每日論文速遞:計算機視覺相關(10月8日更新版)

2021-01-14 深度學習這件小事

出品 | 深度學習這件小事公眾號

[1] High-Capacity Expert Binary Networks作者 | Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos連結 | https://arxiv.org/abs/2010.03558 [2] On the Evaluation of Generative Adversarial Networks By Discriminative Models作者 | Amirsina Torfi, Mohammadreza Beyki, Edward A. Fox連結 | https://arxiv.org/abs/2010.03549 備註 | Accepted to be published in ICPR 2020[3] BoMuDA: Boundless Multi-Source Domain Adaptive Segmentation in Unconstrained Environments作者 | Divya Kothandaraman, Rohan Chandra, Dinesh Manocha連結 | https://arxiv.org/abs/2010.03523 [4] Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels作者 | L. Koestler, N. Yang, R. Wang, D. Cremers連結 | https://arxiv.org/abs/2010.03506 [5] Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning作者 | Daniel Deniz, Francisco Barranco, Juan Isern, Eduardo Ros連結 | https://arxiv.org/abs/2010.03497 [6] Super-Human Performance in Online Low-latency Recognition of Conversational Speech作者 | Thai-Son Nguyen, Sebastian Stueker, Alex Waibel連結 | https://arxiv.org/abs/2010.03449 [7] Universal Weighting Metric Learning for Cross-Modal Matching作者 | Jiwei Wei, Xing Xu, Yang Yang, Yanli Ji, Zheng Wang, Heng Tao Shen連結 | https://arxiv.org/abs/2010.03403 [8] A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations作者 | Haosu Zhou, Qingfeng Xu, Nan Li連結 | https://arxiv.org/abs/2010.03370 備註 | 16 pages, 14 figures[9] Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation作者 | Moi Hoon Yap, Ryo Hachiuma, Azadeh Alavi, Raphael Brungel, Manu Goyal, Hongtao Zhu, Bill Cassidy, Johannes Ruckert, Moshe Olshansky, Xiao Huang, Hideo Saito, Saeed Hassanpour, Christoph M. Friedrich, David Ascher, Anping Song, Hiroki Kajita, David Gillespie, Neil D. Reeves, Joseph Pappachan, Claire O'Shea, Eibe Frank連結 | https://arxiv.org/abs/2010.03341 備註 | 17 pages, 17 figures, 9 tables[10] Multi-label classification of promotions in digital leaflets using textual and visual information作者 | Roberto Arroyo, David Jiménez-Cabello, Javier Martínez-Cebrián連結 | https://arxiv.org/abs/2010.03331 備註 | Conference on Computational Linguistics (COLING). Workshop on Natural Language Processing in E-Commerce (EcomNLP 2020)[11] Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement作者 | Fangbo Qin, Jie Qin, Siyu Huang, De Xu連結 | https://arxiv.org/abs/2010.03325 備註 | Submitted to IEEE Robotics and Automation Letters[12] YOdar: Uncertainty-based Sensor Fusion for Vehicle Detection with Camera and Radar Sensors作者 | Kamil Kowol, Matthias Rottmann, Stefan Bracke, Hanno Gottschalk連結 | https://arxiv.org/abs/2010.03320 [13] Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud作者 | Seohyun Kim, Jaeyoo Park, Bohyung Han連結 | https://arxiv.org/abs/2010.03318 備註 | 15 pages, Accepted by NeurIPS 2020[14] CD-UAP: Class Discriminative Universal Adversarial Perturbation作者 | Chaoning Zhang, Philipp Benz, Tooba Imtiaz, In So Kweon連結 | https://arxiv.org/abs/2010.03300 [15] Attention Model Enhanced Network for Classification of Breast Cancer Image作者 | Xiao Kang, Xingbo Liu, Xiushan Nie, Xiaoming Xi, Yilong Yin連結 | https://arxiv.org/abs/2010.03271 [16] Learning Binary Semantic Embedding for Histology Image Classification and Retrieval作者 | Xiao Kang, Xingbo Liu, Xiushan Nie, Yilong Yin連結 | https://arxiv.org/abs/2010.03266 [17] Variational Transfer Learning for Fine-grained Few-shot Visual Recognition作者 | Jingyi Xu, Mingzhen Huang, ShahRukh Athar, Dimitris Samaras連結 | https://arxiv.org/abs/2010.03255 [18] Learning Clusterable Visual Features for Zero-Shot Recognition作者 | Jingyi Xu, Zhixin Shu, Dimitris Samaras連結 | https://arxiv.org/abs/2010.03245 [19] RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition作者 | Yan Yang, Md Zakir Hossain, Tom Gedeon, Shafin Rahman連結 | https://arxiv.org/abs/2010.03203 [20] Vision-Based Object Recognition in Indoor Environments Using Topologically Persistent Features作者 | Ekta U. Samani, Xingjian Yang, Ashis G. Banerjee連結 | https://arxiv.org/abs/2010.03196 備註 | This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible[21] VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks作者 | Caren Han, Siqu Long, Siwen Luo, Kunze Wang, Josiah Poon連結 | https://arxiv.org/abs/2010.03182 備註 | Accepted by COLING 2020[22] A Study on Trees's Knots Prediction from their Bark Outer-Shape作者 | Mejri Mohamed, Antoine Richard, Cedric Pradalier連結 | https://arxiv.org/abs/2010.03173 備註 | arXiv admin note: text overlap with arXiv:2002.04571[23] DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval作者 | Yun Cao, Yuebin Wang, Junhuan Peng, Liqiang Zhang, Linlin Xu, Kai Yan, Lihua Li連結 | https://arxiv.org/abs/2010.03116 [24] SLCRF: Subspace Learning with Conditional Random Field for Hyperspectral Image Classification作者 | Yun Cao, Jie Mei, Yuebin Wang, Liqiang Zhang, Junhuan Peng, Bing Zhang, Lihua Li, Yibo Zheng連結 | https://arxiv.org/abs/2010.03115 [25] Channel Recurrent Attention Networks for Video Pedestrian Retrieval作者 | Pengfei Fang, Pan Ji, Jieming Zhou, Lars Petersson, Mehrtash Harandi連結 | https://arxiv.org/abs/2010.03108 備註 | To appear in ACCV 2020[26] Adversarial Patch Attacks on Monocular Depth Estimation Networks作者 | Koichiro Yamanaka, Ryutaroh Matsumoto, Keita Takahashi, Toshiaki Fujii連結 | https://arxiv.org/abs/2010.03072 項目連結 | https://www.fujii.nuee.nagoya-u.ac.jp/Research/MonoDepth/備註 | Publisher's Open Access PDF with the CC-BY copyright. [27] Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization作者 | Ashiq Imran, Vassilis Athitsos連結 | https://arxiv.org/abs/2010.03071 備註 | 18 pages, 12 figures, 4 tables[28] Weakly-Supervised Feature Learning via Text and Image Matching作者 | Gongbo Liang, Connor Greenwell, Yu Zhang, Xiaoqin Wang, Ramakanth Kavuluru, Nathan Jacobs連結 | https://arxiv.org/abs/2010.03060 [29] Rotate to Attend: Convolutional Triplet Attention Module作者 | Diganta Misra, Trikay Nalamada, Ajay Uppili Arasanipalai, Qibin