【今日CS 视觉论文速览】 27 Dec 2018

今日CS.CV计算机视觉论文速览
Thu, 27 Dec 2018
Totally 70 papers

Interesting:

• 荧光显微镜数据集FMD,提供了包含12000张真实荧光显微镜的照片。主要用于解决显微镜中噪声特别是泊松噪声的问题。研究人员提供了原始数据和不同张图片平均得到的不同噪声水平的图像，其中基准图像利用了50张噪声图像平均得到。研究人员使用了VST based的算法和深度学习算法DnCNN,Noise2Noise算法，发现深度学习算法可以达到35dB以上的PSNR。(from 圣母大学)
  
  Fluorescence Microscopy Denoising dataset

• 基于单张深度图的手势估计, 通过深度图转换的体素输入，直接回归出每个手部关节3D热力图。这一工作主要基于horuglass网络和MSRA\NYU数据集来进行。(from 香港理工)
  
  
  DATASET:
  MSRA: Cascaded hand pose regression 75K 17种手势 9个主体
  NYC:Real-time continuous pose recovery of human hands using convolutional networks 72k训练 8k测试。

• 深度人脸属性综述,介绍了人脸特征估计FAE和人脸特征操作FAM两个核心问题，并处数据预处理和建模两个方面介绍了人脸特征的工作流程。同时还总结了常用的数据集、分析了前沿的算法，并介绍了一些前沿的研究问题和应用。(from 大连理工)
  
  两种不同的基于外部条件的操作：
  
  常见数据集dataset：
  

• FPD-M-net基于M-Net的指纹图像去噪和修复,去除手指污染和传感器性能失效的影响。(from IIT Center for Visual Information Technology,CVIT)
  
  指纹dataset，以及一个数据集网站
  Code

• 隐性指纹搜索,从物体上将隐性指纹恢复得到清晰的指纹，用于取证。主要流程包括ROI提取、隐性图像处理、特征抽取、比较、输出结果。(from 密歇根大学)
  系统的工作流程如下，包括估计ROI、隐性指纹处理、特征抽取和编码、匹配。
  
  其中利用了自编码器做指纹增强：
  
  指纹隐空间数据集:NIST SD27 (258 latents); MSP (1,200 latents), WVU (449 latents) and N2N (10,000 latents)
  add 一位做指纹研究的老师

• 基于生成对抗网络的增强食物识别，这一工作利用了部分标注的数据通过GAN来生成了丰富的数据，用于训练神经网络，并在食物分类上实现了很好的效果。(from 基尔大学 UK and IIT)
  
  相关数据集
  ETHZ Food-101
  一大堆食物相关数据集
  data.world 小众食物数据
  50 salad

• 识别对抗样本，这个工作扎到了一种有效的方法来定量表示对抗样本的变化，通过特征空间的不同来识别出对抗样本。越深层的特征图、真实图和对抗样本的特征表达差异就越大，这种现象称为对抗特征可分性。基于这种方法研究人员提出了对抗特征“基因”来识别对抗样本，实现网络防御。（from 中南大学）
  
  对抗样本可分性表现如下，随着深度增加特征图差异逐渐增大：
  
  具体流程框图如下：
  
  数据库和源码

• GDWTC:group-wise deep whitening and coloring图像翻译风格化新方法，这一工作充分使用了基于方差和均值的特征对，利用了协方差的统计特性。通过将输入图像的内容百化处理(transforms a covariance matrix of a given input into the identity matrix)，随后加入色彩以匹配协方差统计信息。(from 高丽大学 LG)
  
  GDWCT模块的实现细化，即上图中的淡色框内部分，包含了多个白化模块hops和多层感知机：
  
  最后实现的效果很好玩：
  风格迁移
  
  哭变笑，笑变哭：
  
  男变女女变男：
  
  刘海也不怕：
  
  
  数据集：
  模特：CelebA
  艺术：Artworks
  猫狗：cat2dog
  颜色：Behance Artistic Media (BAM)
  春冬季节：Yosemite
  相关方法：MUNIT&DRIT,WCT。

• TextNet,非规则字符检测和识别网络，端到端的实现了图像中文字的定位和检测。首先基于多出度注意力机制解决了不同尺度的问题，随后在检测阶段proposal出不同方向、视角和曲率的文本区域。随后利用ROI转换层得到较小的特征图、并利用编码器获取有效特征。(from Baidu)
  
