计算机视觉每日论文速递[07.26]

同步wx订阅号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)

cs.CV 方向,今日共计49篇

[检测分类相关]:

【1】 MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification
MultiDepth:通过多任务回归和分类的单图像深度估计
作者: Lukas Liebel, Marco Körner
备注:Accepted for presentation at the IEEE Intelligent Transportation Systems Conference (ITSC) 2019
链接:https://arxiv.org/abs/1907.11111

【2】 Interpretability Beyond Classification Output: Semantic Bottleneck Networks
分类输出之外的可解释性:语义瓶颈网络
作者: Max Losch, Bernt Schiele
链接:https://arxiv.org/abs/1907.10882

【3】 Hard-Aware Fashion Attribute Classification
硬感知时尚属性分类
作者: Yun Ye, Tao Mei
链接:https://arxiv.org/abs/1907.10839

【4】 Accurate and Robust Eye Contact Detection During Everyday Mobile Device Interactions
在日常移动设备交互过程中准确且健壮的眼部接触检测
作者: Mihai Bâce, Andreas Bulling
链接:https://arxiv.org/abs/1907.11115

【5】 Simultaneous multi-view instance detection with learned geometric soft-constraints
具有学习几何软约束的同时多视图实例检测
作者: Ahmed Samy Nassar, Jan D. Wegner
备注:Internationcal Conference on Computer Vision 2019 (ICCV 19)
链接:https://arxiv.org/abs/1907.10892

【6】 Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification
综合增强和特征滤波用于改进的宫颈组织病理学图像分类
作者: Yuan Xue, Xiaolei Huang
备注:MICCAI 2019
链接:https://arxiv.org/abs/1907.10655

[分割/语义相关]:

【1】 Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems
导航辅助系统中基于金字塔上下文网络的重要性感知语义分割
作者: Kaite Xiang, Kailun Yang
备注:7 pages, 22 figures, IEEE Intelligent Transporation Systems Conference - ITSC 2019
链接:https://arxiv.org/abs/1907.11066

【2】 Cross Attention Network for Semantic Segmentation
用于语义分割的交叉注意网络
作者: Mengyu Liu, Hujun Yin
备注:Accepted in ICIP 2019
链接:https://arxiv.org/abs/1907.10958

【3】 ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation
ET-NET:一种用于医学图像分割的通用边缘注意引导网络
作者: Zhijie Zhang, Ling Shao
备注:MICCAI 2019
链接:https://arxiv.org/abs/1907.10936

【4】 Interpreting the Latent Space of GANs for Semantic Face Editing
语义人脸编辑中GANS潜在空间的解释
作者: Yujun Shen, Bolei Zhou
备注:19 pages, 19 figures
链接:https://arxiv.org/abs/1907.10786

【5】 SDNet: Semantically Guided Depth Estimation Network
SDNet:语义引导的深度估计网络
作者: Matthias Ochs, Rudolf Mester
备注:Paper is accepted at German Conference on Pattern Recognition (GCPR), Dortmund, Germany, September 2019
链接:https://arxiv.org/abs/1907.10659

【6】 Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation
用于联合模态完成和分割的异模态变分编解码器
作者: Reuben Dorent, Tom Vercauteren
备注:Accepted at MICCAI 2019
链接:https://arxiv.org/abs/1907.11150

【7】 Overfitting of neural nets under class imbalance: Analysis and improvements for segmentation
类不平衡下的神经网络过拟合:分割分析与改进
作者: Zeju Li, Ben Glocker
备注:Accepted at MICCAI 2019
链接:https://arxiv.org/abs/1907.10982

[GAN/对抗式/生成式相关]:

【1】 PU-GAN: a Point Cloud Upsampling Adversarial Network
PU-GAN:一个点云上采样对抗网络
作者: Ruihui Li, Pheng-Ann Heng
备注:accepted by ICCV2019, project page at this https URL
链接:https://arxiv.org/abs/1907.10844

【2】 Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
使用基于特征散射的对抗训练防御对抗攻击
作者: Haichao Zhang, Jianyu Wang
链接:https://arxiv.org/abs/1907.10764

【3】 Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks
联合对抗训练:合并空间攻击和像素攻击
作者: Haichao Zhang, Jianyu Wang
链接:https://arxiv.org/abs/1907.10737

【4】 Enhancing Adversarial Example Transferability with an Intermediate Level Attack
通过中级攻击增强对抗实例的可转移性
作者: Qian Huang, Ser-Nam Lim
备注:ICCV 2019. arXiv admin note: text overlap with arXiv:1811.08458
链接:https://arxiv.org/abs/1907.10823

