CVPR2019 | 03-21日更新10篇论文及代码汇总（2篇oral，含语义分割、物体识别、GAN、SLAM等）

2019 年 3 月 21 日 极市平台

加入极市专业CV交流群，与6000+来自腾讯，华为，百度，北大，清华，中科院等名企名校视觉开发者互动交流！更有机会与李开复老师等大牛群内互动！

同时提供每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流。点击文末“阅读原文”立刻申请入群~

前段时间，计算机视觉顶会CVPR 2019 公布了接收结果，极市也对此做了相关报道：1300篇！CVPR2019接收结果公布，你中了吗？。目前官方只公布了接收论文ID列表，极市已汇总目前公开的所有论文链接及code（目前已更新221篇），今日更新论文如下：

CVPR2019 全部论文汇总：

https://github.com/extreme-assistant/cvpr2019

CVPR2019 论文解读

http://bbs.cvmart.net/topics/287/cvpr2019

1.Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses(Oral)
作者：Jérôme Rony, Luiz G. Hafemann, Luiz S. Oliveira, Ismail Ben Ayed, Robert Sabourin, Eric Granger
论文链接：https://arxiv.org/abs/1811.09600
代码链接：

https://github.com/jeromerony/fast_adversarial

2.Direct Object Recognition Without Line-of-Sight Using Optical Coherence(非视距物体识别技术)
作者：Xin Lei, Liangyu He, Yixuan Tan, Ken Xingze Wang, Xinggang Wang, Yihan Du, Shanhui Fan, Zongfu Yu
论文链接：https://arxiv.org/abs/1903.07705

3.Graphical Contrastive Losses for Scene Graph Generation
作者：Ji Zhang, Kevin J. Shih, Ahmed Elgammal, Andrew Tao, Bryan Catanzaro
论文链接：https://arxiv.org/abs/1903.02728
代码链接：

https://github.com/NVIDIA/ContrastiveLosses4VRD

4.Knowledge Adaptation for Efficient Semantic Segmentation（语义分割）
作者：Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, Youliang Yan
论文链接：https://arxiv.org/abs/1903.04688

5.Improving Semantic Segmentation via Video Propagation and Label Relaxation(oral)
作者：Yi Zhu, Karan Sapra, Fitsum A. Reda, Kevin J. Shih, Shawn Newsam, Andrew Tao, Bryan Catanzaro
论文链接：https://arxiv.org/abs/1812.01593

6.Pay attention! - Robustifying a Deep Visuomotor Policy through Task-Focused Attention
作者：Pooya Abolghasemi, Amir Mazaheri, Mubarak Shah, Ladislau Bölöni
论文链接：https://arxiv.org/abs/1809.10093

7.Cross-task weakly supervised learning from instructional videos
作者：Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis, David Fouhey, Ivan Laptev, Josef Sivic
论文链接：https://arxiv.org/abs/1903.08225

8.In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
作者：Marin Oršić, Ivan Krešo, Petra Bevandić, Siniša Šegvić
论文链接：https://arxiv.org/abs/1903.08469
代码链接：https://github.com/orsic/swiftnet

9.OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
作者：Pramuditha Perera, Ramesh Nallapati, Bing Xiang
论文链接：https://arxiv.org/abs/1903.08550

10.An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM
作者：Patrick Geneva, James Maley, Guoquan Huang
论文链接：https://arxiv.org/abs/1903.08636

*延伸阅读