CVPR 2019 | 300篇 CVPR 2019 Oral 论文精选汇总，值得一看的 CV 论文都在这里

CVPR 2019 即将在美国长滩召开。今年有超过 5165 篇的大会论文投稿，最终录取 1299 篇，其中 Oral 论文近 300 篇。为了方便社区开发者和学术青年查找和阅读高价值论文，AI 研习社从入选的 Oral 论文中，按应用方向挑选了部分精华论文，贴在本文。

本篇论文精华帖社长将会持续更新，每天不间断推荐高价值论文，并且社长已经把相关论文下载好了，下载链接附在每个板块论文下方，您可点击文末【阅读原文】访问相关链接。

同时社长希望可爱的你们能够向 AI 研习社推荐自己的论文，自荐论文的用户有机会获得 AI 研习社赠送的大礼一份！

CVPR 2019 Oral 论文精选PDF下载地址：

https://ai.yanxishe.com/page/resourceDetail/819

CVPR 2019 全部论文PDF合集下载地址：

https://ai.yanxishe.com/page/resourceDetail/845

以下是论文具体地址：

百度

论文下载地址：

https://ai.yanxishe.com/page/resourceDetail/798

1.A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision

作者：Runmin Wu, Mengyang Feng, Wenlong Guan, Dong Wang, Huchuan Lu, Errui Ding

论文链接：https://pan.baidu.com/s/1EUxabfnEi_l5-ghUI3_qVQ

2.ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving

作者：Xibin Song, Peng Wang, Dingfu Zhou, Rui Zhu, Chenye Guan, Yuchao Dai, Hao Su, Hongdong Li, Ruigang Yang

论文链接：https://arxiv.org/abs/1811.12222

3.Attentive Feedback Network for Boundary-aware Salient Object Detection

作者：Mengyang Feng, Huchuan Lu, Errui Ding

论文链接：https://github.com/ArcherFMY/AFNet

4.Contrastive Adaptation Network for Unsupervised Domain Adaptation

作者：Guoliang Kang, Lu Jiang, Yi Yang, Alexander G Hauptmann

论文链接：https://arxiv.org/abs/1901.00976

5.Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation

作者：Hao Zhu, Xinxin Zuo, Sen Wang, Xun Cao, Ruigang Yang

论文链接：https://arxiv.org/abs/1904.10506

6.DM-GAN- Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis

作者：Minfeng Zhu, Pingbo Pan, Wei Chen, Yi Yang

论文链接：https://arxiv.org/abs/1904.01310

7.Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

作者：Yang He, Ping Liu, Ziwei Wang, Zhilan Hu, Yi Yang

论文链接：https://arxiv.org/abs/1811.00250

8.GA-Net- Guided Aggregation Net for End-to-end Stereo Matching

作者：Feihu Zhang, Victor Prisacariu, Ruigang Yang, Philip H.S. Torr

论文链接：https://arxiv.org/abs/1904.06587

9.Improving Transferability of Adversarial Examples with Input Diversity

作者：Cihang Xie, Zhishuai Zhang, Yuyin Zhou, Song Bai, Jianyu Wang, Zhou Ren, Alan Yuille

论文链接：https://arxiv.org/abs/1803.06978

10.Invariance Matters- Exemplar Memory for Domain Adaptive Person Re-identification

作者：Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang

论文链接：https://arxiv.org/abs/1904.01990

11.Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos

作者：Yang Wang, Zhenheng Yang, Peng Wang, Yi Yang, Chenxu Luo, Wei Xu

论文链接：https://arxiv.org/abs/1810.03654

12.L3-Net- Towards Learning based LiDAR Localization for Autonomous Driving

作者：Weixin Lu，Yao Zhou， Guowei Wan，Shenhua Hou，Shiyu Song

论文链接：https://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf

13.Look More Than Once- An Accurate Detector for Text of Arbitrary Shapes

作者：Chengquan Zhang, Borong Liang, Zuming Huang, Mengyi En, Junyu Han, Errui Ding, Xinghao Ding

