同步公众号(arXiv每日论文速递),欢迎关注,感谢支持哦~
[检测分类相关]:
【1】 Dynamic Mode Decomposition based feature for Image Classification
基于动态模式分解特征的图像分类
作者: Rahul-Vigneswaran K, Sachin-Kumar S
备注:Selected for Spotlight presentation at TENCON 2019
链接:https://arxiv.org/abs/1910.03188
【2】 Sky pixel detection in outdoor imagery using an adaptive algorithm and machine learning
使用自适应算法和机器学习的室外图像中天空像素检测
作者: Kerry A. Nice, Jasper S. Wijnands
链接:https://arxiv.org/abs/1910.03182
【3】 xYOLO: A Model For Real-Time Object Detection In Humanoid Soccer On Low-End Hardware
xYOLO:一种基于低端硬件的仿人足球实时目标检测模型
作者: Daniel Barry, Munir Shah
链接:https://arxiv.org/abs/1910.03159
【4】 Deep Network classification by Scattering and Homotopy dictionary learning
基于散射和同伦字典学习的深层网络分类
作者: John Zarka, Louis Thiry
链接:https://arxiv.org/abs/1910.03561
【5】 Lossy Image Compression with Recurrent Neural Networks: from Human Perceived Visual Quality to Classification Accuracy
基于递归神经网络的有损图像压缩:从人类感知的视觉质量到分类精度
作者: Maurice Weber, Cedric Renggli
链接:https://arxiv.org/abs/1910.03472
[分割/语义相关]:
【1】 Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds
在3DLiDAR点云上利用深度“可移动”对象分割改进地图重新定位
作者: Victor Vaquero, Kai Fischer
链接:https://arxiv.org/abs/1910.03336
【2】 Eyenet: Attention based Convolutional Encoder-Decoder Network for Eye Region Segmentation
EyeNet:用于眼部区域分割的基于注意力的卷积编解码器网络
作者: Priya Kansal, Sabari Nathan
备注:To be appear in ICCVW 2019
链接:https://arxiv.org/abs/1910.03274
【3】 Lung nodule segmentation via level set machine learning
基于水平集机器学习的肺结节分割
作者: Matthew C Hancock, Jerry F Magnan
链接:https://arxiv.org/abs/1910.03191
[人脸相关]:
【1】 Defective samples simulation through Neural Style Transfer for automatic surface defect segment
用于表面缺陷自动分割的神经风格传递缺陷样本模拟
作者: Taoran Wei, Danhua Cao
备注:To be published in 2019 International Conference on Optical Instrument and Technology (OIT 2019)
链接:https://arxiv.org/abs/1910.03334
【2】 Self-Paced Deep Regression Forests for Facial Age Estimation
用于面部年龄估计的自定步长深度回归森林
作者: Shijie Ai, Yazhou Ren
链接:https://arxiv.org/abs/1910.03244
【3】 ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
ATFaceGAN:大气湍流中的单面图像恢复与识别
作者: Chun Pong Lau, Hossein Souri
链接:https://arxiv.org/abs/1910.03119
[行为/时空/光流/姿态/运动]:
【1】 Metric Pose Estimation for Human-Machine Interaction Using Monocular Vision
基于单目视觉的人机交互度量位姿估计
作者: Christoph Heindl, Markus Ikeda
备注:IROS 2019, Factory of the Future
链接:https://arxiv.org/abs/1910.03239
【2】 Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Rekall:使用时空标签合成指定视频事件
作者: Daniel Y. Fu, Will Crichton
链接:https://arxiv.org/abs/1910.02993
[半/弱/无监督相关]:
【1】 Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019
多源域适配和半监督域适配,重点关注视域适配挑战2019年
作者: Yingwei Pan, Yehao Li
备注:Rank 1 in Multi-Source Domain Adaptation of Visual Domain Adaptation Challenge (VisDA-2019). Source code of each task: this https URL and this https URL
链接:https://arxiv.org/abs/1910.03548
[跟踪相关]:
【1】 Real-time processing of high resolution video and 3D model-based tracking in remote tower operations
远程塔操作中高分辨率视频的实时处理和基于3D模型的跟踪
作者: Oliver J.D. Barrowclough, Sverre Briseid
链接:https://arxiv.org/abs/1910.03517
[视频理解VQA/caption等]:
【1】 Modulated Self-attention Convolutional Network for VQA
用于VQA的调制自注意卷积网络
作者: Jean-Benoit Delbrouck, Antoine Maiorca
备注:Accepted at NeurIPS 2019 workshop: ViGIL
链接:https://arxiv.org/abs/1910.03343
[3D/3D重建等相关]:
【1】 Improvements to Target-Based 3D LiDAR to Camera Calibration
基于目标的3DLiDAR对摄像机校准的改进
作者: Jiunn-Kai Huang, Jessy W. Grizzle
链接:https://arxiv.org/abs/1910.03126
[其他]:
【1】 Object-centric Forward Modeling for Model Predictive Control
模型预测控制的对象中心正向建模
作者: Yufei Ye, Dhiraj Gandhi
链接:https://arxiv.org/abs/1910.03568
【2】 When Does Self-supervision Improve Few-shot Learning?
