【今日CS 视觉论文速览】31 Dec 2018
今日CS.CV计算机视觉论文速览
Mon, 31 Dec 2018
Totally 42 papers
Interesting:
-
识别艺术作品中的物体,利用非监督方法在绘画、卡通和草图中进行物体识别。利用风格迁移将绘画作品迁移到目标域中,并获取不变的特征,利用风格迁移在艺术作品中实现了自动标注。(from 匹兹堡大学)
多种形式的图像中抽取出不变的特征:
CASPA Dataset
ACCV2018 -
基于量子计算的图像处理,利用量子傅里叶变换及相关算法实现了灵活的量子图像表示、重建和边缘检测等任务。(from 阿肯色大学)
-
利用简单随机取样和随机局外点移除的方法来防止三维点云分类对抗攻击,(from 中科大)
基于随机点移除的攻击防御方法:
实验结果,红色表示对抗攻击样本:
Dataset:ModelNet40 -
基于先前的断层扫描进行有效的重建,用于检测新的结构, 对于新出现的未知结构,利用差分变化图和已有的结构进行精确的重建。(from 莫纳什大学)
新出现的结构来作为测试集:
较好的重建效果:
包括土豆、秋葵、芽等的植物三维扫描数据集 -
TROVE,一种基于三条射线和一个定点检测方法用于双目相机空间位姿估计。这一方法不依靠传统的角点搜索或者PnP问题求解,而是利用空间中交于一个定点的三条线和一个点来进行,达到了60Hz的实时速度(1280*760p双目)和高精度(0.2度,2cm)(from 香港大学)
平均误差图
-
显著性目标检测,基于层级的内容增强算法,(from 南开大学)
层级内容增强模块:
多尺度深度学习架构总结:
结果很好:
Dataset:s. DUTS [41], ECSSD [49], SOD [34], HKU-IS [23], THUR15K [6] and DUT-OMRON [50].
ref:
https://blog.csdn.net/ametor/article/details/51275084
dataset:http://mmcheng.net/zh/salobjbenchmark/
https://blog.csdn.net/StupidAutofan/article/details/80915535
人脸识别和人脸空间,TODO:(from 德州大学)
CNN顶层的相似性空间特征可视化:
识别强度变分的高层相似性空间可视化:
Dataset:CASIA-WebFace
UMDFaces
MS-Celeb-1M, download, collection
生物识别与安全技术研究中心
可视化:
t-sne:Visualizing data using t-sne
ref:
POETICON video dataset
Landscan Population Dataset,1 Geospatial ,2,Landscan
InsightFace
- 从图像级分类标签中得到由粗到精的语义分割结果,避免了使用像素级的分割标记或者目标级别的框,通过初始化的mask来不断回归改善,在每张图只需要一个类别标签的情况下就可以处理包含多个物体的照片。(from纽约城市大学)
结果:
Dataset:ImageNet,VOC,MIT Object Discovery Dataset
SIGNAL CLASSIFICATION UNDER STRUCTURED SPARSITY CONSTRAINTS,对于分类问题,一般包含了特征抽取和分类器两部分。在实际中常常遇到训练不充分和噪声、遮挡的影响、以及类内高方差类间低方差的问题。作者利用稀疏表示来解决这一系列问题,提出了基于稀疏表示的分类器SRC。
low-rank shared dictionary learning framework (LRSDL)
Daily Computer Vision Papers
[1] Title: Learning to Reconstruct Shapes from Unseen Classes
Authors:Xiuming Zhang, Zhoutong Zhang, Chengkai Zhang, Joshua B. Tenenbaum, William T. Freeman, Jiajun Wu
[2] Title: Center Emphasized Visual Saliency and Contrast-based Full Reference Image Quality Index
Authors:Md Abu Layek, Sanjida Afroz, TaeChoong Chung, Eui-Nam Huh
[3] Title: Artistic Object Recognition by Unsupervised Style Adaptation
Authors:Christopher Thomas, Adriana Kovashka
[4] Title: Image Processing in Quantum Computers
Authors:Aditya Dendukuri, Khoa Luu
[5] Title: Deflecting 3D Adversarial Point Clouds Through Outlier-Guided Removal
Authors:Hang Zhou, Kejiang Chen, Weiming Zhang, Han Fang, Wenbo Zhou, Nenghai Yu
[6] Title: Hierarchical LSTMs with Adaptive Attention for Visual Captioning
Authors:Jingkuan Song, Xiangpeng Li, Lianli Gao, Heng Tao Shen
[7] Title: Learning from past scans: Tomographic reconstruction to detect new structures
Authors:Preeti Gopal, Sharat Chandran, Imants Svalbe, Ajit Rajwade
[8] Title: TROVE Feature Detection for Online Pose Recovery by Binocular Cameras
Authors:Yuance Liu, Michael Z. Q. Chen
[9] Title: Salient Object Detection via High-to-Low Hierarchical Context Aggregation
Authors:Yun Liu, Yu Qiu, Le Zhang, JiaWang Bian, Guang-Yu Nie, Ming-Ming Cheng
[10] Title: Spatiotemporal Data Fusion for Precipitation Nowcasting
Authors:Vladimir Ivashkin, Vadim Lebedev
[11] Title: Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealed
Authors:Matthew Q. Hill (1), Connor J. Parde (1), Carlos D. Castillo (2), Y. Ivette Colon (1), Rajeev Ranjan (2), Jun-Cheng Chen (2), Volker Blanz (3), Alice J. O’Toole (1) ((1) The University of Texas at Dallas, (2) University of Maryland, (3) University of Siegen)
[12] Title: Coarse-to-fine Semantic Segmentation from Image-level Labels
Authors:Longlong Jing, Yucheng Chen, Yingli Tian
[13] Title: Signal Classification under structure sparsity constraints
Authors:Tiep Huu Vu
[14] Title: Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction
Authors:Qiqin Dai, Henry Chopp, Emeline Pouyet, Oliver Cossairt, Marc Walton, Aggelos K. Katsaggelos
[15] Title: DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
Authors:Husheng Zhou, Wei Li, Yuankun Zhu, Yuqun Zhang, Bei Yu, Lingming Zhang, Cong Liu
[16] Title: Hyperspectral Unmixing Based on Clustered Multitask Networks
Authors:Sara Khoshsokhan, Roozbeh Rajabi, Hadi Zayyani
[17] Title: Future semantic segmentation of time-lapsed videos with large temporal displacement
Authors:Talha Siddiqui, Samarth Bharadwaj
[18] Title: Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery?
