【今日CS 视觉论文速览】 18 Dec 2018

今日CS.CV计算机视觉论文速览
Tue, 18 Dec 2018
Totally 52 papers

Interesting:

• 从美食图片生成菜谱和烹饪指南,这一系统可以通过输入预测食材及其相关性，并生成烹调指南。（from UPC &FAIR）
  菜谱是这样的：
  

从图像生成菜谱的模型如下：

首先通过自编码器抽取图像特征，随后利用原料解码器预测出各种食材，并编码后送入RNN中来生成烹饪方法。
其中包含了三种不同的注意力机制来融合食材特征和图像特征：

并利用时序pool来避免顺序产生影响：

• 一个用于几何研究的大规模的CAD模型库,包含了100万中CAD参数化模型，可以用于面片分解、形状特征抽取、几何分割、特征检测和重建等各种几何学习算法。(from 柏林工大 斯科沃理工skoltech 纽约大学 )
  
  精美的数据集:
  
  
  同时为了展示模型库的使用，研究人员比较了不同表面法向量估计方法，下图是不同算法的角度误差分布：
  
  https://www.skoltech.ru/en

• 二进制神经网络的图像超分辨,通过将残差单元内的滤波器二值化，并为每个二进制滤波器提供了一个可学习的权重。最终利用20%的模型5x的速度实现了前沿的效果。(from adobe 斯坦福 海康威视 华东师范）
  论文经过改造的生成器，其中红色部分为二进制：
  
  判别器：
  

拉普拉斯金字塔网络：

最后的结果很不错得到了34.91dB的分辨率：

• TET-GAN 字体风格迁移 一种可以将字体加上不同风格，或者去除风格的网络模型。(from 北大)
  网络模型如下，主要包含了重建损失、特征损失s/deat、像素损失s/d pix、对抗损失s/dadv：
  
  生成风格如下：
  

• 生成说话中的人脸根据输入面部照片和语音片段就可以合成出主体在说话时的新表情照片 (from 安徽大学)
  

• 通过向预测输出诸如先验的HintedNetworks来提高回归任务的精度，并在相机重定位中获得了精度的提升。
  
  

• XY Network为了解决组织学中细胞核分割问题，研究人员利用细胞核像素到质心的垂直和水平距离编码来分离和分割细胞核。（from 华威大学）
  
  

• RGB多光谱进行太阳能电池板缺陷检测 (from 河北大学)
  

• 冬日道路状况检测(from 滑铁卢大学)
  