Hou連結 | https://arxiv.org/abs/2010.03045 項目連結 | https://github.com/LandskapeAI/triplet-attention[30] A deep learning pipeline for identification of motor units in musculoskeletal ultrasound作者 | Hazrat Ali, Johannes Umander, Robin Rohlén, Christer Grönlund連結 | https://arxiv.org/abs/2010.03028 [31] Predicting Hourly Demand in Station-free Bike-sharing Systems with Video-level Data作者 | Xiao Yan, Gang Kou, Feng Xiao, Dapeng Zhang, Xianghua Gan連結 | https://arxiv.org/abs/2010.03027 備註 | 12 pages, 15 figures[32] Place Recognition in Forests with Urquhart Tessellations作者 | Guilherme V. Nardari, Avraham Cohen, Steven W. Chen, Xu Liu, Vaibhav Arcot, Roseli A. F. Romero, Vijay Kumar連結 | https://arxiv.org/abs/2010.03026 [33] Real-Time Resource Allocation for Tracking Systems作者 | Yash Satsangi, Shimon Whiteson, Frans A. Oliehoek, Henri Bouma連結 | https://arxiv.org/abs/2010.03024 [34] IS-CAM: Integrated Score-CAM for axiomatic-based explanations作者 | Rakshit Naidu, Ankita Ghosh, Yash Maurya, Shamanth R Nayak K, Soumya Snigdha Kundu連結 | https://arxiv.org/abs/2010.03023 [35] Global Self-Attention Networks for Image Recognition作者 | Zhuoran Shen, Irwan Bello, Raviteja Vemulapalli, Xuhui Jia, Ching-Hui Chen連結 | https://arxiv.org/abs/2010.03019 [36] Online Action Detection in Streaming Videos with Time Buffers作者 | Bowen Zhang, Hao Chen, Meng Wang, Yuanjun Xiong連結 | https://arxiv.org/abs/2010.03016 [37] Motion Prediction Using Temporal Inception Module作者 | Tim Lebailly, Sena Kiciroglu, Mathieu Salzmann, Pascal Fua, Wei Wang連結 | https://arxiv.org/abs/2010.03006 備註 | 16 pages, 4 figures. To appear in the proceedings of the 15th Asian Conference on Computer Vision, ACCV 2020[38] Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning作者 | Yannick Le Cacheux, Hervé Le Borgne, Michel Crucianu連結 | https://arxiv.org/abs/2010.02959 [39] Learning to Represent Image and Text with Denotation Graph作者 | Bowen Zhang, Hexiang Hu, Vihan Jain, Eugene Ie, Fei Sha連結 | https://arxiv.org/abs/2010.02949 備註 | to appear at EMNLP 2020[40] Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win作者 | Utku Evci, Yani A. Ioannou, Cem Keskin, Yann Dauphin連結 | https://arxiv.org/abs/2010.03533 備註 | sparse training, sparsity, pruning, lottery ticket hypothesis, lottery tickets, sparse initialization, initialization, deep learning, gradient flow[41] Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications作者 | Yue Yang, Pengtao Xie連結 | https://arxiv.org/abs/2010.03468 [42] Deep Neural Network: An Efficient and Optimized Machine Learning Paradigm for Reducing Genome Sequencing Error作者 | Ferdinand Kartriku, Dr. Robert Sowah, Charles Saah連結 | https://arxiv.org/abs/2010.03420 [43] Memory-efficient GAN-based Domain Translation of High Resolution 3D Medical Images作者 | Hristina Uzunova, Jan Ehrhardt, Heinz Handels連結 | https://arxiv.org/abs/2010.03396 備註 | Accepted for Computerized Medical Imaging and Graphics[44] Descriptive analysis of computational