, USA

連結:https://arxiv.org/abs/2012.09243

【3】 Learned Block-based Hybrid Image Compression

作者:Yaojun Wu,Xin Li,Zhizheng Zhang,Xin Jin,Zhibo Chen

機構:ICAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, University of Science and Technology of China, Hefei , China

備註:9 pages, 11 figures

連結:https://arxiv.org/abs/2012.09550

[視頻理解VQA/caption等]:

【1】 AutoCaption: Image Captioning with Neural Architecture Search

標題:AutoCaption:使用神經結構搜索的圖像字幕

作者:Xinxin Zhu,Weining Wang,Longteng Guo,Jing Liu

機構: National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences

連結:https://arxiv.org/abs/2012.09742

【2】 Robust Image Captioning

作者:Daniel Yarnell,Xian Wang

機構:Central Michigan University

連結:https://arxiv.org/abs/2012.09732

[數據集dataset]:

【1】 RainNet: A Large-Scale Dataset for Spatial Precipitation Downscaling

標題:RainNet:一種空間降水量的大規模數據集

作者:Xuanhong Chen,Kairui Feng,Naiyuan Liu,Naiyuan Liu,Zhengyan Tong,Bingbing Ni,Ziang Liu,Ning Lin

機構:Shanghai Jiao Tong University,Princeton University,University of Technology Sydney

備註:submit to CVPR2021

連結:https://arxiv.org/abs/2012.09700

【2】 CT Film Recovery via Disentangling Geometric Deformation and Illumination Variation: Simulated Datasets and Deep Models

標題:基於解纏幾何變形和光照變化的CT膠片恢復:模擬數據集和深度模型

作者:Quan Quan,Qiyuan Wang,Liu Li,Yuanqi Du,S. Kevin Zhou

機構:Institute of Computing Technology, CAS, Nanjing University, Imperial College London, George Mason University

連結:https://arxiv.org/abs/2012.09491

[超解析度]:

【1】 Deep Learning Techniques for Super-Resolution in Video Games

作者:Alexander Watson

機構:Informatics, Bournemouth University, Bournemouth, UK

備註:4 pages, 1 figure

連結:https://arxiv.org/abs/2012.09810

[點雲]:

【1】 PCT: Point Cloud Transformer

作者:Meng-Hao Guo,Jun-Xiong Cai,Zheng-Ning Liu,Tai-Jiang Mu,Ralph R. Martin,Shi-Min Hu

機構:Tsinghua University, Cardiff University

備註:10 pages, 5 figures

連結:https://arxiv.org/abs/2012.09688

【2】 FG-Net: Fast Large-Scale LiDAR Point CloudsUnderstanding Network Leveraging CorrelatedFeature Mining and Geometric-Aware Modelling

標題:FG-NET:利用關聯特徵挖掘和幾何感知建模的快速大規模LiDAR點雲理解網絡

作者:Kangcheng Liu,Zhi Gao,Feng Lin,Ben M. Chen

連結:https://arxiv.org/abs/2012.09439

[深度depth相關]:

【1】 Multi-Modal Depth Estimation Using Convolutional Neural Networks

作者:Sadique Adnan Siddiqui,Axel Vierling,Karsten Berns

機構:Robotics Research Lab, Dep. of Computer Science, TU Kaiserslautern, Kaiserslautern, Germany

備註:submitted to IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

連結:https://arxiv.org/abs/2012.09667

[3D/3D重建等相關]:

【1】 Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image

標題:Worldsheet:將世界包裝在3D工作表中,以便從單個圖像合成視圖

作者:Ronghang Hu,Deepak Pathak

機構:Facebook AI Research, Carnegie Mellon University

備註:Videos and code on the project page at this https URL

連結:https://arxiv.org/abs/2012.09854

【2】 Learning to Recover 3D Scene Shape from a Single Image

作者:Wei Yin,Jianming Zhang,Oliver Wang,Simon Niklaus,Long Mai,Simon Chen,Chunhua Shen

機構:t The University of Adelaide, Australia, Adobe Research, - Top View Point Cloud, RGB, Predicted Depth Distorted Point Cloud, Recovered Shift Focal Length

連結:https://arxiv.org/abs/2012.09365

[其他視頻相關]:

