Bridging the Gap Between Computational Photography and Visual Recognition


Dissecting the High-Frequency Bias in Convolutional Neural Networks
Antonio A. Abello,
Roberto Hirata,
Zhangyang Wang
[pdf]
[bibtex]
@InProceedings{Abello_2021_CVPR, author = {Abello, Antonio A. and Hirata, Roberto and Wang, Zhangyang}, title = {Dissecting the High-Frequency Bias in Convolutional Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {863-871} }

VRHI: Visibility Restoration for Hazy Images Using a Haze Density Model
Mingye Ju,
Chuheng Chen,
Juping Liu,
Kai Chen,
Dengyin Zhang
[pdf]
[bibtex]
@InProceedings{Ju_2021_CVPR, author = {Ju, Mingye and Chen, Chuheng and Liu, Juping and Chen, Kai and Zhang, Dengyin}, title = {VRHI: Visibility Restoration for Hazy Images Using a Haze Density Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {897-904} }

Delta Sampling R-BERT for Limited Data and Low-Light Action Recognition
Sanchit Hira,
Ritwik Das,
Abhinav Modi,
Daniil Pakhomov
[pdf]
[bibtex]
@InProceedings{Hira_2021_CVPR, author = {Hira, Sanchit and Das, Ritwik and Modi, Abhinav and Pakhomov, Daniil}, title = {Delta Sampling R-BERT for Limited Data and Low-Light Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {853-862} }

Two-Stage Network for Single Image Super-Resolution
Yuzhuo Han,
Xiaobiao Du,
Zhi Yang
[pdf]
[bibtex]
@InProceedings{Han_2021_CVPR, author = {Han, Yuzhuo and Du, Xiaobiao and Yang, Zhi}, title = {Two-Stage Network for Single Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {880-887} }

Expectation-Maximization Attention Cross Residual Network for Single Image Super-Resolution
Xiaobiao Du,
Jie Niu,
Chongjin Liu
[pdf]
[bibtex]
@InProceedings{Du_2021_CVPR, author = {Du, Xiaobiao and Niu, Jie and Liu, Chongjin}, title = {Expectation-Maximization Attention Cross Residual Network for Single Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {888-896} }

DarkLight Networks for Action Recognition in the Dark
Rui Chen,
Jiajun Chen,
Zixi Liang,
Huaien Gao,
Shan Lin
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2021_CVPR, author = {Chen, Rui and Chen, Jiajun and Liang, Zixi and Gao, Huaien and Lin, Shan}, title = {DarkLight Networks for Action Recognition in the Dark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {846-852} }

Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining
Xiang Chen,
Yufeng Huang,
Lei Xu
[pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2021_CVPR, author = {Chen, Xiang and Huang, Yufeng and Xu, Lei}, title = {Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {872-879} }

CE-PeopleSeg: Real-Time People Segmentation With 10% CPU Usage for Video Conference
Ziyu Jiang,
Zhenhua He,
Xueqin Huang,
Zibin Yang,
Pearl Tan
[pdf]
[bibtex]
@InProceedings{Jiang_2021_CVPR, author = {Jiang, Ziyu and He, Zhenhua and Huang, Xueqin and Yang, Zibin and Tan, Pearl}, title = {CE-PeopleSeg: Real-Time People Segmentation With 10% CPU Usage for Video Conference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {914-922} }

E2VTS: Energy-Efficient Video Text Spotting From Unmanned Aerial Vehicles
Zhenyu Hu,
Pengcheng Pi,
Zhenyu Wu,
Yunhe Xue,
Jiayi Shen,
Jianchao Tan,
Xiangru Lian,
Zhangyang Wang,
Ji Liu
[pdf]
[bibtex]
@InProceedings{Hu_2021_CVPR, author = {Hu, Zhenyu and Pi, Pengcheng and Wu, Zhenyu and Xue, Yunhe and Shen, Jiayi and Tan, Jianchao and Lian, Xiangru and Wang, Zhangyang and Liu, Ji}, title = {E2VTS: Energy-Efficient Video Text Spotting From Unmanned Aerial Vehicles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {905-913} }