methods for automating mammograms with practical applications作者 | Aparna Bhale, Manish Joshi連結 | https://arxiv.org/abs/2010.03378 備註 | 33 pages and 2 Figures. A review paper of the research work related to mamography[45] Secure 3D medical Imaging連結 | https://arxiv.org/abs/2010.03367 備註 | 24 Pages, 4 Tables, 6 Figures[46] Batch Normalization Increases Adversarial Vulnerability: Disentangling Usefulness and Robustness of Model Features作者 | Philipp Benz, Chaoning Zhang, In So Kweon連結 | https://arxiv.org/abs/2010.03316 [47] Double Targeted Universal Adversarial Perturbations作者 | Philipp Benz, Chaoning Zhang, Tooba Imtiaz, In So Kweon連結 | https://arxiv.org/abs/2010.03288 備註 | Accepted at ACCV 2020[48] Low-Rank Robust Online Distance/Similarity Learning based on the Rescaled Hinge Loss作者 | Davood Zabihzadeh, Ali Karami-Mollaee連結 | https://arxiv.org/abs/2010.03268 備註 | An Online Distance-Similarity learning approach in noisy environment[49] A Novel Face-tracking Mouth Controller and its Application to Interacting with Bioacoustic Models作者 | Gamhewage C. de Silva, Tamara Smyth, Michael J. Lyons連結 | https://arxiv.org/abs/2010.03265 備註 | Proceedings of the International Conference on New Interfaces for Musical Expression, 2004 (NIME-04)[50] Deep Learning-Based Grading of Ductal Carcinoma In Situ in Breast Histopathology Images作者 | Suzanne C. Wetstein, Nikolas Stathonikos, Josien P.W. Pluim, Yujing J. Heng, Natalie D. ter Hoeve, Celien P.H. Vreuls, Paul J. van Diest, Mitko Veta連結 | https://arxiv.org/abs/2010.03244 [51] Sonification of Facial Actions for Musical Expression作者 | Mathias Funk, Kazuhiro Kuwabara, Michael J. Lyons連結 | https://arxiv.org/abs/2010.03223 備註 | Proceedings of the International Conference on New Interfaces for Musical Expression, 2005 (NIME-05)[52] Designing, Playing, and Performing with a Vision-based Mouth Interface作者 | Michael J. Lyons, Michael Haehnel, Nobuji Tetsutani連結 | https://arxiv.org/abs/2010.03213 備註 | Proceedings of the International Conference on New Interfaces for Musical Expression, 2003[53] M3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening from CT Imaging作者 | Xuelin Qian, Huazhu Fu, Weiya Shi, Tao Chen, Yanwei Fu, Fei Shan, Xiangyang Xue連結 | https://arxiv.org/abs/2010.03201 備註 | IEEE Journal of Biomedical and Health Informatics (JBHI), 2020[54] WDN: A Wide and Deep Network to Divide-and-Conquer Image Super-resolution作者 | Vikram Singh (1), Anurag Mittal (1) ((1) Indian Institute of Technology - Madras)連結 | https://arxiv.org/abs/2010.03199 [55] Conditional Generative Modeling via Learning the Latent Space作者 | Sameera Ramasinghe, Kanchana Ranasinghe, Salman Khan, Nick Barnes, Stephen Gould連結 | https://arxiv.org/abs/2010.03132 [56] A Fast and Effective Method of Macula Automatic Detection for Retina Images作者 | Yukang Jiang, Jianying Pan, Yanhe Shen, Jin Zhu, Jiamin Huang, Huirui Xie, Xueqin Wang, Yan Luo連結 | https://arxiv.org/abs/2010.03122 

相關焦點

