今日CS.CV計算機視覺論文速覽
Tue, 1 Jan 2019
Totally 52 papers

Interesting:

• 圖片快速視覺效果增強演算法，基於Ignatov的演算法提高影象的感知質量，利用了輕量級的模型得到了6.3倍的提速。主要就超分辨、色彩校正和去模糊等方面提出了內容損失、紋理損失、色彩損失以及全域性變化損失等。（from 蘇黎世理工）
  網路架構如下：
  
  
  一些結果：
  
  資料集DPED dataset,包含手機照片和對應的單反照片。
  Code

• GAN生成影象的指紋,研究從自相關性、殘差相關性以及混淆矩陣等方面進行了度量，發現GAN具有獨特的數字指紋可以被識別出來。(那不勒斯費迪南德||大學)
  

  
  
  資料集：RAISE dataset

• 結合殘差和稀疏卷積編碼實現影象超分辨RL-CSC,其中卷積稀疏編碼可以迭代的學習出輸入特徵並稀疏編碼，同時殘差可以再網路加深時保持訓練的穩定。在工作Learned Iterative Shrinkage Threshold Algorithm (LISTA)的基礎上改進，利用全卷積的方式實現，增加了模型的可解釋性。
  
  一些相關的迴圈結構：
  
  code
  Dataset: Berkeley Segmentation Dataset,BSD100,Urban100

• 檢測蜜蜂運動軌跡,實現了對於緻密、迅速無規則物件的軌跡跟蹤。主要方法是利用基於分割的檢測方法獲得短距離的區域性軌跡，隨後利用目標識別模型來融合這些軌跡。主要的貢獻在於建立一種稱為畫素識別

  （Pixel personality）的機制來從進行軌跡融合。
  （from 沖繩科技）
  
  一些蜜蜂的軌跡跟總結果
  
  蜜蜂Dataset，密集慎入

• 多種背景光照變化下的目標檢測,在140個網路攝像頭的5M張照片上測評了yolo演算法的應對不同光照變化的能力。研究表明演算法無法適應光照變化和夜間環境，並建議未來的目標檢測演算法應該在相關資料集上進行訓練才能保證各個時間段的有效性。（from普渡大學）
  不同場景下的光照變化：
  
  不同時間下的變化：
  

• 一種準確高效的字元識別方法，（from 艾斯尤特大學 Egypt）
  
  阿拉伯手寫字元KFUPM Handwritten Arabic TexT (KHATT)：

  http://khatt.ideas2serve.net/index.php

• 利用簡單快速的線性求解器方法解決了相機捲簾快門帶來的絕對定位問題, 使用了6點求解器達到了R6P求解器的效果。（from 日本國立情報研究所）
  
  ref:https://www.nii.ac.jp/en/

• 基於RGB-D點雲的三維卷積無模型位姿估計，與通常需要目標三維模型的位姿估計問題不同的是，這一工作使用了兩個步驟，通過3D卷積處理了RGB-D點雲資訊進行點雲估計。實現了1cm的定位精度和5度的角度精度。並在真實的機器人抓取任務中獲得90%的準確率。此外在研究過程中，還利用運動捕捉系統實現了點雲的精確標註，能為訓練提供大量高精度標記的點雲資料。(from 南洋理工)
  
  三維卷積網路模型：
  
  在ros中的流程，點雲>體素化>旋轉/平移>軌跡規劃
  

• 通過變化分解實現快速全域性點雲剛性配準, 為了解決點雲的剛性配準問題，避免BnB方法龐大的計算量和低效的約束評價方法，研究人員提出了一種具有不變性的向量，將6D剛體變換分解為了3D旋轉和平移的搜尋。在減小計算維度的條件下提高了效率，並利用新的資料結果3D Integral Volume來加速Bound過程。（from 復旦 tum）
  
  選擇和平移的空間限制Bound：
  
  Synthetic Data：Stanford 3D Scanning Repository [50], Chicken,Rhino and T-rex from Mians dataset [51], [52],Camera from the Stefan Hinterstoissers dataset [53] and Hand from the Large Geometric Models Archive at Georgia Tech [54]。
  Real data:Stanford Scanning Models, Indoor Scan Data（from matlab）, Clinical Data(3D MRI 資料)
  http://graphics.stanford.edu/data/3Dscanrep/
  http://campar.in.tum.de/Main/StefanHinterstoisser
  https://www.cc.gatech.edu/projects/

