今日新出 CV 论文汇总（含医学图像、目标检测、唇语识别、SLAM等）

最近，52CV分享了多篇CVPR 2019 的论文，有位群友问难道除了CVPR 就没有值得读的论文了吗？当然不是，其实很多优秀的工作并不一定出自CVPR。CVPR肯定也有很多灌水的。

另外，不同的方向，会投不同的期刊会议。做医学图像处理识别的人貌似不喜欢到CVPR上投论文，但arXiv CV部分有大量医学图像处理的文献。做AR增强现实人机交互方向，可能更看中ISMAR。

本文汇总了今天arXiv CV部分新出的所有论文，涉及方向众多，其中最多的是医学图像处理识别，还有目标检测、唇语识别、网络压缩、车辆跟踪与重识别、多标签学习算法评估等，配以简单的题目翻译，所有论文均提供下载，有感兴趣的朋友请于“我爱计算机视觉”对话界面回复“cv325”，即可收到下载地址。

今天有三篇CVPR 2019 的论文，排在前三位。

1

Few-shot Adaptive Faster R-CNN

Tao Wang, Xiaopeng Zhang, Li Yuan, Jiashi Feng

目标检测

https://arxiv.org/abs/1903.09372

2

CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

Zheng Tang, Milind Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, David Anastasiu, Jenq-Neng Hwang

城市级多目标多摄像头车辆跟踪与重识别。

https://arxiv.org/abs/1903.09254

3

SkelNetOn 2019 Dataset and Challenge on Deep Learning for Geometric Shape Understanding

Ilke Demir, Camilla Hahn, Kathryn Leonard, Geraldine Morin, Dana Rahbani, Athina Panotopoulou, Amelie Fondevilla, Elena Balashova, Bastien Durix, Adam Kortylewski

数据集。

https://arxiv.org/abs/1903.09233

4

On the Importance of Video Action Recognition for Visual Lipreading

Xinshuo Weng

人机交互，唇语识别，做来来自卡内基梅隆大学。

https://arxiv.org/pdf/1903.09616

5

Evaluation of a deep learning system for the joint automated detection of diabetic retinopathy and age-related macular degeneration

Cristina González-Gonzalo, Verónica Sánchez-Gutiérrez, Paula Hernández-Martínez, Inés Contreras, Yara T. Lechanteur, Artin Domanian, Bram van Ginneken, Clara I. Sánchez

医学图像处理识别，根据视网膜图像进行糖尿病检测。

https://arxiv.org/abs/1903.09555

6

Aggregated Deep Local Features for Remote Sensing Image Retrieval

Raffaele Imbriaco, Clint Sebastian, Egor Bondarev, Peter H.N. de With

遥感影像处理识别，聚合深度局部特征的遥感图像检索。

https://arxiv.org/abs/1903.09469

7

Factorised Representation Learning in Cardiac Image Analysis

Agisilaos Chartsias, Thomas Joyce, Giorgos Papanastasiou, Michelle Williams, David Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris

医学图像处理识别，心脏图像分析的分解表示学习。

https://arxiv.org/abs/1903.09467

8

Fast Bayesian Uncertainty Estimation of Batch Normalized Single Image Super-Resolution Network

Aupendu Kar, Prabir Kumar Biswas

图像超分辨率中的批归一化。

https://arxiv.org/abs/1903.09410

9

Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning

Xiaoguang Tu, Jian Zhao, Zihang Jiang, Yao Luo, Mei Xie, Yang Zhao, Linxiao He, Zheng Ma, Jiashi Feng

3D人脸重建，密集人脸对齐，2D辅助的自监督学习。

https://arxiv.org/abs/1903.09359

10

Overcoming Small Minirhizotron Datasets Using Transfer Learning

Weihuang Xu, Guohao Yu, Alina Zare, Brendan Zurweller, Diane Rowland, Joel Reyes-Cabrera, Felix B Fritschi, Roser Matamala, Thomas E. Juenger

迁移学习。

https://arxiv.org/abs/1903.09344

11

Pose Estimation of Periacetabular Osteotomy Fragments with Intraoperative X-Ray Navigation

Robert B. Grupp, Rachel A. Hegeman, Ryan J. Murphy, Clayton P. Alexander, Yoshito Otake, Benjamin A. McArthur, Mehran Armand, Russell H. Taylor

医学图像处理识别，髋臼周围截骨骨碎片手术中X射线导航姿态估计。

https://arxiv.org/abs/1903.09339

12

Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations

Chen Qin, Bibo Shi, Rui Liao, Tommaso Mansi, Daniel Rueckert, Ali Kamen

多模态图像无监督非刚体配准。

https://arxiv.org/abs/1903.09331

13

A resnet-based universal method for speckle reduction in optical coherence tomography images

Cai Ning, Shi Fei, Hu Dianlin, Chen Yang

利用ResNet网络进行图像去噪。

https://arxiv.org/abs/1903.09330

14

Towards Optimal Structured CNN Pruning via Generative Adversarial Learning

Shaohui Lin, Rongrong Ji, Chenqian Yan, Baochang Zhang, Liujuan Cao, Qixiang Ye, Feiyue Huang, David Doermann

基于GAN的最有结构化CNN剪枝。

https://arxiv.org/abs/1903.09291

15

Fast and accurate reconstruction of HARDI using a 1D encoder-decoder convolutional network

Shi Yin, Zhengqiang Zhang, Qinmu Peng, Xinge You

医学影像的3D重建。

https://arxiv.org/abs/1903.09272

16

Deep Learning with Anatomical Priors: Imitating Enhanced Autoencoders in Latent Space for Improved Pelvic Bone Segmentation in MRI

Duc Duy Pham, Gurbandurdy Dovletov, Sebastian Warwas, Stefan Landgraeber, Marcus Jäger, Josef Pauli

MRI图像分割。

https://arxiv.org/abs/1903.09263

17

Deep Radiomics for Brain Tumor Detection and Classification from Multi-Sequence MRI

Subhashis Banerjee, Sushmita Mitra, Francesco Masulli, Stefano Rovetta

医学图像处理识别，MRI脑肿瘤的检测与分类

https://arxiv.org/abs/1903.09240

18

Multi-person Articulated Tracking with Spatial and Temporal Embeddings

Sheng Jin, Wentao Liu, Wanli Ouyang, Chen Qian

时空信息嵌入的多人关键点跟踪。

https://arxiv.org/abs/1903.09214

19

Semantic Comparison of State-of-the-Art Deep Learning Methods for Image Multi-Label Classification

Adam Kubany, Shimon Ben Ishay, Ruben-sacha Ohayon, Armin Shmilovici, Lior Rokach, Tomer Doitshman

深度学习多标签分类的语义比较评估。

https://arxiv.org/abs/1903.09190

20

Quantitative Depth Quality Assessment of RGBD Cameras At Close Range Using 3D Printed Fixtures

Michele Pratusevich, Jason Chrisos, Shreyas Aditya

RGBD相机的深度质量评价。

https://arxiv.org/abs/1903.09169

21

Sparse2Dense: From direct sparse odometry to dense 3D reconstruction

Jiexiong Tang, John Folkesson, Patric Jensfelt

SLAM算法，Sparse2Dense，从稀疏里程计到密集3D重建。

https://arxiv.org/abs/1903.09199

论文下载：

请于“我爱计算机视觉”对话界面回复“cv325”，即可收到下载地址。