  • 每日論文速遞:計算機視覺相關(12月18日更新版)
    出品 | 深度學習這件小事公眾號   計算機視覺
  • 每日論文速遞:計算機視覺相關(5月18日更新版)
    出品 | 深度學習這件小事公眾號   計算機視覺(5月19日更新版
  • 【Arxiv】每日論文速遞:自然語言處理相關(3月16日更新版)
    自然語言處理
  • 每日論文速遞:自然語言處理相關(1月13日更新版)
    出品 | 深度學習這件小事公眾號   自然語言處理(1月13日更新版
  • 2018最具突破性計算機視覺論文Top 10
    新智元報導 來源; topbots.com編輯:肖琴、三石【新智元導讀】本文總結了2018年以來最重要的10篇計算機視覺/圖像生成相關的研究,包括許多新穎的架構設計,圖像生成方面的突破等。自從卷積神經網絡在特定的圖像識別任務上開始超越人類以來,計算機視覺領域的研究一直在飛速發展。
  • 探索計算機視覺音頻的交叉—基於視覺的音樂相關研究Review
    本文作者分析了這一領域相較於純視覺領域的前景性所在,並且著重於實驗主要 conducted on 樂器和音樂數據的相關研究工作,從視覺引導的聲源分離、視覺引導的立體聲重構、視覺引導的音樂生成相關任務三個領域出發對相關研究成果進行介紹。相關Talk, 現可預約!
  • 《全面戰爭模擬器》4月8日更新內容一覽
    《全面戰爭模擬器》發售了一個多星期了,期間經歷了多次更新,而4月8日遊戲又更新了一次,很多玩家都不太清楚4月8日的更新內容都有什麼,今天小編就給大家帶來玩家「汙妖王303」分享的4月8日更新內容,希望能對大家有所幫助。
  • 方舟指令11月8日更新-結婚系統正式上線
    方舟指令11月8日更新-結婚系統正式上線 作者:佚名來源:方舟指令發布時間:2018-11-09 09:47:24 方舟指令更新公告,方舟指令更新內容,方舟指令結婚系統方舟指令11月8日更新-結婚系統正式上線方舟指令將於11月8日9:00~12:00對以下伺服器進行3小時的升級維護,本次維護更新內容如下:◢維護伺服器◣全體iOS伺服器、全體安卓伺服器◢維護補償◣體力×600金幣×1900◢更新內容◣■ 實裝『締結靈契』功能遊戲內將會永久新增『締結靈契
  • 騰訊優圖學術再進階 論文入選計算機視覺領頂級會議CVPR 2018
    據外媒報導,即將在6月美國鹽湖城舉行的計算機視覺頂級會議CVPR 2018,騰訊優圖的其中兩篇入選論文,由於其較高的應用價值,受到學術界和產業界的關注。騰訊優圖論文再次入庫頂級學術會議作為計算機視覺領域最高級別的會議之一的CVPR,其論文集通常代表著計算機視覺領域最新的發展方向和水平。這也是騰訊優圖繼2017年在另一計算機視覺頂級會議ICCV會議中獲得12篇論文被收錄,包含3篇口頭報告(該類論文僅佔總投稿數2.1%)的成績後,2018年,科研成果再次豐收,論文被CVPR2018收錄。
  • 全球計算機視覺頂會CVPR 2019論文出爐:騰訊優圖25篇論文入選
    全球計算機視覺頂級會議 IEEE CVPR 2019(Computer Vision and Pattern Recognition,即IEEE國際計算機視覺與模式識別會議) 即將於6月在美國長灘召開。本屆大會總共錄取來自全球論文1299篇。
  • 《Ryte: 亞特蘭蒂斯之眼》12月8日發布PC VR版
    沉浸式VR冒險遊戲《Ryte:亞特蘭蒂斯之眼》將於12月8日推出PC VR版。「《Ryte》是一款充滿想像力的作品,但我們試圖將我們的視覺世界儘可能地基於歷史元素。我們的設定主要是希臘風格,有波塞冬的雕像、神聖的公牛,但我們也在加入阿茲特克和埃及元素。為了讓玩家有那種敬畏和好奇的感覺,走到哪裡都有深深的陌生感,我們選擇在一片廣闊空曠的土地上,做一個向上蔓延的城市,天空中布滿了明亮的星星。
  • 計算機視覺/圖像處理學術速遞[10.08]
    點擊藍字↑關注公眾號,如有幫助, 點個「在看」哦cs.CV 方向,今日共計56篇 [檢測分類相關
  • arXiv 每日論文集 190 篇 02.19 更新
    今日 arXiv 論文集「今日 arXiv 論文集」是 AI 研習社論文板塊推出的全新欄目,每日為你自動抓取arXiv上更新的論文並且按照不同領域分類打包成集,方便社區用戶以最快的速度,最便捷的方式一件打包下載學術成果,獲取知識養分。
  • 西工大王鵬教授課題組論文被計算機視覺頂級會議CVPR2020錄用
    西工大新聞網2月26日電(王寧 高揚)2月24日,我校計算機學院王鵬教授課題組論文被2020年IEEE國際計算機視覺與模式識別會議(IEEE Conference on ComputerCVPR會議始於1983年,由IEEE舉辦,是計算機視覺和模式識別領域的頂級會議。今年CVPR共收到的投稿超過7000篇,有效論文投稿為6656篇,最終收錄數量為1470篇,收錄率為22.0%。
  • 它為什麼比計算機視覺更重要?
    總的來說,自然語言就是指人類社會互相默認同時又區別於人工語言的一門獨特的語言,它區別於計算機的語言,就像python等等,這些語言有著嚴格的格式,與人類的語言有著本質的區別。同時,縱觀人類文明史,所有人類歷史的記載和流傳,以及代代相傳的知識與科學文化藝術等,這些文字信息佔到人類全體知識總量的 80%以上。
  • 計算機視覺/圖像處理學術速遞[02.03]
    www.arxivdaily.com上線啦,論文摘要、多學科、收藏、評論、搜索……,點擊文末「
  • 騰訊優圖25篇論文入選全球頂級計算機視覺會議CVPR 2019
    全球計算機視覺頂級會議 IEEE CVPR 2019(Computer Vision and Pattern Recognition,即IEEE國際計算機視覺與模式識別會議) 即將於6月在美國長灘召開。本屆大會總共錄取來自全球論文1299篇。
  • 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
  • 一文帶你讀懂計算機視覺
    原文連結:https://towardsdatascience.com/learning-computer-vision-41398ad9941f最近,我已經閱讀了很多與計算機視覺相關的資料並做了大量實驗
  • HCP Lab 12篇論文入選世界頂級計算機視覺會議 CVPR 2019
    全球計算機視覺三大頂會之一 CVPR 2019 (IEEE Conference on Computer Visionand Pattern Recognition) 於 6月 16~20日 在美國洛杉磯如期舉辦。CVPR 作為計算機視覺三大頂級會議之一,一直以來都備受關注。被 CVPR 收錄的論文更是代表了計算機視覺領域的最新發展方向和水平。