---

Daily Computer Vision Papers

[1] Title: Fast Learning-based Registration of Sparse Clinical Images
Authors:Kathleen M. Lewis, Guha Balakrishnan, Natalia S. Rost, John Guttag, Adrian V. Dalca
[2] Title: Taking a Deeper Look at the Inverse Compositional Algorithm
Authors:Zhaoyang Lv, Frank Dellaert, James M. Rehg, Andreas Geiger
[3] Title: Convolutional herbal prescription building method from multi-scale facial features
Authors:Huiqiang Liao, Guihua Wen, Yang Hu, Changjun Wang
[4] Title: Discriminant Patch Representation for RGB-D Face Recognition Using Convolutional Neural Networks
Authors:Nesrine Grati, Achraf Ben-Hamadou, Mohamed Hammami
[5] Title: Fully-deformable 3D image registration in two seconds
Authors:Daniel Budelmann, Lars König, Nils Papenberg, Jan Lellmann
[6] Title: Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation
Authors:Rakshith Shetty, Bernt Schiele, Mario Fritz
[7] Title: Floorplan Priors for Joint Camera Pose and Room Layout Estimation
Authors:Cheng Lin, Changjian Li, Yasutaka Furukawa, Wenping Wang
[8] Title: Robust Graph Learning from Noisy Data
Authors:Zhao Kang, Haiqi Pan, Steven C.H. Hoi, Zenglin Xu
[9] Title: Attending Category Disentangled Global Context for Image Classification
Authors:Keke Tang, Guodong Wei, Runnan Chen, Jie Zhu, Wenping Wang
[10] Title: Feature Fusion Effects of Tensor Product Representation on (De)Compositional Network for Caption Generation for Images
Authors:Chiranjib Sur
[11] Title: A Layer Decomposition-Recomposition Framework for Neuron Pruning towards Accurate Lightweight Networks
Authors:Weijie Chen, Yuan Zhang, Di Xie, Shiliang Pu
[12] Title: High-Resolution Talking Face Generation via Mutual Information Approximation
Authors:Hao Zhu, Aihua Zheng, Huaibo Huang, Ran He
[13] Title: Grounded Video Description
Authors:Luowei Zhou, Yannis Kalantidis, Xinlei Chen, Jason J. Corso, Marcus Rohrbach
[14] Title: Learning Incremental Triplet Margin for Person Re-identification
Authors:Yingying Zhang, Qiaoyong Zhong, Liang Ma, Di Xie, Shiliang Pu
[15] Title: Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
Authors:Xiang Li, Shihao Ji
[16] Title: Towards Robust Human Activity Recognition from RGB Video Stream with Limited Labeled Data
Authors:Krishanu Sarker, Mohamed Masoud, Saeid Belkasim, Shihao Ji
[17] Title: Non-invasive measuring method of skin temperature based on skin sensitivity index and deep learning
Authors:Xiaogang Cheng, Bin Yang, Kaige Tan, Erik Isaksson, Liren Li, Anders Hedman, Thomas Olofsson, Haibo Li
[18] Title: XY Network for Nuclear Segmentation in Multi-Tissue Histology Images
Authors:Simon Graham, Quoc Dang Vu, Shan E Ahmed Raza, Jin Tae Kwak, Nasir Rajpoot
[19] Title: Classifier and Exemplar Synthesis for Zero-Shot Learning
Authors:Soravit Changpinyo, Wei-Lun Chao, Boqing Gong, Fei Sha
[20] Title: Model-free Tracking with Deep Appearance and Motion Features Integration
Authors:Xiaolong Jiang, Peizhao Li, Xiantong Zhen, Xianbin Cao
[21] Title: Visual Dialogue without Vision or Dialogue
Authors:Daniela Massiceti, Puneet K. Dokania, N. Siddharth, Philip H.S. Torr
[22] Title: Human Pose and Path Estimation from Aerial Video using Dynamic Classifier Selection
Authors:Asanka G Perera, Yee Wei Law, Javaan Chahl
[23] Title: Unified Graph based Multi-Cue Feature Fusion for Robust Visual Tracking
Authors:Kapil Sharma, Himanshu Ahuja, Ashish Kumar, Nipun Bansal, Gurjit Singh Walia
[24] Title: Pre-Trained Convolutional Neural Network Features for Facial Expression Recognition
Authors:Aravind Ravi
[25] Title: TET-GAN: Text Effects Transfer via Stylization and Destylization
Authors:Shuai Yang, Jiaying Liu, Wenjing Wang, Zongming Guo
[26] Title: Efficient Super Resolution Using Binarized Neural Network
Authors:Yinglan Ma, Hongyu Xiong, Zhe Hu, Lizhuang Ma
[27] Title: Action Quality Assessment Across Multiple Actions