【1】 Neural Radiance Flow for 4D View Synthesis and Video Processing

作者:Yilun Du,Yinan Zhang,Hong-Xing Yu,Joshua B. Tenenbaum,Jiajun Wu

機構:MIT CSAIL Stanford University, MIT CSAIL, BCS, CBMM

備註:Website: this https URL

連結:https://arxiv.org/abs/2012.09790

【2】 LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos

標題:Lightten:視頻中HOI的圖形和分層時間網絡學習交互

作者:Sai Praneeth Reddy Sunkesula,Rishabh Dabral,Ganesh Ramakrishnan

機構:Indian Institute of Technology, bombay, Bombay, Mumbai, Maharashtra, India, Mumbai,Maharashtra, India, Mumbai, Maharashtra,India, reaching, moving, cleaning, stationary, cleanable, movable, cleaner, reachable, throw, hold, hit, kick, ride, talk on phone

備註:9 pages, 6 figures, ACM Multimedia Conference 2020

連結:https://arxiv.org/abs/2012.09402

[其他]:

【1】 Reconstructing Hand-Object Interactions in the Wild

作者:Zhe Cao,Ilija Radosavovic,Angjoo Kanazawa,Jitendra Malik

機構:University of California, Berkeley

備註:Project page: this https URL

連結:https://arxiv.org/abs/2012.09856

【2】 Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image

作者:Andrew Liu,Richard Tucker,Varun Jampani,Ameesh Makadia,Noah Snavely,Angjoo Kanazawa

機構:Google Research, TRAIN, TEST, Output frames

連結:https://arxiv.org/abs/2012.09855

【3】 Human Mesh Recovery from Multiple Shots

作者:Georgios Pavlakos,Jitendra Malik,Angjoo Kanazawa

機構:University of California, Berkeley

連結:https://arxiv.org/abs/2012.09843

【4】 $\mathbb{X}$Resolution Correspondence Networks

作者:Georgi Tinchev,Shuda Li,Kai Han,David Mitchell,Rigas Kouskouridas

機構:University of Oxford, XYZ Reality, Oxford Robotics Insitute shuda .lixyzreality. com Visual Geometry Group

備註:Preprint. Code will be available at this https URL

連結:https://arxiv.org/abs/2012.09842

【5】 Taming Transformers for High-Resolution Image Synthesis

標題:馴服Transformer實現高解析度圖像合成

作者:Patrick Esser,Robin Rombach,Björn Ommer

機構:Heidelberg Collaboratory for Image Processing, IWR, Heidelberg University, Germany, Both authors contributed equally to this work

連結:https://arxiv.org/abs/2012.09841

【6】 Transformer Interpretability Beyond Attention Visualization

標題:超越注意力可視化的Transformer可解釋性

作者:Hila Chefer,Shir Gur,Lior Wolf

機構:Tel Aviv University, Facebook AI Research(FAIR)

連結:https://arxiv.org/abs/2012.09838

【7】 SceneFormer: Indoor Scene Generation with Transformers

標題:SceneFormer:使用Transformer生成室內場景

作者:Xinpeng Wang,Chandan Yeshwanth,Matthias Nießner

機構:Technical University of Munich

連結:https://arxiv.org/abs/2012.09793

【8】 Interpretable Image Clustering via Diffeomorphism-Aware K-Means

作者:Romain Cosentino,Randall Balestriero,Yanis Bahroun,Anirvan Sengupta,Richard Baraniuk,Behnaam Aazhang

機構:Rice University, Flatiron Institute Rutgers University

連結:https://arxiv.org/abs/2012.09743

【9】 A fully pipelined FPGA accelerator for scale invariant feature transform keypoint descriptor matching,

標題:一種用於尺度不變特徵變換關鍵點描述符匹配的全流水線FPGA加速器,

作者:Luka Daoud,Muhammad Kamran Latif,H S. Jacinto,Nader Rafla

機構:Boise State University, Boise, ID , USA

備註:None

連結:https://arxiv.org/abs/2012.09666

【10】 Learning to Share: A Multitasking Genetic Programming Approach to Image Feature Learning

作者:Ying Bi,Bing Xue,Mengjie Zhang

備註:will submit to IEEE Transactions on Evolutionary Computation soon

連結:https://arxiv.org/abs/2012.09444

【11】 Multi-shot Temporal Event Localization: a Benchmark

作者:Xiaolong Liu,Yao Hu,Song Bai,Fei Ding,Xiang Bai,Philip H. S. Torr

機構:Huazhong University of Science and Technology, Alibaba Group , University of Oxford

