【今日CV 计算机视觉论文速览】 11 Mar 2019
今日CS.CV计算机视觉论文速览
Mon, 11 Mar 2019
Totally 35 papers
Interesting:
📚Three-Player GAN,在通常GAN的基础上增加了生成器和分类器间的竞争。利用C来合成更为困难的样本，随后这些样本将提高分类器的能力。（from ESAT-PSI）
当分类器加入时，生成的数据分布改变了不再是real/fake，而是更难分辨的中间数据：
📚, 基于分级的方法来实现弱监督语义分割，加快语义分割的速度。(from Eindhoven University of Technology)
基础分类器先分类，而后将相关车辆行人的像素交给子分类器，右图是相关数据集和模型表现。
📚3DN,三维的可变形网络，实现了三维模型的风格迁移。（from USC）
其损失包含了以下部分：
mesh的两项为形状损失，包含了CD（chamfer ）和EMD（earth mover）两项，来确定变型后的模型与目标模型的外形。point的两项用于保持对称性，所以要通过点云来比较。为了避免自交叉引入了局域变异不变性损失，保持源形状的局域几何特性拉普拉斯损失。
code ：github.com/laughtervv/3DN
📚FastDepth,用于嵌入式设备的快速单目深度估计,利用了depthwise separable的解码器和剪枝算法NetAdapt（from MIT）
用于嵌入式的网络模型架构：
在TX2上的精度速度：
项目主页： http://fastdepth.mit.edu/
数据集：NYC Depth Dataset V2
code:https://github.com/dwofk/fast-depth
📚MLOSR：Open-Set未知类别识别，通过将自动编码器和分类结合起来可以有效通过多任务提高open-set的表现。（From Johns Hopkins University）
相关数据集和方法：
code:github.com/otkupjnoz/mlosr
📚HOPS-Net,通过RGB图估计手持物体的位姿。通过引入手部的信息，来得到更精确的结果。模型在大型合成数据集上进行了训练，并使用了图像迁移来将虚拟训练转移到真实数据上来。(from KTH)
网络的流程框架如下，结合了分割和位姿估计：
基于模拟环境GraspIt! 合成数据。
📚SVST, 一种高效的视频场景文字识别，包括检查、跟踪、分析和识别几个过程。（from 浙江大学）
视频文字检测和视频流打分联合学习：
dataset: IC13 [19] and IC15 [18]
📚CLEVR-Dialog, 用于多轮对话推理对话数据集。(from CMU FB GIT)
与MNIST Dialog， VisDial数据集的比较：
📚基于WNet GAN 优化遥感数字表面建模，（from German Aerospace Center）
模型架构和一些结果：
ref:城市数字模型：https://www.businesslocationcenter.de/downloadportal/
📚ICDAR2019中国家谱的历史文献识别
******ref:http://icdar2019.org/competitions-2/
📚基于分形随机场的海洋石油泄漏检测，基于长程依赖性的随机场和小波滤波器（from Universidad de Buenos Aires）
📚植物根茎检测，(from 弗罗里达大学)
参考方法：MI-ACE, miSVM, MIForests
📚自动化近地小行星检测系统综述，（from Technical University of Cluj-Napoca）
Daily Computer Vision Papers
[1] *Title: Geometry-Aware Graph Transforms for Light Field Compact Representation
Authors:Mira Rizkallah, Xin Su, Thomas Maugey, Christine Guillemot
[2] *Title: Prediction and Sampling with Local Graph Transforms for Quasi-Lossless Light Field Compression
Authors:Mira Rizkallah, Thomas Maugey, Christine Guillemot
[3] *Title: Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
Authors:Adrian V. Dalca, Guha Balakrishnan, John Guttag, Mert R. Sabuncu
[4] **Title: DSM Building Shape Refinement from Combined Remote Sensing Images based on Wnet-cGANs
Authors:Ksenia Bittner, Marco Körner, Peter Reinartz
[5] *Title: OpenCL-based FPGA accelerator for disparity map generation with stereoscopic event cameras
Authors:David Castells-Rufas, Jordi Carrabina
[6] Title: Unsupervised Data Imputation via Variational Inference of Deep Subspaces
Authors:Adrian V. Dalca, John Guttag, Mert R. Sabuncu
[7] **Title: A Three-Player GAN: Generating Hard Samples To Improve Classification Networks
Authors:Simon Vandenhende, Bert De Brabandere, Davy Neven, Luc Van Gool
[8] *Title: Auto-Encoding Progressive Generative Adversarial Networks For 3D Multi Object Scenes
Authors:Vedant Singh, Manan Oza, Himanshu Vaghela, Pratik Kanani
[9] *Title: On Boosting Semantic Street Scene Segmentation with Weak Supervision
Authors:Panagiotis Meletis, Gijs Dubbelman
[10] Title: Joint Learning of Brain Lesion and Anatomy Segmentation from Heterogeneous Datasets
Authors:Nicolas Roulet, Diego Fernandez Slezak, Enzo Ferrante
[11] **Title: Unsupervised Medical Image Translation Using Cycle-MedGAN
Authors:Karim Armanious, Chenming Jiang, Sherif Abdulatif, Thomas Küstner, Sergios Gatidis, Bin Yang
[12] Title: Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval
Authors:Anjan Dutta, Zeynep Akata
[13] **Title: ICDAR 2019 Historical Document Reading Challenge on Large Structured Chinese Family Records
Authors:Foteini Simistira Liwicki, Rajkumar Saini, Derek Dobson, Jon Morrey, Marcus Liwicki
[14] **Title: Learning to Estimate Pose and Shape of Hand-Held Objects from RGB Images
