​ 本文整理了2019年计算机视觉方面的综述论文，包含目标检测、图像分割(含语义/实例分割)、目标跟踪、医学图像分割、显著性目标检测、行为识别、深度估计等。可以使读者对相关领域有一个系统的了解。很适合初学者以及相关领域的研究人员。

object detection

1. Imbalance Problems in Object Detection: A Reviewintro: under review at TPAMI

arXiv: https://arxiv.org/abs/1909.00169

2. Recent Advances in Deep Learning for Object Detectionintro: From 2013 (OverFeat) to 2019 (DetNAS)

arXiv: https://arxiv.org/abs/1908.03673

3. A Survey of Deep Learning-based Object Detectionintro：From Fast R-CNN to NAS-FPN

arXiv: https://arxiv.org/abs/1907.09408

4. Object Detection in 20 Years: A Surveyintro：This work has been submitted to the IEEE TPAMI for possible publication

arXiv: https://arxiv.org/abs/1905.05055

图像分割

1. Deep Semantic Segmentation of Natural and Medical Images: A Reviewintro

从 FCN(2014) 到 Auto-DeepLab(2019)，本综述共含179篇语义分割和医学图像分割参考文献

arXiv: https://arxiv.org/abs/1910.07655

2. Understanding Deep Learning Techniques for Image Segmentationintro

本综述介绍了从2013年到2019年，主流的30多种分割算法（含语义/实例分割），50多种数据集，共计224篇参考文献

arXiv: https://arxiv.org/abs/1907.06119

目标跟踪

1. A Review of Visual Trackers and Analysis of its Application to Mobile Robotintro

本目标跟踪综述共含185篇参考文献！从传统方法到最新的深度学习网络

arXiv: https://arxiv.org/abs/1910.09761

2. Deep Learning in Video Multi-Object Tracking: A Surveyintro

38页目标跟踪综述，含30多种主流算法，共计174篇参考文献

arXiv: https://arxiv.org/abs/1907.12740

超分辨率

1. A Deep Journey into Super-resolution: A survey

arXiv: https://arxiv.org/abs/1904.07523

2. Deep Learning for Image Super-resolution: A Survey

arXiv: https://arxiv.org/abs/1902.06068

医学图像分割

1. Deep learning for cardiac image segmentation: A reviewintro

本医学图像分割综述从FCN(2014)到Dense U-net(2019)，超过250篇的参考文献（论文中光画图的工作量就超级大）

arXiv: https://arxiv.org/abs/1911.03723

2. Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications

arXiv: https://arxiv.org/abs/1911.02521

显著性目标检测

1. Salient Object Detection in the Deep Learning Era: An In-Depth Survey

arXiv: https://arxiv.org/abs/1904.09146

github: https://github.com/wenguanwang/SODsurvey

行为识别

1. Spatio-temporal Action Recognition: A Survey

arXiv: https://arxiv.org/abs/1901.09403

深度估计

1. Monocular Depth Estimation: A Survey

arXiv: https://arxiv.org/abs/1901.09402

地址连接：https://github.com/FranxYao/Deep-Generative-Models-for-Natural-Language-Processing

AutoML + NAS

1. Neural Architecture Search: A Survey

arXiv: https://arxiv.org/pdf/1808.05377

GAN

1. The Six Fronts of the Generative Adversarial Networks

arXiv: https://arxiv.org/pdf/1910.13076