  网络主要架构，分为了主体网络、四边形推举层、尺度注意力、层透视ROI变换层等。
  多尺度机制和空间注意力机制：
  
  一些结果：
  
  相关dataset：ICDAR-13 ICDAR-15 Total-Text

基于耦合自编码器的去模糊,主要思想在于分别训练两个自编码器来恢复各自的图像，然后将coder进行映射，将模糊图的coder映射到清晰图的coder上，然后解码出清晰图。(from tata TCS)

耦合网络ref:Coupled deep autoencoder for single image super-resolution
CERTH dataset：No-reference blur assessment in natural images using fourier transform and spatial pyramids

• 宫颈癌检测，利用分类和形态学特征来解决遮挡重合问题。（from 耶尔德兹技术大学 土耳其）
  
  

Daily Computer Vision Papers

[1] Title: A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images
Authors:Yide Zhang, Yinhao Zhu, Evan Nichols, Qingfei Wang, Siyuan Zhang, Cody Smith, Scott Howard
[2] Title: Informative Object Annotations: Tell Me Something I Don’t Know
Authors:Lior Bracha, Gal Chechik
[3] Title: Learning Not to Learn: Training Deep Neural Networks with Biased Data
Authors:Byungju Kim, Hyunwoo Kim, Kyungsu Kim, Sungjin Kim, Junmo Kim
[4] Title: Region Proposal Networks with Contextual Selective Attention for Real-Time Organ Detection
Authors:Awais Mansoor, Antonio R. Porras, Marius George Linguraru
[5] Title: A Multi-Stream Convolutional Neural Network Framework for Group Activity Recognition
Authors:Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi
[6] Title: Cluster Loss for Person Re-Identification
Authors:Doney Alex, Zishan Sami, Sumandeep Banerjee, Subrat Panda
[7] Title: Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image
Authors:Fuyang Huang, Ailing Zeng, Minhao Liu, Jing Qin, Qiang Xu
[8] Title: Spotting Micro-Expressions on Long Videos Sequences
Authors:Jingting Li, Catherine Soladie, Renaud Sguier, Sujing Wang, Moi Hoon Yap
[9] Title: Spatial and Temporal Mutual Promotion for Video-based Person Re-identification
Authors:Yiheng Liu, Zhenxun Yuan, Wengang Zhou, Houqiang Li
[10] Title: A Survey to Deep Facial Attribute Analysis
Authors:Xin Zheng, Yanqing Guo, Huaibo Huang, Yi Li, Ran He
[11] Title: A Whole Slide Image Grading Benchmark and Tissue Classification for Cervical Cancer Precursor Lesions with Inter-Observer Variability
Authors:Abdulkadir Albayrak, Asli Unlu, Nurullah Calik, Abdulkerim Capar, Gokhan Bilgin, Behcet Ugur Toreyin, Bahar Muezzinoglu, Ilknur Turkmen, Lutfiye Durak-Ata
[12] Title: 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
Authors:Lin Wu, Yang Wang, Ling Shao, Meng Wang
[13] Title: Practical Adversarial Attack Against Object Detector
Authors:Yue Zhao, Hong Zhu, Qintao Shen, Ruigang Liang, Kai Chen, Shengzhi Zhang
[14] Title: End-to-End Latent Fingerprint Search
Authors:Kai Cao, Dinh-Luan Nguyen, Cori Tymoszek, A.K. Jain
[15] Title: RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
Authors:Lei Han, Mengqi Ji, Lu Fang, Matthias Nießner
[16] Title: FPD-M-net: Fingerprint Image Denoising and Inpainting Using M-Net Based Convolutional Neural Networks
Authors:Sukesh Adiga V, Jayanthi Sivaswamy
[17] Title: Deep Convolutional Generative Adversarial Network Based Food Recognition Using Partially Labeled Data
Authors:Bappaditya Mandal, N. B. Puhan, Avijit Verma
[18] Title: Motion Selective Prediction for Video Frame Synthesis
Authors:Veronique Prinet
[19] Title: The algorithm of the impulse noise filtration in images based on an algorithm of community detection in graphs
Authors:S.V. Belim, S.B. Larionov
[20] Title: Classification of X-Ray Protein Crystallization Using Deep Convolutional Neural Networks with a Finder Module
Authors:Yusei Miura, Tetsuya Sakurai, Claus Aranha, Toshiya Senda, Ryuichi Kato, Yusuke Yamada
[21] Title: Adversarial Feature Genome: a Data Driven Adversarial Examples Recognition Method
