计算机视觉每日论文速递[07.16]

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44篇

[检测分类相关]:

【1】 Detecting and Simulating Artifacts in GAN Fake Images
GaN伪图像中伪影的检测与仿真
作者: Xu Zhang, Shih-Fu Chang
链接:https://arxiv.org/abs/1907.06515

【2】 Sequence Level Semantics Aggregation for Video Object Detection
用于视频对象检测的序列级语义聚合
作者: Haiping Wu, Zhaoxiang Zhang
链接:https://arxiv.org/abs/1907.06390

【3】 Multimodal deep networks for text and image-based document classification
用于基于文本和图像的文档分类的多模态深度网络
作者: Nicolas Audebert, Cédric Vidal
链接:https://arxiv.org/abs/1907.06370

【4】 FoodX-251: A Dataset for Fine-grained Food Classification
FoodX-251:一个用于细粒度食品分类的数据集
作者: Parneet Kaur, Ajay Divakaran
备注:Published at Fine-Grained Visual Categorization Workshop, CVPR19
链接:https://arxiv.org/abs/1907.06167

【5】 ALFA: Agglomerative Late Fusion Algorithm for Object Detection
ALFA:用于目标检测的凝聚后期融合算法
作者: Evgenii Razinkov, Jiři Matas
备注:E. Razinkov, I. Saveleva and J. Matas, "ALFA: Agglomerative Late Fusion Algorithm for Object Detection," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, 2018, pp. 2594-2599
链接:https://arxiv.org/abs/1907.06067

【6】 M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
M3D-RPN:用于物体检测的单目3D区域建议网络
作者: Garrick Brazil, Xiaoming Liu
链接:https://arxiv.org/abs/1907.06038

【7】 A Conditional Wasserstein Generative Adversarial Network for Pixel-level Crack Detection using Video Extracted Images
利用视频提取图像进行像素级裂纹检测的条件Wasserstein生成对抗网络
作者: Qipei Mei, Mustafa Gül
链接:https://arxiv.org/abs/1907.06014

【8】 Exploring Deep Anomaly Detection Methods Based on Capsule Net
基于胶囊网的深度异常检测方法探索
作者: Xiaoyan Li, Yifeng Li
备注:Presented in the "ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning", June 14, Long Beach, California, USA
链接:https://arxiv.org/abs/1907.06312

【9】 Image Evolution Trajectory Prediction and Classification from Baseline using Learning-based Patch Atlas Selection for Early Diagnosis
基于学习的补丁图集选择用于早期诊断的基线图像演化轨迹预测和分类
作者: Can Gafuroglu, Islem Rekik
链接:https://arxiv.org/abs/1907.06064

[分割/语义相关]:

【1】 CA-RefineNet:A Dual Input WSI Image Segmentation Algorithm Based on Attention
CA-RefineNet:一种基于注意力的双输入WSI图像分割算法
作者: Ziqiang Li, Bin Li
链接:https://arxiv.org/abs/1907.06358

【2】 Understanding Deep Learning Techniques for Image Segmentation
理解图像分割的深度学习技术
作者: Swarnendu Ghosh, Ujjwal Maulik
链接:https://arxiv.org/abs/1907.06119

【3】 Motion Segmentation Using Locally Affine Atom Voting
基于局部仿射原子投票的运动分割
作者: Erez Posner, Rami Hagege
链接:https://arxiv.org/abs/1907.06091

【4】 Adaptive Context Encoding Module for Semantic Segmentation
用于语义分割的自适应上下文编码模块
作者: Congcong Wang, Ole Jakob Elle
链接:https://arxiv.org/abs/1907.06082

[GAN/对抗式/生成式相关]:

【1】 Recovery Guarantees for Compressible Signals with Adversarial Noise
具有对抗性噪声的可压缩信号的恢复保证
作者: Jasjeet Dhaliwal, Kyle Hambrook
链接:https://arxiv.org/abs/1907.06565