備註:Project page at this https URL

連結:https://arxiv.org/abs/2012.09434

【12】 Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup

作者:Guodong Xu,Ziwei Liu,Chen Change Loy

機構:he chinese University of Hong Kong ,Nanyang Technological University

備註:The code is available at: this https URL

連結:https://arxiv.org/abs/2012.09413

【13】 Temporal LiDAR Frame Prediction for Autonomous Driving

作者:David Deng,Avideh Zakhor

機構:UC Berkeley

備註:In 3DV 2020

連結:https://arxiv.org/abs/2012.09409

【14】 Zoom-to-Inpaint: Image Inpainting with High Frequency Details

標題:Zom-to-Inaint:高頻細節的圖像修復

作者:Soo Ye Kim,Kfir Aberman,Nori Kanazawa,Rahul Garg,Neal Wadhwa,Huiwen Chang,Nikhil Karnad,Munchurl Kim,Orly Liba

機構:IKAIST, Google Research, Daejeon, Republic of Korea, Mountain View CA, USA

連結:https://arxiv.org/abs/2012.09401

【15】 Event Camera Calibration of Per-pixel Biased Contrast Threshold

作者:Ziwei Wang,Yonhon Ng,Pieter van Goor,Robert Mahony

機構:Systems Theory and Robotics Group Systems Theory and Robotics Group Systems Theory and Robotics Group, Australian National University, ACT, Australia, December

備註:11 pages, 7 figures, the paper has been accepted for publication at the Australian Conference on Robotics and Automation, 2019

連結:https://arxiv.org/abs/2012.09378

【16】 Semi-Global Shape-aware Network

作者:Pengju Zhang,Yihong Wu,Jiagang Zhu

機構:University of Chinese Academy of Sciences, National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences, XForwardAI Technology Co., Ltd.

備註:8 pages, 6 figures

連結:https://arxiv.org/abs/2012.09372

【17】 Polyblur: Removing mild blur by polynomial reblurring

作者:Mauricio Delbracio,Ignacio Garcia-Dorado,Sungjoon Choi,Damien Kelly,Peyman Milanfar

機構:Google Research

連結:https://arxiv.org/abs/2012.09322

【18】 Projected Distribution Loss for Image Enhancement

作者:Mauricio Delbracio,Hossein Talebi,Peyman Milanfar

連結:https://arxiv.org/abs/2012.09289

【19】 Sparse Signal Models for Data Augmentation in Deep Learning ATR

作者:Tushar Agarwal,Nithin Sugavanam,Emre Ertin

備註:12 pages, 5 figures, to be submitted to IEEE Transactions on Geoscience and Remote Sensing

連結:https://arxiv.org/abs/2012.09284

【20】 On Episodes, Prototypical Networks, and Few-shot Learning

作者:Steinar Laenen,Luca Bertinetto

機構:www. five. ai

備註:19 pages. A preliminary version of this work appeared as an oral presentation at NeurIPS 2020 meta-learning workshop

連結:https://arxiv.org/abs/2012.09831

【21】 Describing the Structural Phenotype of the Glaucomatous Optic Nerve Head Using Artificial Intelligence

作者:Satish K. Panda,Haris Cheong,Tin A. Tun,Sripad K. Devella,Ramaswami Krishnadas,Martin L. Buist,Shamira Perera,Ching-Yu Cheng,Tin Aung,Alexandre H. Thiéry,Michaël J. A. Girard

機構:Ophthalmic Engineering Innovation Laboratory (OEIL), Singapore Eye Research Institute, National University of Singapore, Singapore, Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Glaucoma Services, Aravind Eye Care Systems, Madurai, India, Duke-NUS Medical School, Singapore

連結:https://arxiv.org/abs/2012.09755

【22】 Image-Based Jet Analysis

作者:Michael Kagan

機構:SLAC National Accelerator Laboratory

備註:To appear in Artificial Intelligence for Particle Physics, World Scientific Publishing

連結:https://arxiv.org/abs/2012.09719

【23】 Joint Search of Data Augmentation Policies and Network Architectures

作者:Taiga Kashima,Yoshihiro Yamada,Shunta Saito

機構: The University of Tokyo, Preferred Networks inc., Japan

備註:under review

連結:https://arxiv.org/abs/2012.09407

【24】 Simultaneous View and Feature Selection for Collaborative Multi-Robot Recognition

作者:Brian Reily,Hao Zhang

連結:https://arxiv.org/abs/2012.09328

【25】 StarcNet: Machine Learning for Star Cluster Identification

作者:Gustavo Perez,Matteo Messa,Daniela Calzetti,Subhransu Maji,Dooseok Jung,Angela Adamo,Mattia Siressi

連結:https://arxiv.org/abs/2012.09327

【26】 Reduction in the complexity of 1D 1H-NMR spectra by the use of Frequency to Information Transformation

