【今日CV 视觉论文速览】26 Nov 2018

今日CS.CV计算机视觉论文速览
Mon, 26 Nov 2018
Totally 50 papers

Daily Computer Vision Papers

[1] Title: Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses
Authors:Jérôme Rony, Luiz G. Hafemann, Luis S. Oliveira, Ismail Ben Ayed, Robert Sabourin, Eric Granger
[2] Title: Do GAN Loss Functions Really Matter?
Authors:Yipeng Qin, Niloy Mitra, Peter Wonka
[3] Title: An Adaptive Approach for Automated Grapevine Phenotyping using VGG-based Convolutional Neural Networks
Authors:Jonatan Grimm, Katja Herzog, Florian Rist, Anna Kicherer, Reinhard Töpfer, Volker Steinhage
[4] Title: An Interpretable Model for Scene Graph Generation
Authors:Ji Zhang, Kevin Shih, Andrew Tao, Bryan Catanzaro, Ahmed Elgammal
[5] Title: Complementary Segmentation of Primary Video Objects with Reversible Flows
Authors:Jia Li, Junjie Wu, Anlin Zheng, Yafei Song, Yu Zhang, Xiaowu Chen
[6] Title: MURAUER: Mapping Unlabeled Real Data for Label AUstERity
Authors:Georg Poier, Michael Opitz, David Schinagl, Horst Bischof
[7] Title: LSD$_2$ - Joint Denoising and Deblurring of Short and Long Exposure Images with Convolutional Neural Networks
Authors:Janne Mustaniemi, Juho Kannala, Jiri Matas, Simo Särkkä, Janne Heikkilä
[8] Title: Defect Detection from UAV Images based on Region-Based CNNs
Authors:Meng Lan, Yipeng Zhang, Lefei Zhang, Bo Du
[9] Title: Fast Object Class Labelling via Speech
Authors:Michael Gygli, Vittorio Ferrari
[10] Title: Joint Neural Architecture Search and Quantization
Authors:Yukang Chen, Gaofeng Meng, Qian Zhang, Xinbang Zhang, Liangchen Song, Shiming Xiang, Chunhong Pan
[11] Title: MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image
Authors:Jinglu Wang, Bo Sun, Yan Lu
[12] Title: Temporally Coherent GANs for Video Super-Resolution (TecoGAN)
Authors:Mengyu Chu, You Xie, Laura Leal-Taixé, Nils Thuerey
[13] Title: PRIN: Pointwise Rotation-Invariant Network
Authors:Yang You, Yujing Lou, Qi Liu, Lizhuang Ma, Weiming Wang, Yuwing Tai, Cewu Lu
[14] Title: Revisiting Pre-training: An Efficient Training Method for Image Classification
Authors:Bowen Cheng, Yunchao Wei, Honghui Shi, Shiyu Chang, Jinjun Xiong, Thomas S. Huang
[15] Title: Learning Grouped Convolution for Efficient Domain Adaptation
Authors:Ruizhe Zhao, Wayne Luk
[16] Title: TGANv2: Efficient Training of Large Models for Video Generation with Multiple Subsampling Layers
Authors:Masaki Saito, Shunta Saito
[17] Title: Automatic L3 slice detection in 3D CT images using fully-convolutional networks
Authors:Fahdi Kanavati, Shah Islam, Eric O. Aboagye, Andrea Rockall
[18] Title: FAIM – A ConvNet Method for Unsupervised 3D Medical Image Registration
Authors:Dongyang Kuang, Tanya Schmah
[19] Title: Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
Authors:Nikolay Jetchev, Urs Bergmann, Gokhan Yildirim
[20] Title: Self Paced Adversarial Training for Multimodal Few-shot Learning
Authors:Frederik Pahde, Oleksiy Ostapenko, Patrick Jähnichen, Tassilo Klein, Moin Nabi
[21] Title: Object-oriented Targets for Visual Navigation using Rich Semantic Representations
Authors:Jean-Benoit Delbrouck, Stéphane Dupont
[22] Title: Dual Reweighted Lp-Norm Minimization for Salt-and-pepper Noise Removal
Authors:Huiwen Donga, Jing Yua, Chuangbai Xiaoa
[23] Title: Generalized Range Moves
Authors:Richard Hartley, Thalaiyasingam Ajanthan
[24] Title: MGANet: A Robust Model for Quality Enhancement of Compressed Video
Authors:Xiandong Meng, Xuan Deng, Shuyuan Zhu, Shuaicheng Liu, Chuan Wang, Chen Chen, Bing Zeng
[25] Title: IEGAN: Multi-purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network
Authors:Soumya Shubhra Ghosh, Yang Hua, Sankha Subhra Mukherjee, Neil Robertson
[26] Title: Uncalibrated Non-Rigid Factorisation by Independent Subspace Analysis
Authors:Sami Sebastian Brandt, Hanno Ackermann, Stella Grasshof
[27] Title: BRDF Estimation of Complex Materials with Nested Learning
Authors:Raquel Vidaurre, Dan Casas, Elena Garces, Jorge Lopez-Moreno
[28] Title: Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
Authors:Chaoyun Zhang, Rui Li, Woojin Kim, Daesub Yoon, Paul Patras
[29] Title: Feature-based groupwise registration of historical aerial images to present-day ortho-photo maps
Authors:Sebastian Zambanini
[30] Title: Response monitoring of breast cancer on DCE-MRI using convolutional neural network-generated seed points and constrained volume growing
Authors:Bas H.M. van der Velden, Bob D. de Vos, Claudette E. Loo, Hugo J. Kuijf, Ivana Isgum, Kenneth G.A. Gilhuijs
[31] Title: Mask R-CNN with Pyramid Attention Network for Scene Text Detection
Authors:Zhida Huang, Zhuoyao Zhong, Lei Sun, Qiang Huo
[32] Title: Super Diffusion for Salient Object Detection
Authors:Peng Jiang, Zhiyi Pan, Nuno Vasconcelos, Baoquan Chen, Jingliang Peng
[33] Title: KekuleScope: improved prediction of cancer cell line sensitivity using convolutional neural networks trained on compound images
Authors:Isidro Cortes Ciriano, Andreas Bender
[34] Title: Data Augmentation using Random Image Cropping and Patching for Deep CNNs
Authors:Ryo Takahashi, Takashi Matsubara, Kuniaki Uehara
[35] Title: Three-dimensional Optical Coherence Tomography Image Denoising via Multi-input Fully-Convolutional Networks
Authors:Ashkan Abbasi, Amirhassan Monadjemi, Leyuan Fang, Hossein Rabbani, Yi Zhang
[36] Title: Distorting Neural Representations to Generate Highly Transferable Adversarial Examples
Authors:Muzammal Naseer, Salman H. Khan, Shafin Rahman, Fatih Porikli
[37] Title: Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement
Authors:Yibing Song, Jiawei Zhang, Lijun Gong, Shengfeng He, Linchao Bao, Jinshan Pan, Qingxiong Yang, Ming-Hsuan Yang
[38] Title: Multi-View Inpainting for RGB-D Sequence
Authors:Feiran Li, Gustavo Alfonso Garcia Ricardez, Jun Takamatsu, Tsukasa Ogasawara
[39] Title: Supervised Fitting of Geometric Primitives to 3D Point Clouds
Authors:Lingxiao Li, Minhyuk Sung, Anastasia Dubrovina, Li Yi, Leonidas Guibas
[40] Title: Polarity Loss for Zero-shot Object Detection
Authors:Shafin Rahman, Salman Khan, Nick Barnes
[41] Title: Low-Resolution Face Recognition
Authors:Zhiyi Cheng, Xiatian Zhu, Shaogang Gong
[42] Title: Pneumonia Detection in Chest Radiographs
Authors: The DeepRadiology Team
[43] Title: MAC: Mining Activity Concepts for Language-based Temporal Localization
Authors:Runzhou Ge, Jiyang Gao, Kan Chen, Ram Nevatia
[44] Title: Learning from Multiview Correlations in Open-Domain Videos
Authors:Nils Holzenberger, Shruti Palaskar, Pranava Madhyastha, Florian Metze, Raman Arora
[45] Title: A Sufficient Condition for Convergences of Adam and RMSProp
Authors:Fangyu Zou, Li Shen, Zequn Jie, Weizhong Zhang, Wei Liu
[46] Title: Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack
Authors:Adnan Siraj Rakin, Zhezhi He, Deliang Fan
[47] Title: Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spaces
Authors:Ziv Katzir, Yuval Elovici
[48] Title: MS-UNIQUE: Multi-model and Sharpness-weighted Unsupervised Image Quality Estimation
Authors:Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
[49] Title: Generating Adaptive and Robust Filter Sets Using an Unsupervised Learning Framework
Authors:Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
[50] Title: A Comparative Study of Quality and Content-Based Spatial Pooling Strategies in Image Quality Assessment
Authors:Dogancan Temel, Ghassan AlRegib