自我监督何时能改善少发学习?
作者: Jong-Chyi Su, Subhransu Maji
备注:This is an updated version of "Boosting Supervision with Self-Supervision for Few-shot Learning" arXiv:1906.07079
链接:https://arxiv.org/abs/1910.03560
【3】 TraffickCam: Explainable Image Matching For Sex Trafficking Investigations
TraffickCam:用于性交易调查的可解释图像匹配
作者: Abby Stylianou, Richard Souvenir
备注:Presented at AAAI FSS-19: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA
链接:https://arxiv.org/abs/1910.03455
【4】 Refining 6D Object Pose Predictions using Abstract Render-and-Compare
使用抽象渲染和比较精化6D对象姿势预测
作者: Arul Selvam Periyasamy, Max Schwarz
备注:Accepted for IEEE-RAS International Conference on Humanoid Robots, Toronto, Canada, to appear October 2019
链接:https://arxiv.org/abs/1910.03412
【5】 Semi Few-Shot Attribute Translation
半少炮属性转换
作者: Ricard Durall, Franz-Josef Pfreundt
链接:https://arxiv.org/abs/1910.03240
【6】 Meta Module Network for Compositional Visual Reasoning
用于组合视觉推理的元模块网络
作者: Wenhu Chen, Zhe Gan
链接:https://arxiv.org/abs/1910.03230
【7】 Identifying Candidate Spaces for Advert Implantation
确定广告植入的候选空间
作者: Soumyabrata Dev, Hossein Javidnia
备注:Published in Proc. IEEE 7th International Conference on Computer Science and Network Technology, 2019
链接:https://arxiv.org/abs/1910.03227
【8】 The 'Paris-end' of town? Urban typology through machine learning
城市的“巴黎尽头”?基于机器学习的城市类型学
作者: Kerry A. Nice, Jason Thompson
链接:https://arxiv.org/abs/1910.03220
【9】 A Study on Wrist Identification for Forensic Investigation
司法鉴定中手腕鉴定的研究
作者: Wojciech Michal Matkowski, Frodo Kin Sun Chan
链接:https://arxiv.org/abs/1910.03213
【10】 Deep Multiphase Level Set for Scene Parsing
用于场景解析的深度多阶段级别集
作者: Pingping Zhang, Wei Liu
链接:https://arxiv.org/abs/1910.03166
【11】 GetNet: Get Target Area for Image Pairing
Getnet:获取图像配对的目标区域
作者: Henry H. Yu, Jiang Liu
备注:Accepted by Image and Vision Computing New Zealand (IVCNZ 2019)
链接:https://arxiv.org/abs/1910.03152
【12】 ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
ECA-net:深卷积神经网络的有效通道注意
作者: Qilong Wang, Banggu Wu
链接:https://arxiv.org/abs/1910.03151
【13】 DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
DexPilot:基于视觉的灵巧机器人手臂系统遥操作
作者: Ankur Handa, Karl Van Wyk
链接:https://arxiv.org/abs/1910.03135
【14】 Leveraging Vision Reconstruction Pipelines for Satellite Imagery
利用视觉重建流水线进行卫星图像
作者: Kai Zhang, Noah Snavely
链接:https://arxiv.org/abs/1910.02989
【15】 SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability
SMART:为机器人的可解释性培训浅记忆感知变压器
作者: Marcella Cornia, Lorenzo Baraldi
链接:https://arxiv.org/abs/1910.02974
【16】 Learning event representations in image sequences by dynamic graph embedding
通过动态图嵌入学习图像序列中的事件表示
作者: Mariella Dimiccoli, Herwig Wendt
链接:https://arxiv.org/abs/1910.03483
【17】 Model-based Behavioral Cloning with Future Image Similarity Learning
基于模型的行为克隆与未来图像相似性学习
作者: Alan Wu, AJ Piergiovanni
链接:https://arxiv.org/abs/1910.03157
【18】 CeliacNet: Celiac Disease Severity Diagnosis on Duodenal Histopathological Images Using Deep Residual Networks
CeliacNet:使用深层残差网络的十二指肠组织病理学图像上的腹腔疾病严重程度诊断
作者: Rasoul Sali, Lubaina Ehsan
备注:accepted at IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM 2019)
链接:https://arxiv.org/abs/1910.03084
【19】 Bregman-divergence-guided Legendre exponential dispersion model with finite cumulants (K-LED)
Bregman-发散引导的有限累积量Legendre指数色散模型(K-LED)
作者: Hyenkyun Woo
链接:https://arxiv.org/abs/1910.03025
【20】 Hyperspectral holography and spectroscopy: computational features of inverse discrete cosine transform
高光谱全息术和光谱学:离散余弦逆变换的计算特征
作者: Vladimir Katkovnik, Igor Shevkunov
备注:20 pages, 9 figures
链接:https://arxiv.org/abs/1910.03013
机器翻译,仅供参考
网友评论