Daily Computer Vision Papers

[1] Title: Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks
Authors:Alexander Sax, Bradley Emi, Amir R. Zamir, Leonidas Guibas, Silvio Savarese, Jitendra Malik
[2] Title: The role of visual saliency in the automation of seismic interpretation
Authors:Muhammad Amir Shafiq, Tariq Alshawi, Zhiling Long, Ghassan AlRegib
[3] Title: Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding
Authors:Menglei Zhang, Zhou Liu, Lei Yu
[4] Title: High Quality Monocular Depth Estimation via Transfer Learning
Authors:Ibraheem Alhashim, Peter Wonka
[5] Title: Large-Scale Object Detection of Images from Network Cameras in Variable Ambient Lighting Conditions
Authors:Caleb Tung, Matthew R. Kelleher, Ryan J. Schlueter, Binhan Xu, Yung-Hsiang Lu, George K. Thiruvathukal, Yen-Kuang Chen, Yang Lu
[6] Title: Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
Authors:Mohamed Yousef, Khaled F. Hussain, Usama S. Mohammed
[7] Title: Fast Perceptual Image Enhancement
Authors:Etienne de Stoutz, Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Luc Van Gool
[8] Title: Do GANs leave artificial fingerprints?
Authors:Francesco Marra, Diego Gragnaniello, Luisa Verdoliva, Giovanni Poggi
[9] Title: Sequential Gating Ensemble Network for Noise Robust Multi-Scale Face Restoration
Authors:Zhibo Chen, Jianxin Lin, Tiankuang Zhou, Feng Wu
[10] Title: Pixel personality for dense object tracking in a 2D honeybee hive
Authors:Katarzyna Bozek, Laetitia Hebert, Alexander S Mikheyev, Greg J Stephens
[11] Title: PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
Authors:Sida Peng, Yuan Liu, Qixing Huang, Hujun Bao, Xiaowei Zhou
[12] Title: Predicting Group Cohesiveness in Images
Authors:Shreya Ghosh, Abhinav Dhall, Nicu Sebe
[13] Title: The meaning of “most” for visual question answering models
Authors:Alexander Kuhnle, Ann Copestake
[14] Title: Total Variation with Overlapping Group Sparsity and Lp Quasinorm for Infrared Image Deblurring under Salt-and-Pepper Noise
Authors:Xingguo Liua, Yinping Chena, Zhenming Penga, Juan Wu
[15] Title: SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks
Authors:Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan
[16] Title: Sex-Classification from Cell-Phones Periocular Iris Images
Authors:Juan Tapia, Claudia Arellano, Ignacio Viedma
[17] Title: Unsupervised monocular stereo matching
Authors:Zhimin Zhang, Jianzhong Qiao, Shukuan Lin
[18] Title: Path-Invariant Map Networks
Authors:Zaiwei Zhang, Zhenxiao Liang, Lemeng Wu, Xiaowei Zhou, Qixing Huang
[19] Title: Actor Conditioned Attention Maps for Video Action Detection
Authors:Oytun Ulutan, Swati Rallapalli, Mudhakar Srivatsa, B.S. Manjunath
[20] Title: Solar Potential Analysis of Rooftops Using Satellite Imagery
Authors:Akash Kumar, S. Indu
[21] Title: Cascaded V-Net using ROI masks for brain tumor segmentation
Authors:Adrià Casamitjana, Marcel Catà, Irina Sánchez, Marc Combalia, Verónica Vilaplana
[22] Title: Leishmaniasis Parasite Segmentation and Classification using Deep Learning
Authors:Marc Górriz, Albert Aparicio, Berta Raventós, Verónica Vilaplana, Elisa Sayrol, Daniel López-Codina
[23] Title: Fingerprint Presentation Attack Detection: Generalization and Efficiency
Authors:Tarang Chugh, Anil K. Jain
[24] Title: Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification
Authors:Marc Combalia, Veronica Vilaplana
[25] Title: Linear solution to the minimal absolute pose rolling shutter problem
Authors:Zuzana Kukelova, Cenek Albl, Akihiro Sugimoto, Tomas Pajdla
[26] Title: CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences
Authors:Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Xiao Xiang Zhu
[27] Title: A High-Performance CNN Method for Offline Handwritten Chinese Character Recognition and Visualization
Authors:Pavlo Melnyk, Zhiqiang You, Keqin Li
[28] Title: DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