Authors:Congcong Wang, Vivek Sharma, Yu Fan, Faouzi Alaya Cheikh, Azeddine Beghdadi, Ole Jacob Elle, Rainer Stiefelhagen
[19] Title: Semantic Driven Multi-Camera Pedestrian Detection
Authors:Alejandro López-Cifuentes, Marcos Escudero-Viñolo, Jesús Bescós, Pablo Carballeira
[20] Title: 3D Point-Capsule Networks
Authors:Yongheng Zhao, Tolga Birdal, Haowen Deng, Federico Tombari
[21] Title: SMPLR: Deep SMPL reverse for 3D human pose and shape recovery
Authors:Meysam Madadi, Hugo Bertiche, Sergio Escalera
[22] Title: Finite State Machines for Semantic Scene Parsing and Segmentation
Authors:Hichem Sahbi
[23] Title: S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation
Authors:Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit
[24] Title: Surface Networks via General Covers
Authors:Niv Haim, Nimrod Segol, Heli Ben-Hamu, Haggai Maron, Yaron Lipman
[25] Title: No-Reference Color Image Quality Assessment: From Entropy to Perceptual Quality
Authors:Xiaoqiao Chen, Qingyi Zhang, Manhui Lin, Guangyi Yang, Chu He
[26] Title: Chart-Text: A Fully Automated Chart Image Descriptor
Authors:Abhijit Balaji, Thuvaarakkesh Ramanathan, Venkateshwarlu Sonathi
[27] Title: Deep Learning based Early Detection and Grading of Diabetic Retinopathy Using Retinal Fundus Images
Authors:Sheikh Muhammad Saiful Islam, Md Mahedi Hasan, Sohaib Abdullah
[28] Title: Deception Detection by 2D-to-3D Face Reconstruction from Videos
Authors:Minh Ngô, Burak Mandira, Selim Fırat Yılmaz, Ward Heij, Sezer Karaoglu, Henri Bouma, Hamdi Dibeklioglu, Theo Gevers
[29] Title: Solving Archaeological Puzzles
Authors:Niv Derech, Ayellet Tal, Ilan Shimshoni
[30] Title: Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks
Authors:Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin
[31] Title: A Unified Learning Based Framework for Light Field Reconstruction from Coded Projections
Authors:Anil Kumar Vadathya, Sharath Girish, Kaushik Mitra
[32] Title: Exploring the Challenges towards Lifelong Fact Learning
Authors:Mohamed Elhoseiny, Francesca Babiloni, Rahaf Aljundi, Marcus Rohrbach, Manohar Paluri, Tinne Tuytelaars
[33] Title: Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN
Authors:Shervin Minaee, Amirali Abdolrashidi
[34] Title: Residual Dense Network for Image Restoration
Authors:Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Fu
[35] Title: Multi-resolution neural networks for tracking seismic horizons from few training images
Authors:Bas Peters, Justin Granek, Eldad Haber
[36] Title: TOP-GAN: Label-Free Cancer Cell Classification Using Deep Learning with a Small Training Set
Authors:Moran Rubin, Omer Stein, Nir A. Turko, Yoav Nygate, Darina Roitshtain, Lidor Karako, Itay Barnea, Raja Giryes, Natan T. Shaked
[37] Title: Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Authors:Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu
[38] Title: Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model
Authors:Tian Han, Erik Nijkamp, Xiaolin Fang, Mitch Hill, Song-Chun Zhu, Ying Nian Wu
[39] Title: InstaGAN: Instance-aware Image-to-Image Translation
Authors:Sangwoo Mo, Minsu Cho, Jinwoo Shin
[40] Title: Classification of radiology reports by modality and anatomy: A comparative study
Authors:Marina Bendersky, Joy Wu, Tanveer Syeda-Mahmood
[41] Title: Off-the-grid model based deep learning (O-MODL)
Authors:Aniket Pramanik, Hemant Kumar Aggarwal, Mathews Jacob
[42] Title: Learning Dynamic Generator Model by Alternating Back-Propagation Through Time
Authors:Jianwen Xie, Ruiqi Gao, Zilong Zheng, Song-Chun Zhu, Ying Nian Wu