標題:利用頻率到信息變換降低一維1H-NMR譜的複雜度

作者:Homayoun Valafar,Faramarz Valafar

備註:21 pages

連結:https://arxiv.org/abs/2012.09267

機器翻譯,僅供參考

點擊

閱讀原文

訪問www.arxivdaily.com,獲取帶摘要及更多學科的學術速遞。

相關焦點

  • 計算機視覺/圖像處理學術速遞[02.03]
    Benedetta Tondi,Yao Zhao,Rongrong Ni,Mauro Barni連結:https://arxiv.org/abs/2102.01439【9】 Child-Computer Interaction: Recent Works, New Dataset, and Age Detection標題:兒童-計算機交互
  • 計算機視覺/圖像處理學術速遞[12.14]
    July 15th, 2020連結:https://arxiv.org/abs/2012.06136【7】 Color-related Local Binary Pattern: A Learned Local Descriptor for Color  Image Recognition標題:顏色相關局部二值模式:一種用於彩色圖像識別的學習型局部描述子
  • 計算機視覺/圖像處理學術速遞[08.03]
    //arxiv.org/abs/2007.15818【4】 Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies標題:使用大規模肺炎和氣胸研究的弱監督一期視覺和語言疾病檢測
  • 計算機視覺/圖像處理學術速遞[10.08]
    Yap, Eibe Frank 連結:https://arxiv.org/abs/2010.03341【3】 Multi-label classification of promotions in digital leaflets using textual and visual information標題:使用文本和視覺信息對數字傳單中的促銷進行多標籤分類
  • 計算機視覺/圖像處理學術速遞[11.03]
    Huisman 備註:Accepted to Medical Imaging Meets NeurIPS Workshop of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020)連結:https://arxiv.org/abs/2011.00263【12
  • 計算機視覺/圖像處理學術速遞[08.20]
    /2008.08452【4】 Anchor-free Small-scale Multispectral Pedestrian Detection作者: Alexander Wolpert, Rainer Stiefelhagen 備註:BMVC2020連結:https://arxiv.org/abs/2008.08418
  • 計算機視覺將用來處理相機圖像
    得到一些數據以及判斷,然後推斷應該怎麼工作,這其中包括對人的數據進行分析,包括性別,年齡,籍貫等等,也包括對機器的運算發送指令給人工,使用代碼來進行循環.然後在人工智慧的背後,一個重要的單位就是計算機視覺,它們主要負責識別,分類,檢測,填充,分割.首先計算機視覺可以幫助我們更好的了解自己的眼睛,也就是我們的眼睛,視覺的作用在於生物可以更好的了解周圍的世界。
  • 計算機視覺和圖像處理之間有什麼區別?
    現代機器視覺系統背後的的核心動機在於模擬人類視覺,用於識別圖案,面部以及將將2D圖像轉化為3D模型等。在概念層面,圖像處理和計算機視覺之間存在很多重疊,並且經常被誤解的術語可以互換使用。在這裡,我們簡要概述了這些技術,並解釋了它們在基礎層面上的不同之處。
  • 計算機視覺/圖像處理學術速遞[08.06]
    2020連結:https://arxiv.org/abs/2008.01860【3】 Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidance標題:基於自監督語義引導的組織病理圖像結構保持染色歸一化
  • 計算機視覺(圖像)技術:視覺圖像搜索綜述
    這些年計算機視覺識別和搜索這個領域非常熱鬧,後期出現了很多的創業公司,大公司也在這方面也花了很多力氣在做。做視覺搜索,其實是深度學習(或人工智慧)領域最重要的研究課題之一,在現實生活中有著非常廣泛的應用。  通常,視覺搜索包含了兩步任務:首先,待搜索物體的檢測與定位;其次,從庫(知識圖譜、圖片庫、信息庫等)中搜索該物體,或查詢相關聯的場景。