Papers from arxiv.org

Interesting:

• 谷歌开发语音辅助的高效图像标注工具, 基于鼠标点击和语音识别加速了2.3-14.9倍的标注速度。（from 谷歌）
  

• 单张图像生成多视角点以及三维重建MVPNet,包含了多视角点云生成（栅格化适用于CNN输入），引入了几何损失来进行训练。（from 微软 普渡）

• 

• Pointwise Rotation-Invariant Network (PRIN)通过从稀疏点云中的自适应采样和球卷积抽取了旋转不变性的特征。(from 上海交大、腾讯)
  
  code

• Fully Adversarial Mosaics (FAMOS)结合参数（快速infer）和非参数化（精确重建复杂结构）方法实现对抗风格迁移，小数据量小灵活模型。（from zalando）
  

• 利用Dual reweighted Lp norm (DWLP)模型实现椒盐噪声去噪。（from 北大）
  

• IEGAN一个多功能模型可实现修复和超分辨，提出了结合重建误差(底层语义信息)、特征误差(更为自然)和边缘误差(锐利)的新损失函数。(from 女王大学 Anyvision)
  
  

• Super Diffusion,基于扩散过程的物体显著性检测， diffusion process is actually computing the similarity of nodes with respect to the seeds based on diffusion maps。(from 山大 UCSD 北大)
  

利用RGB-D消除图像中无用物体,(from 奈良先端科学技術大学院大学)

• Supervised Primitive Fitting Network (SPFN)实现端到端的从点云到几何图元的拟合，先预测每点属性，再根据属性选择差分估计模块来实现参数和图元的计算。（from 斯坦福）
  
• 线性解码器模型估计图像感知质量 (from 佐治亚理工)
  
• 生成具有适应性和鲁棒性的滤波器集, (from 佐治亚理工)
• 比较了特征和pooling对于图像质量评价，都很重要，并提出了基于linearly weighted percentile pooling(WPP)的基于质量的空间pooling策略（from 佐治亚理工）。