[行为/时空/光流/姿态/运动]:

【1】 Submission to ActivityNet Challenge 2019: Task B Spatio-temporal Action Localization
向ActivityNet挑战2019年提交:任务B时空操作本地化
作者: Chunfei Ma, Seungji Yang
链接:https://arxiv.org/abs/1907.10837

[半/弱/无监督相关]:

【1】 Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
不要担心天气:无监督的条件依赖域适应
作者: Horia Porav, Paul Newman
备注:Presented at ITSC2019
链接:https://arxiv.org/abs/1907.11004

【2】 Self-supervised Domain Adaptation for Computer Vision Tasks
计算机视觉任务的自监督域自适应
作者: Jiaolong Xu, Antonio M. Lopez
链接:https://arxiv.org/abs/1907.10915

【3】 U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
U-GAT-IT:用于图像到图像翻译的具有自适应层实例归一化的无监督生成性注意网络
作者: Junho Kim, Kwanghee Lee
链接:https://arxiv.org/abs/1907.10830

【4】 Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking
用于单目跟踪的高保真度人脸模型的自监督自适应
作者: Jae Shin Yoon, Hyun Soo Park
备注:This work is accepted by CVPR 2019
链接:https://arxiv.org/abs/1907.10815

【5】 Unsupervised Domain Adaptation via Calibrating Uncertainties
通过校准不确定性的无监督域自适应
作者: Ligong Han, Dimitris Metaxas
链接:https://arxiv.org/abs/1907.11202

【6】 Weakly Supervised Recognition of Surgical Gestures
手术手势的弱监督识别
作者: Beatrice van Amsterdam, Danail Stoyanov
备注:2019 IEEE International Conference on Robotics and Automation (ICRA)
链接:https://arxiv.org/abs/1907.10993

[跟踪相关]:

【1】 Towards Generalizing Sensorimotor Control Across Weather Conditions
向推广跨越天气条件的传感器运动控制
作者: Qadeer Khan, Laura Leal-Taixé
备注:Accepted for publication in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
链接:https://arxiv.org/abs/1907.11025

[迁移学习/domain/主动学习相关]:

【1】 Curriculum based Dropout Discriminator for Domain Adaptation
用于领域适应的基于课程的Dropout鉴别器
作者: Vinod Kumar Kurmi, Vinay P Namboodiri
备注:BMVC 2019 Accepted, Project Page: this https URL
链接:https://arxiv.org/abs/1907.10628

[裁剪/量化/加速相关]:

【1】 Co-Evolutionary Compression for Unpaired Image Translation
用于不配对图像平移的协同进化压缩
作者: Han Shu, Chang Xu
备注:Accepted by ICCV 2019
链接:https://arxiv.org/abs/1907.10804

[Re-id相关]:

【1】 Learning Resolution-Invariant Deep Representations for Person Re-Identification
学习分解-用于个人重新识别的不变深度表示
作者: Yun-Chun Chen, Yu-Chiang Frank Wang
备注:Accepted to AAAI 2019 (Oral)
链接:https://arxiv.org/abs/1907.10843

[其他]:

【1】 Learning Visual Actions Using Multiple Verb-Only Labels
使用多个仅限动词的标签学习视觉动作
作者: Michael Wray, Dima Damen
备注:Accepted at BMVC 2019. Annotations can be found at this https URL
链接:https://arxiv.org/abs/1907.11117

【2】 SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications
SlimYOLOv3:更窄,更快,更好的实时无人机应用
作者: Pengyi Zhang, Xiaoqiong Li
链接:https://arxiv.org/abs/1907.11093

【3】 Enhancing Underexposed Photos using Perceptually Bidirectional Similarity
利用感知双向相似性增强曝光不足的照片
作者: Qing Zhang, Wei-Shi Zheng
链接:https://arxiv.org/abs/1907.10992

【4】 Y-Autoencoders: disentangling latent representations via sequential-encoding
Y-自动编码器:通过顺序编码解除潜在表示的纠缠
作者: Massimiliano Patacchiola, Edward Rosten
链接:https://arxiv.org/abs/1907.10949

【5】 Convolutional Neural Networks on Randomized Data
随机数据的卷积神经网络
作者: Cristian Ivan
备注:8 pages, 17 figures, presented at Deep-Vision workshop, CVPR 2019
链接:https://arxiv.org/abs/1907.10935