【2】 Measuring the Transferability of Adversarial Examples
衡量对抗实例的可转移性
作者: Deyan Petrov, Timothy M. Hospedales
链接:https://arxiv.org/abs/1907.06291

[行为/时空/光流/姿态/运动]:

【1】 FastV2C-HandNet: Fast Voxel to Coordinate Hand Pose Estimation with 3D Convolutional Neural Networks
FastV2C-HandNet:快速体素与3D卷积神经网络协调手势估计
作者: Rohan Lekhwani
备注:7 pages, 5 figures, 2 tables. Submitted to WACV 2020
链接:https://arxiv.org/abs/1907.06327

[半/弱/无监督相关]:

【1】 Unsupervised Automatic Building Extraction Using Active Contour Model on Unregistered Optical Imagery and Airborne LiDAR Data
基于未注册光学图像和机载LiDAR数据的主动轮廓模型的无监督自动建筑物提取
作者: Thanh Huy Nguyen, Jean-Marc Le Caillec
备注:PIA19 - Photogrammetric Image Analysis 2019 which will be held in conjunction with MRSS19 - Munich Remote Sensing Symposium 2019 on September 18th-20th, 2019 in Munich, Germany. Proceeding: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
链接:https://arxiv.org/abs/1907.06206

[跟踪相关]:

【1】 Perceptually Motivated Method for Image Inpainting Comparison
基于感知激励的图像修复比较方法
作者: Ivan Molodetskikh, Dmitry Vatolin
链接:https://arxiv.org/abs/1907.06296

[Re-id相关]:

【1】 An Efficient Framework for Visible-Infrared Cross Modality Person Re-Identification
一种有效的可见光-红外交叉模态人再识别框架
作者: Emrah Basaran, Mustafa E. Kamasak
链接:https://arxiv.org/abs/1907.06498

[数据集dataset]:

【1】 Efficient Video Generation on Complex Datasets
复杂数据集上高效的视频生成
作者: Aidan Clark, Karen Simonyan
链接:https://arxiv.org/abs/1907.06571

【2】 Quick, Stat!: A Statistical Analysis of the Quick, Draw! Dataset
快,统计!:统计分析的快,画!数据集
作者: Raul Fernandez-Fernandez, Carlos Balaguer
备注:12 pages, Eurosim 2019
链接:https://arxiv.org/abs/1907.06417

[其他视频相关]:

【1】 Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis
具有相关损失的多任务递归卷积网络在外科视频分析中的应用
作者: Yueming Jin, Pheng-Ann Heng
链接:https://arxiv.org/abs/1907.06099

【2】 Deep Sequential Mosaicking of Fetoscopic Videos
胎儿镜视频的深度顺序镶嵌
作者: Sophia Bano, Danail Stoyanov
备注:Accepted at MICCAI 2019
链接:https://arxiv.org/abs/1907.06543

[其他]:

【1】 Multi-scale Graph-based Grading for Alzheimer's Disease Prediction
基于多尺度图的阿尔茨海默病预测分级
作者: Kilian Hett, Pierrick Coupé
链接:https://arxiv.org/abs/1907.06625

【2】 Color Cerberus
彩色Cerberus
作者: A.~Savchik, S.~Karpenko
链接:https://arxiv.org/abs/1907.06483

【3】 Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
利用空间分离注意模块提高合成图像的和谐性
作者: Cun Xiaodong, Pun Chi-Man
链接:https://arxiv.org/abs/1907.06406

【4】 Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
减轻三维物体零镜头学习的Hubness问题
作者: Ali Cheraghian, Lars Petersson
备注:BMVC 2019
链接:https://arxiv.org/abs/1907.06371

【5】 Enabling Multi-Shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE
使具有深岸的数据驱动扩散模型的多壳层b值泛化能力
作者: Vishwesh Nath, Bennett A. Landman
链接:https://arxiv.org/abs/1907.06319

【6】 State Estimation in Visual Inertial Autonomous Helicopter Landing Using Optimisation on Manifold
基于流形优化的视觉惯性自主直升机着陆状态估计
作者: Thinh Hoang Dinh, Tri Ngo Dinh
链接:https://arxiv.org/abs/1907.06247

