计算机视觉/图像处理论文速递[11.13]

格林先生MrGreen arXiv每日学术速递
点击蓝字↑关注公众号,如有帮助, 点个“在看”哦
cs.CV 方向,今日共计28篇

[检测分类相关]:

【1】 Pose Guided Attention for Multi-label Fashion Image Classification

标题:姿态引导注意在多标签服装图像分类中的应用

作者: Beatriz Quintino Ferreira, João P. Gomes
备注:Published at ICCV 2019 Workshop on Computer Vision for Fashion, Art and Design
链接:arxiv.org/abs/1911.05024 

【2】 Combined analysis of coronary arteries and the left ventricular myocardium in cardiac CT angiography for detection of patients with functionally significant stenosis

标题:心脏CT血管造影中冠状动脉和左心室心肌的联合分析用于功能显着狭窄患者的检测

作者: Majd Zreik, Ivana Išgum
备注:Submitted to IEEE Access. arXiv admin note: text overlap with arXiv:1906.04419
链接:arxiv.org/abs/1911.04940

【3】 SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

标题:SimpleShot:重温最近邻分类的几次学习

作者: Yan Wang, Laurens van der Maaten
链接:arxiv.org/abs/1911.04623

【4】 ContamiNet: Detecting Contamination in Municipal Solid Waste

标题:ContamiNet:检测城市固体废物中的污染

作者: Khoury Ibrahim, Yannet Interian
备注:8 pages, 3 figures, ICMLA 2020
链接:arxiv.org/abs/1911.04583

【5】 Deep Variational Semi-Supervised Novelty Detection

标题:深变分半监督新颖性检测

作者: Tal Daniel, Aviv Tamar
链接:arxiv.org/abs/1911.04971

[分割/语义相关]:

【1】 Equalization Loss for Large Vocabulary Instance Segmentation

标题:大词汇量实例切分的均衡损失

作者: Jingru Tan, Junjie Yan
备注:Technical Report. Winner of LVIS Challenge 2019
链接:arxiv.org/abs/1911.04692

【2】 Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation

标题:基于骨架的深度对齐卷积神经网络动作识别与分割

作者: Babak Hosseini, Barbara Hammer
备注:19th IEEE International Conference on Data Mining (ICDM 2019)
链接:arxiv.org/abs/1911.04969

【3】 Exploiting Clinically Available Delineations for CNN-based Segmentation in Radiotherapy Treatment Planning

标题:在放射治疗计划中利用临床上可用的基于CNN的分割方法

作者: Louis D. van Harten, Ivana Išgum
备注:SPIE Medical Imaging 2020
链接:arxiv.org/abs/1911.04967

[人脸相关]:

【1】 Recognizing Facial Expressions of Occluded Faces using Convolutional Neural Networks

标题:基于卷积神经网络的闭塞人脸表情识别

作者: Mariana-Iuliana Georgescu, Radu Tudor Ionescu
备注:Accepted at ICONIP 2019
链接:arxiv.org/abs/1911.04852

【2】 Data-Free Point Cloud Network for 3D Face Recognition

标题:用于三维人脸识别的无数据点云网络

作者: Ziyu, Yu
链接:arxiv.org/abs/1911.04731

[图像/视频检索]:

【1】 Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval

标题:用于基于草图的图像检索的半异构三向联合嵌入网络

作者: Jianjun Lei, Yi-Zhe Song
链接:arxiv.org/abs/1911.04470

[跟踪相关]:

【1】 A Proposed Artificial intelligence Model for Real-Time Human Action Localization and Tracking

标题:一种用于实时人体动作定位和跟踪的人工智能模型

作者: Ahmed Ali Hammam, Aboul Ella Hassanien
链接:arxiv.org/abs/1911.04469

[迁移学习/domain/主动学习/自适应]:

【1】 OntoScene, A Logic-based Scene Interpreter: Implementation and Application in the Rock Art Domain