  • 【期刊速遞】高光譜遙感圖像處理與信息提取直播預告
    高光譜圖像處理與信息提取技術是高光譜遙感領域的核心研究內容之一。隨著智能化信息分析和高性能硬體處理技術的發展,高光譜遙感衛星系統也將步入智能化時代。如何利用人工智慧等最新成果,發展高光譜圖像處理與信息提取的高性能實時處理技術?如何發揮高光譜遙感的優勢和特點,發展新理論和新方法?
  • 包括的領域有計算機視覺,語音識別,自然語言處理,圖像識別等
    現在人工智慧已經包括的領域有計算機視覺,語音識別,自然語言處理,圖像識別等。人工智慧的步驟人工智慧基本步驟包括,信息提取->信息分析->假設建模->學習->泛化,具體步驟。如果說計算機視覺是讓計算機看到一張黑白的二維圖像,那麼它可以識別字符串,可以通過圖像獲取某個標註的信息,它具有特定的識別圖像,可以從圖像分析出某個基本的結構。
  • 科研進階 | 哈佛大學 | 電子工程、軟體工程、計算機科學:計算機圖形圖像處理綜合研究 (2021.7.31開課)
    圖像是迄今為止人類最高效的交流方式。從工業到醫療行業,不論是公共還是私人網絡上,都有大量分布式圖像和視頻資料庫。因而,掌握提取相關信息的技術在現在和未來都至關重要。數字圖像處理 (Digital Image Processing) 是通過計算機對圖像進行降噪、增強、復原、分割、提取特徵等處理的方法和技術。圖像處理的應用領域涉及到人類生活和工作的方方面面。
  • 機器視覺和智能圖像處理技術之間的關係
    一般認為機器視覺「是通過光學裝置和非接觸傳感器自動地接受和處理一個真實場景的圖像,通過分析圖像獲得所需信息或用於控制機器運動的裝置」,可以看出智能圖像處理技術在機器視覺中佔有舉足輕重的位置。 智能圖像處理是指一類基於計算機的自適應於各種應用場合的圖像處理和分析技術,本身是一個獨立的理論和技術領域,但同時又是機器視覺中的一項十分重要的技術支撐。
  • 智能圖像處理 讓機器視覺及其應用更智能高效
    編者按:無論是「中國製造2025」還是「工業4.0」都離不開人工智慧,離不開計算機視覺,而智能圖像處理是機器視覺的核心技術,隨著圖像處理水平的不斷提高,一定會有力地推動機器視覺的迅速發展。
  • 計算機視覺領域的王者與榮耀丨CCF-GAIR 2018
    在這背後,安防視頻監控與醫療影像,也成為眾多AI從業者尤為青睞的兩大行業。當計算機視覺研究與落地大潮湧動之際,第三屆CCF-GAIR全球人工智慧與機器人峰會「計算機視覺專場」,眾多科技巨頭首席技術官、獨角獸首席科學家、國際學術頂會主席、世界名校AI實驗室主任將會公開分享最前沿的計算機視覺技術研究與商用成果。
  • 計算機視覺 vs 機器視覺
    計算機視覺和機器視覺通常被認為是同一個行業,其實它們是重疊技術的不同術語。計算機視覺廣義上是指圖像分析的捕獲和自動化,並著重於在廣泛的理論和實際應用中的圖像分析功能。傳統上,機器視覺是借鑑參考了計算機視覺技術,在某些工業或實際應用中根據視覺系統完成圖像分析的某些功能或結果。視覺系統使用軟體來識別預編程的功能,該系統可根據發現結果觸發各種設定的「動作」。例如,在食品和飲料行業的裝瓶廠中,視覺系統可用於識別多個物體。它可以驗證空瓶本身沒有損壞和異物。
  • 人工智慧與計算機視覺
    計算機視覺是使用計算機及相關設備對生物視覺的一種模擬,是人工智慧領域的一個重要部分,它的研究目標是使計算機具有通過二維圖像認知三維環境信息的能力。計算機視覺是以圖象處理技術、信號處理技術、概率統計分析、計算幾何、神經網絡、機器學習理論和計算機信息處理技術等為基礎,通過計算機分析與處理視覺信息。
  • 視覺感知-從人類視覺到計算機視覺
    1.4億個神經元組成,是大腦中最神秘的部分之一,負責處理和解釋視覺數據以提供感知力並建立記憶。例如給定一幅圖像,我們可以利用上下文和先驗知識得知整個故事。 但是,使計算機感知視覺世界有多困難?截至2019年,我們才取得了一定進展,但依舊還有很長的路要走。計算機視覺是計算機科學的一個相對較新的領域,大約有60年的歷史。
  • 預告| CSIG圖像圖形學科前沿講習班:智能駕駛與機器視覺
    主要研究方向包括計算機視覺與模式識別、智能車環境感知及運動控制,在IEEE彙刊TPAMI、TIP、TMM及學術會議ICCV、CVPR、ECCV、IROS、ACM MM等發表論文70餘篇。馬惠敏,清華大學電子工程系副教授,博士生導師,三維圖像仿真研究室負責人,中國圖象圖形學學會秘書長,北京市「三八紅旗獎章」獲得者。