Authors:Xianghong Fang, Haoli Bai, Ziyi Guo, Bin Shen, Steven Hoi, Zenglin Xu
[29] Title: Brain MRI super-resolution using 3D generative adversarial networks
Authors:Irina Sanchez, Veronica Vilaplana
[30] Title: Feature Preserving and Uniformity-controllable Point Cloud Simplification on Graph
Authors:Junkun Qi, Wei Hu, Zongming Guo
[31] Title: EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Authors:Houjing Huang, Wenjie Yang, Xiaotang Chen, Xin Zhao, Kaiqi Huang, Jinbin Lin, Guan Huang, Dalong Du
[32] Title: Rendu basé image avec contraintes sur les gradients
Authors:Grégoire Nieto (LJK), Frédéric Devernay (PRIMA), James Crowley (PERVASIVE)
[33] Title: Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image
Authors:Yusuke Yoshiyasu, Ryusuke Sagawa, Ko Ayusawa, Akihiko Murai
[34] Title: A Deep Learning based Framework to Detect and Recognize Humans using Contactless Palmprints in the Wild
Authors:Yang Liu, Ajay Kumar
[35] Title: Support Vector Guided Softmax Loss for Face Recognition
Authors:Xiaobo Wang, Shuo Wang, Shifeng Zhang, Tianyu Fu, Hailin Shi, Tao Mei
[36] Title: Fast and Globally Optimal Rigid Registration of 3D Point Sets by Transformation Decomposition
Authors:Xuechen Li, Yinlong Liu, Yiru Wang, Chen Wang, Manning Wang, Zhijian Song
[37] Title: Annotation-cost Minimization for Medical Image Segmentation using Suggestive Mixed Supervision Fully Convolutional Networks
Authors:Yash Bhalgat, Meet Shah, Suyash Awate
[38] Title: Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis
Authors:Jianqiao Wangni, Dahua Lin, Ji Liu, Kostas Daniilidis, Jianbo Shi
[39] Title: CamLoc: Pedestrian Location Detection from Pose Estimation on Resource-constrained Smart-cameras
Authors:Adrian Cosma, Ion Emilian Radoi, Valentin Radu
[40] Title: CFA Bayer image sequence denoising and demosaicking chain
Authors:Antoni Buades, Joan Duran
[41] Title: Class-Aware Adversarial Lung Nodule Synthesis in CT Images
Authors:Jie Yang, Siqi Liu, Sasa Grbic, Arnaud Arindra Adiyoso Setio, Zhoubing Xu, Eli Gibson, Guillaume Chabin, Bogdan Georgescu, Andrew F. Laine, Dorin Comaniciu
[42] Title: Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences
Authors:Vignesh Prasad, Dipanjan Das, Brojeshwar Bhowmick
[43] Title: Towards a topological-geometrical theory of group equivariant non-expansive operators for data analysis and machine learning
Authors:Mattia G. Bergomi, Patrizio Frosini, Daniela Giorgi, Nicola Quercioli
[44] Title: An introduction to domain adaptation and transfer learning
Authors:Wouter M. Kouw
[45] Title: BNN+: Improved Binary Network Training
Authors:Sajad Darabi, Mouloud Belbahri, Matthieu Courbariaux, Vahid Partovi Nia
[46] Title: Cluster-Based Active Learning
Authors:Fábio Perez, Rémi Lebret, Karl Aberer
[47] Title: Deep Residual Learning in the JPEG Transform Domain
Authors:Max Ehrlich, Larry Davis
[48] Title: ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers
Authors:Ao Ren, Tianyun Zhang, Shaokai Ye, Jiayu Li, Wenyao Xu, Xuehai Qian, Xue Lin, Yanzhi Wang
[49] Title: Machine learning in resting-state fMRI analysis
Authors:Meenakshi Khosla, Keith Jamison, Gia H. Ngo, Amy Kuceyeski, Mert R. Sabuncu
[50] Title: Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks
Authors:Ghouthi Boukli Hacene (ELEC), Vincent Gripon, Matthieu Arzel (ELEC), Nicolas Farrugia (ELEC), Yoshua Bengio (DIRO)
[51] Title: 3D Convolution on RGB-D Point Clouds for Accurate Model-free Object Pose Estimation
Authors:Zhongang Cai, Cunjun Yu, Quang-Cuong Pham
[52] Title: Kymatio: Scattering Transforms in Python
Authors:Mathieu Andreux, Tomás Angles, Georgios Exarchakis, Roberto Leonarduzzi, Gaspar Rochette, Louis Thiry, John Zarka, Stéphane Mallat, Joakim andén, Eugene Belilovsky, Joan Bruna, Vincent Lostanlen, Matthew J. Hirn, Edouard Oyallon, Sixhin Zhang, Carmine Cella, Michael Eickenberg

Papers from arxiv.org

更多精彩請移步主頁

pic from pixels.com