Authors:Paritosh Parmar, Brendan Tran Morris
[28] Title: PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection
Authors:Nian Liu, Junwei Han, Ming-Hsuan Yang
[29] Title: Hinted Networks
Authors:Joel Lamy-Poirier, Anqi Xu
[30] Title: PVSNet: Palm Vein Authentication Siamese Network Trained using Triplet Loss and Adaptive Hard Mining by Learning Enforced Domain Specific Features
Authors:Daksh Thapar, Gaurav Jaswal, Aditya Nigam, Vivek Kanhangad
[31] Title: Hierarchical Discrete Distribution Decomposition for Match Density Estimation
Authors:Zhichao Yin, Trevor Darrell, Fisher Yu
[32] Title: Weakly supervised segment annotation via expectation kernel density estimation
Authors:Liantao Wang, Qingwu Li, Jianfeng Lu
[33] Title: A Low Effort Approach to Structured CNN Design Using PCA
Authors:Isha Garg, Priyadarshini Panda, Kaushik Roy
[34] Title: Solar Cell Surface Defect Inspection Based on Multispectral Convolutional Neural Network
Authors:Haiyong Chen, Yue Pang, Qidi Hu, Kun Liu
[35] Title: TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition
Authors:Xiyang Dai, Bharat Singh, Joe Yue-Hei Ng, Larry S. Davis
[36] Title: Efficient Interpretation of Deep Learning Models Using Graph Structure and Cooperative Game Theory: Application to ASD Biomarker Discovery
Authors:Xiaoxiao Li, Nicha C. Dvornek, Yuan Zhou, Juntang Zhuang, Pamela Ventola, James S. Duncan
[37] Title: Inverse Cooking: Recipe Generation from Food Images
Authors:Amaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto, Adriana Romero
[38] Title: A Parametric Top-View Representation of Complex Road Scenes
Authors:Ziyan Wang, Buyu Liu, Samuel Schulter, Manmohan Chandraker
[39] Title: Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking
Authors:Heng Fan, Haibin Ling
[40] Title: Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training
Authors:Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel
[41] Title: Axially-shifted pattern illumination for macroscale turbidity suppression and virtual volumetric confocal imaging without axial scanning
Authors:Shaowei Jiang, Jun Liao, Zichao Bian, Pengming Song, Garrett Soler, Kazunori Hoshino, Guoan Zheng
[42] Title: Three-Dimensional Dose Prediction for Lung IMRT Patients with Deep Neural Networks: Robust Learning from Heterogeneous Beam Configurations
Authors:Ana M. Barragan-Montero, Dan Nguyen, Weiguo Lu, Mu-Han Lin, Xavie Geets, Edmond Sterpin, Steve Jiang
[43] Title: BriarPatches: Pixel-Space Interventions for Inducing Demographic Parity
Authors:Alexey A. Gritsenko, Alex D’Amour, James Atwood, Yoni Halpern, D. Sculley
[44] Title: Winter Road Surface Condition Recognition Using A Pretrained Deep Convolutional Network
Authors:Guangyuan Pan, Liping Fu, Ruifan Yu, Matthew Muresan
[45] Title: Variational Autoencoders Pursue PCA Directions (by Accident)
Authors:Michal Rolinek, Dominik Zietlow, Georg Martius
[46] Title: Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
Authors:Zhiwei Wang, Yi Lin, Kwang-Ting Cheng, Xin Yang
[47] Title: Voiceprint recognition of Parkinson patients based on deep learning
Authors:Zhijing Xu, Juan Wang, Ying Zhang, Xiangjian He
[48] Title: Learning Student Networks via Feature Embedding
Authors:Hanting Chen, Yunhe Wang, Chang Xu, Chao Xu, Dacheng Tao
[49] Title: ${\ell }_0$-Motivated Low-Rank Sparse Subspace Clustering
Authors:Maria Brbić, Ivica Kopriva
[50] Title: Latent Dirichlet Allocation in Generative Adversarial Networks
Authors:Lili Pan, Shen Cheng, Jian Liu, Yazhou Ren, Zenglin Xu
[51] Title: ABC: A Big CAD Model Dataset For Geometric Deep Learning
Authors:Sebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev, Marc Alexa, Denis Zorin, Daniele Panozzo
[52] Title: Learning Latent Subspaces in Variational Autoencoders
Authors:Jack Klys, Jake Snell, Richard Zemel

Papers from arxiv.org

更多精彩请移步主页

---

pic from pixels.com