Authors:Li Chen, Hailun Ding, Qi Li, Jiawei Zhu, Haozhe Huang, Yifan Chang, Haifeng Li
[22] Title: Coupled Recurrent Network (CRN)
Authors:Lin Sun, Kui Jia, Yuejia Shen, Silvio Savarese, Dit Yan Yeung, Bertram E. Shi
[23] Title: Selectivity or Invariance: Boundary-aware Salient Object Detection
Authors:Jinming Su, Jia Li, Changqun Xia, Yonghong Tian
[24] Title: MMFNet: A Multi-modality MRI Fusion Network for Segmentation of Nasopharyngeal Carcinoma
Authors:Huai Chen, Yuxiao Qi, Yong Yin, TengXiang Li, Guanzhong Gong, Lisheng Wang
[25] Title: Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
Authors:Hiroshi Fukui, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi
[26] Title: A Unified Framework for Mutual Improvement of SLAM and Semantic Segmentation
Authors:Kai Wang, Yimin Lin, Luowei Wang, Liming Han, Minjie Hua, Xiang Wang, Shiguo Lian, Bill Huang
[27] Title: Similarity R-C3D for Few-shot Temporal Activity Detection
Authors:Huijuan Xu, Bingyi Kang, Ximeng Sun, Jiashi Feng, Kate Saenko, Trevor Darrell
[28] Title: Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
Authors:Yang Zhang, Philip David, Hassan Foroosh, Boqing Gong
[29] Title: Color Image Enhancement Method Based on Weighted Image Guided Filtering
Authors:Qi Mu, Yanyan Wei, Zhanli Li
[30] Title: Image-to-Image Translation via Group-wise Deep Whitening and Coloring Transformation
Authors:Wonwoong Cho, Sungha Choi, David Park, Inkyu Shin, Jaegul Choo
[31] Title: Domain-Aware Generalized Zero-Shot Learning
Authors:Yuval Atzmon, Gal Chechik
[32] Title: TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
Authors:Yipeng Sun, Chengquan Zhang, Zuming Huang, Jiaming Liu, Junyu Han, Errui Ding
[33] Title: Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
Authors:Kyaw Zaw Lin, Weipeng Xu, Qianru Sun, Christian Theobalt, Tat-Seng Chua
[34] Title: Motion Blur removal via Coupled Autoencoder
Authors:Kavya Gupta, Brojeshwar Bhowmick, Angshul Majumdar
[35] Title: Coupled Analysis Dictionary Learning to inductively learn inversion: Application to real-time reconstruction of Biomedical signals
Authors:Kavya Gupta, Brojeshwar Bhowmick, Angshul Majumdar
[36] Title: Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation
Authors:Yazeed Alharbi, Neil Smith, Peter Wonka
[37] Title: Perceptually-based single-image depth super-resolution
Authors:O. Voinov, A. Artemov, V. Egiazarian, A. Notchenko, G. Bobrovskikh, D. Zorin, E. Burnaev
[38] Title: Holistic Decomposition Convolution for Effective Semantic Segmentation of 3D MR Images
Authors:Guodong Zeng, Guoyan Zheng
[39] Title: Texture Deformation Based Generative Adversarial Networks for Face Editing
Authors:WenTing Chen, Xinpeng Xie, Xi Jia, Linlin Shen
[40] Title: Precision Highway for Ultra Low-Precision Quantization
Authors:Eunhyeok Park, Dongyoung Kim, Sungjoo Yoo, Peter Vajda
[41] Title: Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition
Authors:Zi-Rui Wang, Jun Du, Jia-Ming Wang
[42] Title: Deep Learning for Inferring the Surface Solar Irradiance from Sky Imagery
Authors:Mehdi Zakroum, Mounir Ghogho, Mustapha Faqir, Mohamed Aymane Ahajjam
[43] Title: Leveraging Class Similarity to Improve Deep Neural Network Robustness
Authors:Pooran Singh Negi, David chen, Mohammad Mahoor
[44] Title: End-to-end Learning for Graph Decomposition
Authors:Jie Song, Bjoern Andres, Michael Black, Otmar Hilliges, Siyu Tang
[45] Title: Advanced Image Processing for Astronomical Images
Authors:Diganta Misra, Sparsha Mishra, Bhargav Appasani
[46] Title: Image Processing on IOPA Radiographs: A comprehensive case study on Apical Periodontitis