标题:OntoScene,一个基于逻辑的场景解释器:在岩石艺术领域的实现和应用

作者: Daniela Briola, Massimiliano Gioseffi
链接:arxiv.org/abs/1911.04863

[Re-id相关]:

【1】 Wi-Fi Passive Person Re-Identification based on Channel State Information

标题:基于信道状态信息的Wi-Fi被动身份再识别

作者: Danilo Avola, Daniele Pannone
链接:arxiv.org/abs/1911.04900

[3D/3D重建等相关]:

【1】 Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research

标题:高岭土:加速三维深度学习研究的PyTorch库

作者: Krishna Murthy Jatavallabhula, Tommy Xiang
链接:arxiv.org/abs/1911.05063

[其他]:

【1】 Experience-Embedded Visual Foresight

标题:体验-嵌入式视觉预见

作者: Lin Yen-Chen, Phillip Isola
备注:CoRL 2019. Project website: this http URL
链接:arxiv.org/abs/1911.05071

【2】 Comparing pattern sensitivity of a convolutional neural network with an ideal observer and support vector machine

标题:卷积神经网络与理想观测器和支持向量机模式灵敏度的比较

作者: Fabian Reith, Brian Wandell
链接:arxiv.org/abs/1911.05055

【3】 Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks

标题:卷积神经网络中的可训练谱可初始化矩阵变换

作者: Michele, Seuret
链接:arxiv.org/abs/1911.05045

【4】 Visual cryptography in single-pixel imaging

标题:单像素成像中的视觉加密

作者: Shuming Jiao, Xiaocong Yuan
链接:arxiv.org/abs/1911.05033

【5】 Recursive Filter for Space-Variant Variance Reduction

标题:用于空间变方差缩减的递归滤波器

作者: Alexander Zamyatin
链接:arxiv.org/abs/1911.04992

【6】 Multi-hop Convolutions on Weighted Graphs

标题:加权图上的多跳卷积

作者: Qikui Zhu, Pingkun Yan
链接:arxiv.org/abs/1911.04978

【7】 Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Neural Networks

标题:无斑网的永恒阳光:深层神经网络中的选择性遗忘

作者: Aditya Golatkar, Stefano Soatto
链接:arxiv.org/abs/1911.04933

【8】 Grouping Capsules Based Different Types

标题:基于不同类型的胶囊分组

作者: Qiang Ren
链接:arxiv.org/abs/1911.04820

【9】 A Probabilistic Approach for Predicting Landslides by Learning a Self-Aligned Deep Convolutional Model

标题:通过学习自对准深卷积模型预测滑坡的概率方法

作者: Ainaz Hajimoradlou, David Poole
备注:9 pages, 7 figures (2 figure* that contain multiple subfigures), 2 tables, submitted to AISTAT 2020 (under review)
链接:arxiv.org/abs/1911.04651

【10】 Geometry-Aware Neural Rendering

标题:几何感知神经渲染

作者: Josh Tobin, Pieter Abbeel
链接:arxiv.org/abs/1911.04554

【11】 Automatic Online Quality Control of Synthetic CTs

标题:合成CTS的自动在线质量控制

作者: Louis D. van Harten, Ivana Išgum
备注:SPIE Medical Imaging 2020
链接:arxiv.org/abs/1911.04986

【12】 Recurrent Neural Network Transducer for Audio-Visual Speech Recognition

标题:用于视听语音识别的递归神经网络换能器

作者: Takaki Makino (1), Olivier Siohan (1) ((1) Google Inc. (2) DeepMind)
备注:Will be presented in 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019)
链接:arxiv.org/abs/1911.04890

【13】 Merging-ISP: Multi-Exposure High Dynamic Range Image Signal Processing

标题:Merging-ISP:多曝光高动态范围图像信号处理

作者: Prashant Chaudhari, Thomas Köhler
备注:8 pages, 6 figures, 2 tables, WACV-2020 conference
链接:arxiv.org/abs/1911.04762

机器翻译,仅供参考

文章推荐