【6】 Closing the Gap between Deep and Conventional Image Registration using Probabilistic Dense Displacement Networks
利用概率稠密位移网络缩小深度图像配准与常规图像配准之间的差距
作者: Mattias P. Heinrich
备注:accepted for publication at MICCAI 2019, open source code available at this https URL
链接:https://arxiv.org/abs/1907.10931

【7】 How to Manipulate CNNs to Make Them Lie: the GradCAM Case
如何操纵CNN使其说谎:GradCAM案例
作者: Tom Viering, Elmar Eisemann
链接:https://arxiv.org/abs/1907.10901

【8】 A Compact Light Field Camera for Real-Time Depth Estimation
一种用于实时深度估计的紧凑型光场相机
作者: Yuriy Anisimov, Didier Stricker
备注:The 18th International Conference on Computer Analysis of Images and Patterns, Salerno, 2-6 September, 2019
链接:https://arxiv.org/abs/1907.10880

【9】 A Fine-Grained Facial Expression Database for End-to-End Multi-Pose Facial Expression Recognition
一种用于端到端多姿态人脸表情识别的细粒度人脸表情数据库
作者: Wenxuan Wang, Yanwei Fu
链接:https://arxiv.org/abs/1907.10838

【10】 Composition-Aware Image Aesthetics Assessment
构图意识的图像美学评价
作者: Dong Liu, Subhabrata Bhattachary
链接:https://arxiv.org/abs/1907.10801

【11】 One-stage Shape Instantiation from a Single 2D Image to 3D Point Cloud
从单个2D图像到3D点云的一阶段形状实例化
作者: Xiao-Yun Zhou, Guang-Zhong Yang
备注:8.5 pages, 5 figures, MICCAI 2019
链接:https://arxiv.org/abs/1907.10763

【12】 LayoutVAE: Stochastic Scene Layout Generation from a Label Set
LayoutVAE:从标签集生成随机场景布局
作者: Akash Abdu Jyothi, Greg Mori
备注:10 pages, 6 figures, accepted in ICCV 2019
链接:https://arxiv.org/abs/1907.10719

【13】 Uncalibrated Deflectometry with a Mobile Device on Extended Specular Surfaces
在扩展镜面上使用移动设备的未校准验光仪
作者: Florian Willomitzer, Oliver Cossairt
链接:https://arxiv.org/abs/1907.10700

【14】 Dual Grid Net: hand mesh vertex regression from single depth maps
双重网格网:单深度图的手工网格顶点回归
作者: Chengde Wan, Angela Yao
链接:https://arxiv.org/abs/1907.10695

【15】 Deep Differentiable Random Forests for Age Estimation
用于年龄估计的深层可微随机森林
作者: Wei Shen, Alan Yuille
备注:arXiv admin note: substantial text overlap with arXiv:1712.07195
链接:https://arxiv.org/abs/1907.10665

【16】 Semi-parametric Object Synthesis
半参数对象综合
作者: Andrea Palazzi, Rita Cucchiara
链接:https://arxiv.org/abs/1907.10634

【17】 HUGE2: a Highly Untangled Generative-model Engine for Edge-computing
HUGE2:一个用于边缘计算的高度解缠的生成模型引擎
作者: Feng Shi, Song-Chun Zhu
链接:https://arxiv.org/abs/1907.11210

【18】 How far are we from quantifying visual attention in mobile HCI?
我们离量化移动HCI中的视觉注意力还有多远?
作者: Mihai Bâce, Andreas Bulling
链接:https://arxiv.org/abs/1907.11106

【19】 Is Texture Predictive for Age and Sex in Brain MRI?
脑部MRI中纹理对年龄和性别的预测吗?
作者: Nick Pawlowski, Ben Glocker
链接:https://arxiv.org/abs/1907.10961

【20】 Performance Evaluation of Two-layer lossless HDR Coding using Histogram Packing Technique under Various Tone-mapping Operators
使用直方图打包技术的两层无损HDR编码在不同色调映射算子下的性能评估
作者: Hiroyuki Kobayashi, Hitoshi Kiya
备注:to appear in 2019 IEEE 8th Global Conference on Consumer Electronics
链接:https://arxiv.org/abs/1907.10889

【21】 Safe Feature Elimination for Non-Negativity Constrained Convex Optimization
非负约束凸优化的安全特征消除
作者: James Folberth, Stephen Becker
链接:https://arxiv.org/abs/1907.10831

翻译:腾讯翻译君

你可能感兴趣的:(计算机视觉每日论文速递[07.26])