【7】 Smile, be Happy :) Emoji Embedding for Visual Sentiment Analysis
微笑,快乐:)用于视觉情感分析的Emoji嵌入
作者: Ziad Al-Halah, Jose Caballero
链接:https://arxiv.org/abs/1907.06160

【8】 ThirdEye: Triplet Based Iris Recognition without Normalization
ThirdEye:无归一化的基于三元组的虹膜识别
作者: Sohaib Ahmad, Benjamin Fuller
链接:https://arxiv.org/abs/1907.06147

【9】 FMRI data augmentation via synthesis
通过合成实现fMRI数据增强
作者: Peiye Zhuang, Sanmi Koyejo
链接:https://arxiv.org/abs/1907.06134

【10】 Using dynamic routing to extract intermediate features for developing scalable capsule networks
使用动态路由提取中间特征以开发可扩展的封装网络
作者: Bodhisatwa Mandal, Mita Nasipuri
备注:Second International Conference on Advanced Computational and Communication Paradigms held at Sikkim Manipal Institute of Technology, Sikkim, India during February 25 - 28 , 2019
链接:https://arxiv.org/abs/1907.06062

【11】 Structure-Aware Residual Pyramid Network for Monocular Depth Estimation
基于结构感知的残差金字塔网络单目深度估计
作者: Xiaotian Chen, Zheng-Jun Zha
备注:7pages, 7figures, Accepted by the 28th International Joint Conference on Artificial Intelligence (IJCAI-2019)
链接:https://arxiv.org/abs/1907.06023

【12】 SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
SynthText3D:从3D虚拟世界合成场景文本图像
作者: Minghui Liao, Xiang Bai
链接:https://arxiv.org/abs/1907.06007

【13】 Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps
通过类别无关的条件映射实现野外手势到手势的翻译
作者: Yahui Liu, Bruno Lepri
链接:https://arxiv.org/abs/1907.05916

【14】 Batch-Shaped Channel Gated Networks
批量成形通道选通网络
作者: Babak Ehteshami Bejnordi, Max Welling
链接:https://arxiv.org/abs/1907.06627

【15】 Sparsely Activated Networks
稀疏激活网络
作者: Paschalis Bizopoulos, Dimitrios Koutsouris
链接:https://arxiv.org/abs/1907.06592

【16】 Autoencoding sensory substitution
自动编码感觉替代
作者: Viktor Tóth, Lauri Parkkonen
链接:https://arxiv.org/abs/1907.06286

【17】 A Divide-and-Conquer Approach towards Understanding Deep Networks
了解深层网络的分而治之方法
作者: Weilin Fu, Andreas Maier
备注:This paper is accepted in MICCAI 2019
链接:https://arxiv.org/abs/1907.06194

【18】 Neural Embedding for Physical Manipulations
用于物理操作的神经嵌入
作者: Lingzhi Zhang, Jianbo Shi
链接:https://arxiv.org/abs/1907.06143

【19】 S&CNet: A Enhanced Coarse-to-fine Framework For Monocular Depth Completion
S&CNET:一种增强的单目深度完成从粗到细的框架
作者: Lei Zhang, Chao Hu
链接:https://arxiv.org/abs/1907.06071

【20】 Learning better generative models for dexterous, single-view grasping of novel objects
学习更好的生成模型,以便灵活地、单视图地抓取新的对象
作者: Marek Kopicki, Jeremy L. Wyatt
备注:19 pages, 15 figures, 7 tables
链接:https://arxiv.org/abs/1907.06053

【21】 Learning Complex Basis Functions for Invariant Representations of Audio
学习音频不变表示的复基函数
作者: Stefan Lattner, Andreas Arzt
备注:Paper accepted at the 20th International Society for Music Information Retrieval Conference, ISMIR 2019, Delft, The Netherlands, November 4-8; 8 pages, 4 figures, 4 tables
链接:https://arxiv.org/abs/1907.05982

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[07.16])