CVPR2019论文抢鲜看！20篇涵盖目标检测、跨模态、视频处理、语义分割和姿态估计等方向论文

2019 年 3 月 3 日 专知

【导读】计算机视觉顶会 CVPR 2019 的论文接前几天公布了接受论文：在超过 5100 篇投稿中，共有 1300 篇被接收，达到了接近 25.2% 的接收率。今天组委会公布口头报告论文(Oral presentation)，专知特别整理了最近公布CVPR2019接受论文，涉及目标检测、跨模态、视频处理、语义分割和姿态估计，欢迎查看！

CVPR 作为计算机视觉领域的顶级学术会议，今年共收到了 5165 篇有效提交论文，比去年 CVPR2018 增加了 56%。不久之前，CVPR 2019 官网放出了最终的论文接收结果。据统计，本届大会共接收了 1300 论文，接收率接近 25.2%。

CVPR 2019 论文

目标检测

Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression

作者：Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese

论文链接：

http://www.zhuanzhi.ai/paper/46c5a1abbe9463bae94409c2ad1acd94

图像分类

Learning a Deep ConvNet for Multi-label Classification with Partial Labels

作者：Thibaut Durand, Nazanin Mehrasa, Greg Mori

论文链接：

http://www.zhuanzhi.ai/paper/fda6443955706ca76ce8c52ce52c8b24

图像处理

  
  
    
   
   
     Iterative Residual CNNs for Burst Photography Applications

Filippos Kokkinos,Stamatios Lefkimmiatis

http://www.zhuanzhi.ai/paper/c72af348e2ee57d74a0d0d3d884b3b92

Data augmentation using learned transforms for one-shot medical image segmentation
Amy Zhao, Guha Balakrishnan, Frédo Durand, John V. Guttag, Adrian V. Dalca
http://www.zhuanzhi.ai/paper/4af88c0816dd2632069cc84f13d177dc
CollaGAN : Collaborative GAN for Missing Image Data Imputation
Dongwook Lee, Junyoung Kim, Won-Jin Moon, Jong Chul Ye
http://www.zhuanzhi.ai/paper/900e58890d8345f90b9cb488a54aa657

视觉语言跨模态处理

Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
Xin Wang,Qiuyuan Huang,Asli Celikyilmaz,Jianfeng Gao,Dinghan Shen,Yuan-Fang Wang,William Yang Wang,Lei Zhang
论文地址：
http://www.zhuanzhi.ai/paper/6d1e314514c8fdbfb7eba783bde57d99

聚类学习

Efficient Parameter-free Clustering Using First Neighbor Relations

M. Saquib Sarfraz, Vivek Sharma, Rainer Stiefelhagen

论文链接：

http://www.zhuanzhi.ai/paper/d87f92bde8eba49b07b3e9594c61e2e9

表示学习

End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization

作者：Yeonwoo Jeong, Yoonsuing Kim, Hyun Oh Song

论文链接：

http://www.zhuanzhi.ai/paper/3f90437f7b5cd850702cd151def52c0d

Text-to-Image

Object-driven Text-to-Image Synthesis via Adversarial Training

作者：Wenbo Li, Pengchuan Zhang, Lei Zhang, Qiuyuan Huang, Xiaodong He, Siwei Lyu, Jianfeng Gao

论文链接：

http://www.zhuanzhi.ai/paper/1761a44c2505c82125d839e612eaac40

人脸检测

Joint Face Detection and Facial Motion Retargeting for Multiple Faces

作者：Bindita Chaudhuri, Noranart Vesdapunt, Baoyuan Wang

论文链接：

http://www.zhuanzhi.ai/paper/11554b44077224153d5f553bf1b003b4

视频处理、分类、描述、分割

Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning
Nayyer Aafaq, Naveed Akhtar, Wei Liu, Syed Zulqarnain Gilani, Ajmal Mian

论文链接：

http://www.zhuanzhi.ai/paper/05ba5dda315f921bf0510cea6fe58e41

Single-frame Regularization for Temporally Stable CNNs

作者：Gabriel Eilertsen, Rafa? K. Mantiuk, Jonas Unger

论文链接：

http://www.zhuanzhi.ai/paper/479a239277f9cb5f7b5dc8605651631f

Efficient Video Classification Using Fewer Frames

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

论文链接：

http://www.zhuanzhi.ai/paper/2c6aa131c90428629cdb4c10be60044d

FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation

作者：Paul Voigtlaender, Yuning Chai, Florian Schroff, Hartwig Adam, Bastian Leibe, Liang-Chieh Chen

论文链接：

http://www.zhuanzhi.ai/paper/b7016fc2c3a303d2c8f1f8001b4875d

弱监督语义分割

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon

论文链接：

http://www.zhuanzhi.ai/paper/07116fa469bea1b90551d7cf4f8f5306

Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
De-An Huang,Suraj Nair,Danfei Xu,Yuke Zhu,Animesh Garg,Li Fei-Fei,Silvio Savarese,Juan Carlos Niebles
地址链接：
http://www.zhuanzhi.ai/paper/22d03c247815526b3b31d7e4b98cbd69

多视几何

Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference

作者：Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan

论文链接：

http://www.zhuanzhi.ai/paper/1b79b35bfd6765ff23f55ea5f0835f9b

代码链接：

https://github.com/YoYo000/MVSNet

3D检测、重建

Stereo R-CNN based 3D Object Detection for Autonomous Driving

作者：Peiliang Li, Xiaozhi Chen, Shaojie Shen

论文链接：

http://www.zhuanzhi.ai/paper/6e707f41e5ed6d33eafc78bdab39034f

Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding
作者：Zehao Yu, Jia Zheng, Dongze Lian, Zihan Zhou, Shenghua Gao
论文链接：
http://www.zhuanzhi.ai/paper/7362035ddd1d69d241cb45fa3a401d85
代码链接：
https://github.com/svip-lab/PlanarReconstruction