深度学习-推荐系统-CV-NLParXiv daily

计算机视觉每日论文速递[08.23]

2019-08-24  本文已影响22人  arXiv每日论文速递

同步公众号(arXiv每日论文速递),回复'search 关键词'查询相关最新论文。(* ̄rǒ ̄)

cs.CV 方向,今日共计39篇

[检测分类相关]:

【1】 EGNet:Edge Guidance Network for Salient Object Detection
EGNet:用于凸起目标检测的边缘引导网络
作者: Jia-Xing Zhao, Ming-Ming Cheng
链接:https://arxiv.org/abs/1908.08297

【2】 Object detection on aerial imagery using CenterNet
基于Centernet的航空影像目标检测
作者: Dheeraj Reddy Pailla, Sai Saketh Chennamsetty
链接:https://arxiv.org/abs/1908.08244

【3】 Multi-Stream Single Shot Spatial-Temporal Action Detection
多流单镜头时空动作检测
作者: Pengfei Zhang, Benyuan Liu
链接:https://arxiv.org/abs/1908.08178

【4】 Multiple instance dense connected convolution neural network for aerial image scene classification
航空影像场景分类的多实例稠密连接卷积神经网络
作者: Qi Bi, Kai Xu
备注:5 pages,3 figures, a conference paper accepted by IEEE ICIP 2019
链接:https://arxiv.org/abs/1908.08156

【5】 Contour Detection in Cassini ISS images based on Hierarchical Extreme Learning Machine and Dense Conditional Random Field
基于分层极值学习机和稠密条件随机场的卡西尼ISS图像轮廓检测
作者: Xiqi Yang, Zhan Li
链接:https://arxiv.org/abs/1908.08279

【6】 A CNN toolbox for skin cancer classification
CNN皮肤癌分类工具箱
作者: Fabrizio Nunnari, Daniel Sonntag
链接:https://arxiv.org/abs/1908.08187

【7】 Building change detection based on multi-scale filtering and grid partition
基于多尺度滤波和网格划分的建筑物变化检测
作者: Qi Bi, Kai Xu
链接:https://arxiv.org/abs/1908.08164

【8】 Transferability and Hardness of Supervised Classification Tasks
监督分类任务的可移植性和硬度
作者: Anh T. Tran, Tal Hassner
备注:This paper is published at the International Conference on Computer Vision (ICCV) 2019
链接:https://arxiv.org/abs/1908.08142

[分割/语义相关]:

【1】 Uncertainty-Guided Domain Alignment for Layer Segmentation in OCT Images
不确定导引的OCT图像层分割区域对齐方法
作者: Jiexiang Wang, Yefeng Zheng
链接:https://arxiv.org/abs/1908.08242

【2】 Optimal input configuration of dynamic contrast enhanced MRI in convolutional neural networks for liver segmentation
用于肝脏分割的卷积神经网络动态增强MRI的最优输入配置
作者: Mariëlle J.A. Jansen, Josien P.W. Pluim
备注:Submitted to SPIE Medical Imaging 2019
链接:https://arxiv.org/abs/1908.08251

【3】 Boundary Aware Networks for Medical Image Segmentation
边界感知网络在医学图像分割中的应用
作者: Ali Hatamizadeh, Andriy Myronenko
备注:Accepted to Machine Learning in Medical Imaging (MLMI 2019)
链接:https://arxiv.org/abs/1908.08071

【4】 More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation
更多未标记的数据或标记更多数据?半监督腹腔镜图像分割的研究
作者: Yunguan Fu, Yipeng Hu
备注:Accepted to MICCAI MIL3ID 2019
链接:https://arxiv.org/abs/1908.08035

[GAN/对抗式/生成式相关]:

【1】 Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement
基于对抗性的多模型集成和噪声数据精化的知识提取
作者: Zhiqiang Shen, Marios Savvides
备注:This is an extended version of our previous conference paper arXiv:1812.02425
链接:https://arxiv.org/abs/1908.08520

【2】 Saliency Methods for Explaining Adversarial Attacks
解释对抗攻击的显着性方法
作者: Jindong Gu, Volker Tresp
链接:https://arxiv.org/abs/1908.08413

[行为/时空/光流/姿态/运动]:
【1】 Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets
基于体积网的3D关节模型动画骨架预测
作者: Zhan Xu, Karan Singh
备注:3DV 2019
链接:https://arxiv.org/abs/1908.08506

【2】 Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation
基于深度视频的三维人体姿态估计的轨迹空间分解
作者: Jiahao Lin, Gim Hee Lee
备注:13 pages, 5 figures. Accepted in BMVC 2019
链接:https://arxiv.org/abs/1908.08289

【3】 Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance from Motion
Pro-CAM SSFM:用于结构和光谱反射比的投影仪-摄像机系统
作者: Chunyu Li, Masatoshi Okutomi
备注:Accepted by ICCV 2019. Project homepage: this http URL
链接:https://arxiv.org/abs/1908.08185

【4】 Motion correction of dynamic contrast enhanced MRI of the liver
肝脏动态增强MRI的运动校正
作者: Mariëlle J.A. Jansen, Josien P.W. Pluim
链接:https://arxiv.org/abs/1908.08254

[半/弱/无监督相关]:
【1】 3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
3C-NET:弱监督操作定位的类别计数和中心损失
作者: Sanath Narayan, Ling Shao
备注:To appear in ICCV 2019
链接:https://arxiv.org/abs/1908.08216