Authors:Mia Kokic, Danica Kragic, Jeannette Bohg
[15] Title: Complex Valued Gated Auto-encoder for Video Frame Prediction
Authors:Niloofar Azizi, Nils Wandel, Sven Behnke
[16] Title: Knowledge-Embedded Routing Network for Scene Graph Generation
Authors:Tianshui Chen, Weihao Yu, Riquan Chen, Liang Lin
[17] **Title: 3DN: 3D Deformation Network
Authors:Weiyue Wang, Duygu Ceylan, Radomir Mech, Ulrich Neumann
[18] Title: Semi- and Weakly Supervised Directional Bootstrapping Model for Automated Skin Lesion Segmentation
Authors:Yutong Xie, Jianpeng Zhang, Yong Xia, Chunhua Shen
[19] Title: Learning from Synthetic Data for Crowd Counting in the Wild
Authors:Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan
[20] **Title: Efficient Video Scene Text Spotting: Unifying Detection, Tracking, and Recognition
Authors:Zhanzhan Cheng, Jing Lu, Jianwen Xie, Yi Niu, Shiliang Pu, Fei Wu
[21] Title: Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
Authors:Romero Morais, Vuong Le, Truyen Tran, Budhaditya Saha, Moussa Mansour, Svetha Venkatesh
[22] *Title: FastDepth: Fast Monocular Depth Estimation on Embedded Systems
Authors:Diana Wofk, Fangchang Ma, Tien-Ju Yang, Sertac Karaman, Vivienne Sze
[23] Title: Ranked List Loss for Deep Metric Learning
Authors:Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Romain Garnier, Neil M. Robertson
[24] *Title: Pattern Recognition in SAR Images using Fractional Random Fields and its Possible Application to the Problem of the Detection of Oil Spills in Open Sea
Authors:Agustín Mailing, Segundo A. Molina, José L. Hamkalo, Fernando R. Dobarro, Juan M. Medina, Bruno Cernuschi-Frías, Daniel A. Fernández, Érica Schlaps
[25] Title: Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss
Authors:Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto, Samuel Rota Bulo, Nicu Sebe, Elisa Ricci
[26] *Title: Root Identification in Minirhizotron Imagery with Multiple Instance Learning
Authors:Guohao Yu, Alina Zare, Hudanyun Sheng, Roser Matamala, Joel Reyes-Cabrera, Felix B. Frischi, Thomas E. Juenger
[27] Title: Fast Video Retargeting Based on Seam Carving with Parental Labeling
Authors:Zhu Chuning
[28] **Title: CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog
Authors:Satwik Kottur, José M. F. Moura, Devi Parikh, Dhruv Batra, Marcus Rohrbach
[29] **Title: Deep CNN-based Multi-task Learning for Open-Set Recognition
Authors:Poojan Oza, Vishal M. Patel
[30] *Title: Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
Authors:Adrian V. Dalca, John Guttag, Mert R. Sabuncu
[31] Title: A Learnable ScatterNet: Locally Invariant Convolutional Layers
Authors:Fergal Cotter, Nick Kingsbury
[32] Title: Stable Backward Diffusion Models that Minimise Convex Energies
Authors:Leif Bergerhoff, Marcelo Cárdenas, Joachim Weickert, Martin Welk
[33] **Title: NEARBY Platform for Automatic Asteroids Detection and EURONEAR Surveys
Authors:Dorian Gorgan, Ovidiu Vaduvescu, Teodor Stefanut, Victor Bacu, Adrian Sabou, Denisa Copandean Balazs, Constantin Nandra, Costin Boldea, Afrodita Boldea, Marian Predatu, Viktoria Pinter, Adrian Stanica
[34] Title: Research on the pixel-based and object-oriented methods of urban feature extraction with GF-2 remote-sensing images
Authors:Dong-dong Zhang, Lei Zhang, Vladimir Zaborovsky, Feng Xie, Yan-wen Wu, Ting-ting Lu
[35] Title: Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system
Authors:Keelin Murphy, Shifa Salman Habib, Syed Mohammad Asad Zaidi, Saira Khowaja, Aamir Khan, Jaime Melendez, Ernst T. Scholten, Farhan Amad, Steven Schalekamp, Maurits Verhagen, Rick H. H. M. Philipsen, Annet Meijers, Bram van Ginneken