Authors:Diganta Misra, Vanshika Arora
[47] Title: Chinese Herbal Recognition based on Competitive Attentional Fusion of Multi-hierarchies Pyramid Features
Authors:Yingxue Xu, Guihua Wen, Yang Hu, Mingnan Luo, Dan Dai, Yishan Zhuang
[48] Title: Estimation and Restoration of Compositional Degradation Using Convolutional Neural Networks
Authors:Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi
[49] Title: EgoReID: Person re-identification in Egocentric Videos Acquired by Mobile Devices with First-Person Point-of-View
Authors:Emrah Basaran, Yonatan Tariku Tesfaye, Mubarak Shah
[50] Title: The algorithm of formation of a training set for an artificial neural network for image segmentation
Authors:S.V. Belim, S.B. Larionov
[51] Title: Temporal Hockey Action Recognition via Pose and Optical Flows
Authors:Zixi Cai, Helmut Neher, Kanav Vats, David Clausi, John Zelek
[52] Title: Dimensionality Reduction of Hyperspectral Imagery Based on Spatial-spectral Manifold Learning
Authors:Hong Huang, Guangyao Shi, Haibo He, Yule Duan, Fulin Luo
[53] Title: Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
Authors:Zhilin Zheng, Li Sun
[54] Title: Fully Automatic Segmentation of Sublingual Veins from Retrained U-Net Model for Few Near Infrared Images
Authors:Tingxiao Yang, Yuichiro Yoshimura, Akira Morita, Takao Namiki, Toshiya Nakaguchi
[55] Title: Dissociable neural representations of adversarially perturbed images in deep neural networks and the human brain
Authors:Chi Zhang, Xiaohan Duan, Linyuan Wang, Yongli Li, Bin Yan, Guoen Hu, Ruyuan Zhang, Li Tong
[56] Title: Multi-Frame Super-Resolution Reconstruction with Applications to Medical Imaging
Authors:Thomas Köhler
[57] Title: Wireless Software Synchronization of Multiple Distributed Cameras
Authors:Sameer Ansari, Neal Wadhwa, Rahul Garg, Jiawen Chen
[58] Title: An Empirical Analysis of Deep Audio-Visual Models for Speech Recognition
Authors:Devesh Walawalkar, Yihui He, Rohit Pillai
[59] Title: Cross Lingual Speech Emotion Recognition: Urdu vs. Western Languages
Authors:Siddique Latif, Adnan Qayyum, Muhammad Usman, Junaid Qadir
[60] Title: Urban-Rural Environmental Gradient in a Developing City: Testing ENVI GIS Functionality
Authors:Polina Lemenkova
[61] Title: Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning
Authors:Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran
[62] Title: A Survey on Non-rigid 3D Shape Analysis
Authors:Hamid Laga
[63] Title: Learning based Facial Image Compression with Semantic Fidelity Metric
Authors:Zhibo Chen, Tianyu He
[64] Title: Dual Principal Component Pursuit: Probability Analysis and Efficient Algorithms
Authors:Zhihui Zhu, Yifan Wang, Daniel P. Robinson, Daniel Q. Naiman, Rene Vidal, Manolis C. Tsakiris
[65] Title: Dynamic Runtime Feature Map Pruning
Authors:Tailin Liang, Lei Wang, Shaobo Shi, John Glossner
[66] Title: Improving MMD-GAN Training with Repulsive Loss Function
Authors:Wei Wang, Yuan Sun, Saman Halgamuge
[67] Title: Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks
Authors:Thomas Brunner, Frederik Diehl, Michael Truong Le, Alois Knoll
[68] Title: Multi-modal Learning with Prior Visual Relation Reasoning
Authors:Zhuoqian Yang, Jing Yu, Chenghao Yang, Zengchang Qin, Yue Hu
[69] Title: Image Embedding of PMU Data for Deep Learning towards Transient Disturbance Classification
Authors:Yongli Zhu, Chengxi Liu, Kai Sun
[70] Title: Multi-Step Prediction of Occupancy Grid Maps with Recurrent Neural Networks
Authors:Nima Mohajerin, Mohsen Rohani

Papers from arxiv.org

更多精彩请移步主页

pic from pixels.com