[视频理解VQA/caption等]:
【1】 Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning
用于不同图像字幕中意图建模的顺序潜在空间
作者: Jyoti Aneja, Alexander Schwing
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.08529

[超分辨率]:
【1】 Progressive Face Super-Resolution via Attention to Facial Landmark
通过关注人脸地标的渐进式人脸超分辨率
作者: Deokyun Kim, Dae-Shik Kim
备注:BMVC 2019 Accepted
链接:https://arxiv.org/abs/1908.08239

[点云]:
【1】 Globally optimal registration of noisy point clouds
噪声点云的全局最优配准
作者: Rangaprasad Arun Srivatsan, Howie Choset
链接:https://arxiv.org/abs/1908.08162

[深度depth相关]:
【1】 Indoor Depth Completion with Boundary Consistency and Self-Attention
具有边界一致性和自我关注的室内深度完成
作者: Yu-Kai Huang, Winston H. Hsu
备注:Accepted by RLQ2019 @ ICCV 2019
链接:https://arxiv.org/abs/1908.08344

[人脸相关]:
【1】 Scoot: A Perceptual Metric for Facial Sketches
SCOOT:面部草图的感知度量
作者: Deng-Ping Fan, Rongrong Ji
备注:Code & dataset:this http URL, 11 pages, ICCV 2019, First one good evaluation metric for facial sketh that consistent with human judgment. arXiv admin note: text overlap with arXiv:1804.02975
链接:https://arxiv.org/abs/1908.08433

[其他视频相关]:
【1】 Compositional Video Prediction
合成视频预测
作者: Yufei Ye, Shubham Tulsiani
备注:accepted to ICCV19
链接:https://arxiv.org/abs/1908.08522

[其他]:
【1】 VL-BERT: Pre-training of Generic Visual-Linguistic Representations
VL-BERT:类属视觉语言表征的预训练
作者: Weijie Su, Jifeng Dai
链接:https://arxiv.org/abs/1908.08530

【2】 ViCo: Word Embeddings from Visual Co-occurrences
VICO:来自视觉共现的单词嵌入
作者: Tanmay Gupta, Derek Hoiem
备注:Accepted to ICCV 2019. Project Page: this http URL
链接:https://arxiv.org/abs/1908.08527

【3】 EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition
EPIC-Fusion:用于自我中心行为识别的视听时间绑定
作者: Evangelos Kazakos, Dima Damen
备注:Accepted for presentation at ICCV 2019
链接:https://arxiv.org/abs/1908.08498

【4】 Noise Flow: Noise Modeling with Conditional Normalizing Flows
噪声流:使用条件归一化流的噪声建模
作者: Abdelrahman Abdelhamed, Michael S. Brown
链接:https://arxiv.org/abs/1908.08453

【5】 Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks
改进卷积神经网络显着性的深层格林函数卷积
作者: Dominique Beaini, Maxime Raison
链接:https://arxiv.org/abs/1908.08331

【6】 Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
mask TextSpotter:一个端到端可训练的神经网络用于任意形状的文本识别
作者: Minghui Liao, Xiang Bai
链接:https://arxiv.org/abs/1908.08207

【7】 U-Net Training with Instance-Layer Normalization
具有实例层规范化的U-NET训练
作者: Xiao-Yun Zhou, Guang-Zhong Yang
备注:8 pages, 3 figures, accepted by MICCAI-MMMI 2019 workshop
链接:https://arxiv.org/abs/1908.08466

【8】 Improved MR to CT synthesis for PET/MR attenuation correction using Imitation Learning
利用模仿学习改进的用于PET/MR衰减校正的MR to CT合成
作者: Kerstin Kläser, Sebastien Ourselin
备注:Aceppted at SASHIMI2019
链接:https://arxiv.org/abs/1908.08431

【9】 Image Colorization By Capsule Networks
基于胶囊网络的图像着色
作者: Gökhan Özbulak
备注:Accepted to New Trends in Image Restoration and Enhancement(NTIRE) Workshop at CVPR 2019
链接:https://arxiv.org/abs/1908.08307

【10】 NL-LinkNet: Toward Lighter but More Accurate Road Extraction with Non-Local Operations
NL-LinkNet:通过非本地操作实现更轻但更精确的道路提取
作者: Yooseung Wang, Taegyun Jeon
链接:https://arxiv.org/abs/1908.08223

【11】 BIM-assisted object recognition for the on-site autonomous robotic assembly of discrete structures
BIM辅助的离散结构现场自主机器人装配对象识别
作者: Mohamed Dawod, Sean Hanna
链接:https://arxiv.org/abs/1908.08209

【12】 An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures
一种用于空间变化曝光的单次激发高动态范围成像的图像融合方案
作者: Chihiro Go, Hitoshi Kiya
链接:https://arxiv.org/abs/1908.08195

【13】 DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer
双辉光:基于条件流的模态转换生成模型
作者: Haoliang Sun, Vikas Singh
链接:https://arxiv.org/abs/1908.08074

【14】 InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
InSituNet:用于集成仿真参数空间探索的深度图像合成
作者: Wenbin He, Tom Peterka
链接:https://arxiv.org/abs/1908.00407

翻译:腾讯翻译君

上一篇下一篇

猜你喜欢

热点阅读