【今日CS 视觉论文速览】 24 Dec 2018

今日CS.CV计算机视觉论文速览
Mon, 24 Dec 2018
Totally 30 papers

Interesting:

• 3DSRnet基于3D卷积的视频超分辨网络，3D卷积对于视频中的空时关系更为有效，可以保留时间信息。基于3DSRnet的方式可以无需运动匹配的预处理。它可以通过抓取空时特征图中的时域特征，将保留不同分辨率帧之间的关系。(from KAIST)
  作用在输入帧上的N个滤波器得到N组时间特征图：
  
  整个网络的流程图：
  
  上采样过程图解：
  

• 基于Faster RCNN 检测骨折（from 耶路撒冷希伯来大学）
  

• 树的三维重建,为了满足物理仿真的需要，植物的重建需满足一定的几何精度。这项工作基于无人机的RGB图像，创建了点云和三角mesh，并建立了贴片纹理的圆柱刚体模型。(from 斯坦福和工业光魔)
  
  并利用了深度学习进行图像分割：
  
  最后的重建结果：
  
  项目：https://store.speedtree.com/

• 基于RGB图像来提高热红外成像的分辨率
  （from 布鲁塞尔自由大学）
  现有的超分辨网络架构，主要包括基于抽取特征的上采样、残差学习、上采样过程和优化函数：
  
  基于生成对抗的超分辨网络：
  
  本文提出的方法得到的结果如下：
  
  热红外数据集:ULB17-VT
  

• MonkeyNet将视频目标的动作序列映射到目标主体上,将来自驱动图像的信息映射到源图像上生成新的动作,(from 意大利特伦托大学)
  
  
  源码：https://github.com/AliaksandrSiarohin/monkey-net

• 提出了一种为数字图像边界进行多边形拟合的方法(from 南洋理工)
  

---

Daily Computer Vision Papers

[1] Title: Canonical Correlation Analysis for Misaligned Satellite Image Change Detection
Authors:Hichem Sahbi
[2] Title: Polygonal approximation of digital planar curve using novel significant measure
Authors:Mangayarkarasi Ramaiah, Dilip K. Prasad
[3] Title: Learning from Web Data: the Benefit of Unsupervised Object Localization
Authors:Xiaoxiao Sun, Liang Zheng, Yu-Kun Lai, Jufeng Yang
[4] Title: Learning Compositional Representations for Few-Shot Recognition
Authors:Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert
[5] Title: Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMD
Authors:Fabien André, Anne-Marie Kermarrec, Nicolas Le Scouarnec
[6] Title: A Multiscale Image Denoising Algorithm Based On Dilated Residual Convolution Network
Authors:Chang Liu, Zhaowei Shang, Anyong Qin
[7] Title: Cascaded Coarse-to-Fine Deep Kernel Networks for Efficient Satellite Image Change Detection
Authors:Hichem Sahbi
[8] Title: 3DSRnet: Video Super-resolution using 3D Convolutional Neural Networks
Authors:Soo Ye Kim, Jeongyeon Lim, Taeyoung Na, Munchurl Kim
[9] Title: 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects
Authors:Carole H. Sudre, Beatriz Gomez Anson, Silvia Ingala, Chris D. Lane, Daniel Jimenez, Lukas Haider, Thomas Varsavsky, Lorna Smith, H. Rolf Jäger, M. Jorge Cardoso
[10] Title: Detection of distal radius fractures trained by a small set of X-ray images and Faster R-CNN
Authors:Erez Yahalomi, Michael Chernofsky, Michael Werman
[11] Title: Face Hallucination Revisited: An Exploratory Study on Dataset Bias
Authors:Klemen Grm, Martin Pernuš, Leo Cluzel, Walter Scheirer, Simon Dobrišek, Vitomir Štruc
[12] Title: A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
Authors:Amena Khatun, Simon Denman, Sridha Sridharan, Clinton Fookes
[13] Title: Multi-component Image Translation for Deep Domain Generalization
Authors:Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan
[14] Title: Saliency Guided Hierarchical Robust Visual Tracking
Authors:Fangwen Tu, Shuzhi Sam Ge, Yazhe Tang, Chang Chieh Hang
[15] Title: Densely Semantically Aligned Person Re-Identification
Authors:Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Zhibo Chen
[16] Title: ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
Authors:Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, Peter Vajda, Matt Uyttendaele, Niraj K. Jha
[17] Title: Slimmable Neural Networks
Authors:Jiahui Yu, Linjie Yang, Ning Xu, Jianchao Yang, Thomas Huang
[18] Title: Efficient Misalignment-Robust Multi-Focus Microscopical Images Fusion
Authors:Yixiong Liang, Yuan Mao, Zhihong Tang, Meng Yan, Yuqian Zhao, Jianfeng Liu
[19] Title: Deep Learning to Assess Glaucoma Risk and Associated Features in Fundus Images
Authors:Sonia Phene, R. Carter Dunn, Naama Hammel, Yun Liu, Jonathan Krause, Naho Kitade, Mike Schaekermann, Rory Sayres, Derek J. Wu, Ashish Bora, Christopher Semturs, Anita Misra, Abigail E. Huang, Arielle Spitze, Felipe A. Medeiros, April Y. Maa, Monica Gandhi, Greg S. Corrado, Lily Peng, Dale R. Webster
[20] Title: An Optical Flow-Based Approach for Minimally-Divergent Velocimetry Data Interpolation
Authors:Berkay Kanberoglu, Dhritiman Das, Priya Nair, Pavan Turaga, David Frakes
[21] Title: Three Dimensional Reconstruction of Botanical Trees with Simulatable Geometry
Authors:Ed Quigley, Winnie Lin, Yilin Zhu, Ronald Fedkiw
[22] Title: SMILER: Saliency Model Implementation Library for Experimental Research
Authors:Calden Wloka (1), Toni Kunić (1), Iuliia Kotseruba (1), Ramin Fahimi (2), Nicholas Frosst (3), Neil D. B. Bruce (4), John K. Tsotsos (1) ((1) Department of Electrical Engineering and Computer Science York University, (2) Department of Computer Science University of Manitoba, (3) Google Brain Toronto, (4) Department of Computer Science Ryerson University)
[23] Title: Multimodal Sensor Fusion In Single Thermal image Super-Resolution
Authors:Feras Almasri, Olivier Debeir
[24] Title: A Smart Security System with Face Recognition
Authors:Trung Nguyen, Barth Lakshmanan, Weihua Sheng
[25] Title: Generative Models from the perspective of Continual Learning
Authors:Timothée Lesort, Hugo Caselles-Dupré, Michael Garcia-Ortiz, Andrei Stoian, David Filliat
[26] Title: A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization
Authors:Guoyun Tu, Yanwei Fu, Boyang Li, Jiarui Gao, Yu-Gang Jiang, Xiangyang Xue
[27] Title: Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors
Authors:Yedid Hoshen, Jitendra Malik
[28] Title: Cluster validity index based on Jeffrey divergence
Authors:Ahmed Ben Said, Rachid Hadjidj, Sebti Foufou
[29] Title: Animating Arbitrary Objects via Deep Motion Transfer
Authors:Aliaksandr Siarohin, Stéphane Lathuilière, Segey Tulyakov, Elisa Ricci, Nicu Sebe
[30] Title: A Scale Invariant Approach for Sparse Signal Recovery
Authors:Yaghoub Rahimi, Chao Wang, Hongbo Dong, Yifei Lou

Papers from arxiv.org

更多精彩请移步主页

---

pic from pixels.com