论文链接：https://arxiv.org/abs/1904.06535

14.Searching for A Robust Neural Architecture in Four GPU Hours

作者：Xuanyi Dong, Yi Yang

论文链接：https://xuanyidong.com/publication/cvpr-2019-gradient-based-diff-sampler/

15.Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation

作者：Fengda Zhu, Linchao Zhu, Yi Yang

论文链接：https://arxiv.org/abs/1904.03895

16.STGAN- A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

作者：Ming Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, Wangmeng Zuo, Shilei Wen

论文链接：https://arxiv.org/abs/1904.09709

17.Taking A Closer Look at Domain Shift- Category-level Adversaries for Semantics Consistent Domain Adaptation

作者：Yawei Luo, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang

论文链接：https://arxiv.org/abs/1809.09478

人脸检测

论文下载地址：

https://ai.yanxishe.com/page/resourceDetail/796

1.Deep Tree Learning for Zero-shot Face Anti-Spoofing

作者：Yaojie Liu, Joel Stehouwer, Amin Jourabloo, Xiaoming Liu

论文链接：https://arxiv.org/abs/1904.02860

2.ArcFace: Additive Angular Margin Loss for Deep Face Recognition

作者：Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou

论文链接：https://arxiv.org/abs/1801.07698

3.APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs

作者：Ran Yi, Yong-Jin Liu

论文链接：https://cg.cs.tsinghua.edu.cn/papers/CVPR-2019-Drawing.pdf

4.High-Quality Face Capture Using Anatomical Muscles

作者：Michael Bao, Matthew Cong, Stéphane Grabli, Ronald Fedkiw

论文链接：https://arxiv.org/abs/1812.02836

5.AdaScale: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations

作者：Xiao Zhang, Rui Zhao, Yu Qiao, Xiaogang Wang, Hongsheng Li

论文链接：https://arxiv.org/abs/1905.00292

6.Combining 3D Morphable Models: A Largescale Face-and-Head Model

作者：Stylianos Ploumpis, Haoyang Wang, Nick Pears, William A. P. Smith, Stefanos Zafeiriou

论文链接：https://arxiv.org/abs/1903.03785

目标检测

论文下载地址：

https://ai.yanxishe.com/page/resourceDetail/815

1.C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

作者：Fang Wan, Chang Liu, Wei Ke, Xiangyang Ji, Jianbin Jiao, Qixiang Ye

论文链接：https://arxiv.org/abs/1904.05647

2.Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects

作者：Yusuke Niitani, Takuya Akiba, Tommi Kerola, Toru Ogawa, Shotaro Sano, Shuji Suzuki

论文链接：https://arxiv.org/abs/1811.10862

3.Shifting More Attention to Video Salient Object Detection

作者：Deng-Ping Fan, Wenguan Wang, Ming-Ming Cheng, Jianbing Shen

论文链接：https://mmcheng.net/zh/davsod/

运动和跟踪

1.Deeper and Wider Siamese Networks for Real-Time Visual Tracking

作者：Zhipeng Zhang, Houwen Peng

论文链接：https://arxiv.org/abs/1901.01660

2.Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields

作者：Yaadhav Raaj, Haroon Idrees, Gines Hidalgo, Yaser Sheikh

论文链接：https://arxiv.org/abs/1811.11975

3.Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking

作者：Andrii Maksai, Pascal Fua

论文链接：https://arxiv.org/abs/1811.10984

4.Graph Convolutional Tracking

作者：Junyu Gao，Tianzhu Zhang，Changsheng Xu

论文链接：http://nlpr-web.ia.ac.cn/mmc/homepage/jygao/gct_cvpr2019.html

5.ATOM: Accurate Tracking by Overlap Maximization

作者：Martin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg

论文链接：https://arxiv.org/abs/1811.07628

6.Visual Tracking via Adaptive Spatially-Regularized Correlation Filters

作者：Cheng Qian ，Guiping Zhou ，Chunguang Li ，Yuming Xu

论文链接：https://ieeexplore.ieee.org/document/8118454

姿态检测

1.Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation

作者：Xipeng Chen, Kwan-Yee Lin, Wentao Liu, Chen Qian, Xiaogang Wang, Liang Lin

论文链接：https://arxiv.org/abs/1903.08839

2.In the Wild Human Pose Estimation using Explicit 2D Features and Intermediate 3D Representations

