Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Describing and Localizing Multiple Changes with Transformers



Yue Qiu , Shintaro Yamamoto , Kodai Nakashima , Ryota Suzuki , Kenji Iwata , Hirokatsu Kataoka , Yutaka Satoh

* 18 pages, 15 figures, project page: https://cvpaperchallenge.github.io/Describing-and-Localizing-Multiple-Change-with-Transformers/ 

   Access Paper or Ask Questions

Pre-training without Natural Images



Hirokatsu Kataoka , Kazushige Okayasu , Asato Matsumoto , Eisuke Yamagata , Ryosuke Yamada , Nakamasa Inoue , Akio Nakamura , Yutaka Satoh

* ACCV 2020 Best Paper Honorable Mention Award, Codes are publicly available: https://github.com/hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch 

   Access Paper or Ask Questions

Weakly Supervised Dataset Collection for Robust Person Detection



Munetaka Minoguchi , Ken Okayama , Yutaka Satoh , Hirokatsu Kataoka

* Project page: https://github.com/cvpaperchallenge/FashionCultureDataBase_DLoader The paper is under consideration at Pattern Recognition Letters 

   Access Paper or Ask Questions

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?



Hirokatsu Kataoka , Tenga Wakamiya , Kensho Hara , Yutaka Satoh

* Codes and pre-trained models are publicly available: https://github.com/kenshohara/3D-ResNets-PyTorch 

   Access Paper or Ask Questions

Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB



Tomoyuki Suzuki , Hirokatsu Kataoka , Yoshimitsu Aoki , Yutaka Satoh

* Accepted to CVPR 2018 

   Access Paper or Ask Questions

Drive Video Analysis for the Detection of Traffic Near-Miss Incidents



Hirokatsu Kataoka , Teppei Suzuki , Shoko Oikawa , Yasuhiro Matsui , Yutaka Satoh

* Accepted to ICRA 2018 

   Access Paper or Ask Questions

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?



Kensho Hara , Hirokatsu Kataoka , Yutaka Satoh

* Accepted to CVPR 2018 

   Access Paper or Ask Questions

Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition



Kensho Hara , Hirokatsu Kataoka , Yutaka Satoh

* To appear in ICCV 2017 Workshop (Chalearn) 

   Access Paper or Ask Questions

Collaborative Descriptors: Convolutional Maps for Preprocessing



Hirokatsu Kataoka , Kaori Abe , Akio Nakamura , Yutaka Satoh

* CVPR 2017 Workshop Submission 

   Access Paper or Ask Questions

1
2
>>