作者：Ikhsanul Habibie, Weipeng Xu, Dushyant Mehta, Gerard Pons-Moll, Christian Theobalt

论文链接：https://arxiv.org/abs/1904.03289

3.CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark

作者：Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, Cewu Lu

论文链接：https://arxiv.org/abs/1812.00324

手势识别

1.H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions

作者：Bugra Tekin, Federica Bogo, Marc Pollefeys

论文链接：https://arxiv.org/abs/1904.05349

2.3D Hand Shape and Pose Estimation from a Single RGB Image

作者：Liuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang, Jianfei Cai, Junsong Yuan

论文链接：https://arxiv.org/abs/1903.00812

3.3D hand shape and pose from images in the wild

作者：Adnane Boukhayma, Rodrigo de Bem, Philip H.S. Torr

论文链接：https://arxiv.org/abs/1902.03451

4.Monocular Total Capture: Posing Face, Body, and Hands in the Wild

作者:Donglai Xiang, Hanbyul Joo, Yaser Sheikh

论文链接：https://arxiv.org/abs/1812.01598

5.Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

作者：Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, Michael J. Black

论文链接：https://arxiv.org/abs/1904.05866

GAN

1.Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping

作者：Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Kun Zhang, Dacheng Tao

论文链接：https://arxiv.org/abs/1809.05852

2.Label-Noise Robust Generative Adversarial Networks

作者：Takuhiro Kaneko, Yoshitaka Ushiku, Tatsuya Harada

论文链接：https://arxiv.org/abs/1811.11165

3.Sphere Generative Adversarial Network Based on Geometric Moment Matching

作者：Sung Woo Park ， Junseok Kwon

论文链接：http://cau.ac.kr/~jskwon/paper/SphereGAN_CVPR2019.pdf

4.A Style-Based Generator Architecture for Generative Adversarial Networks

作者：Tero Karras, Samuli Laine, Timo Aila

论文链接：https://arxiv.org/abs/1812.04948

5.Constrained Generative Adversarial Networks for Interactive Image Generation

作者：Eric Heim

论文链接：https://arxiv.org/abs/1904.02526

文本

1.Composing Text and Image for Image Retrieval - An Empirical Odyssey

作者：Nam Vo, Lu Jiang, Chen Sun, Kevin Murphy, Li-Jia Li, Li Fei-Fei, James Hays

论文链接：https://arxiv.org/abs/1812.07119

2.Semantics Disentangling for Text-to-Image Generation

作者：Guojun Yin, Bin Liu, Lu Sheng, Nenghai Yu, Xiaogang Wang, Jing Shao

论文链接：https://arxiv.org/abs/1904.01480

3.Text2Scene: Generating Compositional Scenes from Textual Descriptions

作者：Fuwen Tan, Song Feng, Vicente Ordonez

论文链接：https://arxiv.org/abs/1809.01110

视频分析

1.MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation

作者：Shuangjie Xu, Daizong Liu, Linchao Bao, Wei Liu, Pan Zhou

链接：https://arxiv.org/abs/1904.08141

2.5D Visual Sound

作者：Ruohan Gao、Kristen Grauman

链接：http://vision.cs.utexas.edu/projects/2.5D_visual_sound/

3.Efficient Video Classification Using Fewer Frames

作者：Shweta Bhardwaj, Mukundhan Srinivasan, Mitesh M. Khapra

链接：https://arxiv.org/abs/1902.10640

计算摄影学

1.From One Photon to a Billion: High Flux Imaging with Single-Photon Sensors

作者：Atul Ingle, Andreas Velten, Mohit Gupta

链接：https://arxiv.org/abs/1902.10190

2.Photon-Flooded Single-Photon 3D Cameras

作者：Anant Gupta, Atul Ingle, Andreas Velten, Mohit Gupta

链接：https://arxiv.org/abs/1903.08347

3.Acoustic Non-Line-of-Sight Imaging

作者：David B. Lindell, Gordon Wetzstein, Vladlen Koltun

链接：http://www.computationalimaging.org/publications/acoustic-non-line-of-sight-imaging/

4.Steady-state Non-Line-of-Sight Imaging

作者：Wenzheng Chen, Simon Daneau, Fahim Mannan, Felix Heide

链接：https://arxiv.org/abs/1811.09910

5.End-to-end Projector Photometric Compensation

作者：Bingyao Huang, Haibin Ling

链接：https://arxiv.org/abs/1904.04335

6.Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera

作者：Liyuan Pan, Cedric Scheerlinck, Xin Yu, Richard Hartley, Miaomiao Liu, Yuchao Dai

链接：https://arxiv.org/abs/1811.10180

机器人 + 驾驶

1.Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration

作者：De-An Huang, Suraj Nair, Danfei Xu, Yuke Zhu, Animesh Garg, Li Fei-Fei, Silvio Savarese, Juan Carlos Niebles

链接：https://arxiv.org/abs/1807.03480

2.Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

作者：Fei Xue, Xin Wang, Shunkai Li, Qiuyuan Wang, Junqiu Wang, Hongbin Zha

链接：https://arxiv.org/abs/1904.01892

3.Multimodal Explanations by Predicting Counterfactuality in Videos

作者：Atsushi Kanehira, Kentaro Takemoto, Sho Inayoshi, Tatsuya Harada

链接：https://arxiv.org/abs/1812.01263

4.HAQ: Hardware-Aware Automated Quantization

作者：Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han

链接：https://arxiv.org/abs/1811.08886

5.Learning to Explain with Complemental Examples

作者：Atsushi Kanehira, Tatsuya Harada

链接：https://arxiv.org/abs/1812.01280

医疗、生物和细胞显微图

1.Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning from Radiology Reports and Label Ontology

作者：Ke Yan (National Institutes of Health)*; Yifan Peng (NIH); Veit Sanfort (NIH); Mohammadhadi Bagheri (National Institutes of Health); Zhiyong Lu (NLM/NCBI/NIH); Ronald Summers (National Institutes of Health, Bethesda, Maryland, United States)

链接：https://arxiv.org/abs/1904.04661

2.Data augmentation using learned transforms for one-shot medical image segmentation

作者：Amy Zhao, Guha Balakrishnan, Frédo Durand, John V. Guttag, Adrian V. Dalca

链接：https://arxiv.org/abs/1902.09383v1

低级视觉

1.Neural RGB -> D Sensing: Depth and Uncertainty from a Video Camera

作者：Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa Narasimhan, Jan Kautz

链接：https://arxiv.org/abs/1901.02571

2.DAVANet: Stereo Deblurring with View Aggregation

作者：Shangchen Zhou, Jiawei Zhang, Wangmeng Zuo, Haozhe Xie, Jinshan Pan, Jimmy Ren

链接：https://arxiv.org/abs/1904.05065

3.DVC: An End-to-end Deep Video Compression Framework

作者：Guo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang, Chunlei Cai, Zhiyong Gao

链接：https://arxiv.org/abs/1812.00101

4.SOSNet: Second Order Similarity Regularization for Local Descriptor Learning

作者：Yurun Tian, Xin Yu, Bin Fan, Fuchao Wu, Huub Heijnen, Vassileios Balntas

链接：https://arxiv.org/abs/1904.05019

5.“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors

作者：Yossi Gandelsman, Assaf Shocher, Michal Irani

链接：https://arxiv.org/abs/1812.00467

社长提醒：想更方便地下载相关论文，记得点击底部的【阅读原文】快速访问对应链接。

2019 全球人工智能与机器人峰会

2019 年 7 月 12 日至 14 日，由中国计算机学会（CCF）主办、雷锋网和香港中文大学（深圳）联合承办，深圳市人工智能与机器人研究院协办的 2019 全球人工智能与机器人峰会（简称 CCF-GAIR 2019）将于深圳正式启幕。

届时，诺贝尔奖得主JamesJ. Heckman、中外院士、世界顶会主席、知名Fellow，多位重磅嘉宾将亲自坐阵，一起探讨人工智能和机器人领域学、产、投等复杂的生存态势。

  传送门在这里