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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Pre-training without Natural Images

Jan 21, 2021
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

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data

Jan 19, 2021
Nakamasa Inoue, Eisuke Yamagata, Hirokatsu Kataoka

* Accepted to ICPR2020 

  Access Paper or Ask Questions

Alleviating Over-segmentation Errors by Detecting Action Boundaries

Jul 14, 2020
Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki, Hirokatsu Kataoka

* under review 

  Access Paper or Ask Questions

Retrieving and Highlighting Action with Spatiotemporal Reference

May 19, 2020
Seito Kasai, Yuchi Ishikawa, Masaki Hayashi, Yoshimitsu Aoki, Kensho Hara, Hirokatsu Kataoka

* Accepted to ICIP 2020 

  Access Paper or Ask Questions

Weakly Supervised Dataset Collection for Robust Person Detection

May 01, 2020
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?

Apr 10, 2020
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

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation

Feb 29, 2020
Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue


  Access Paper or Ask Questions

What Do Adversarially Robust Models Look At?

May 19, 2019
Takahiro Itazuri, Yoshihiro Fukuhara, Hirokatsu Kataoka, Shigeo Morishima


  Access Paper or Ask Questions

Automatic Paper Summary Generation from Visual and Textual Information

Nov 16, 2018
Shintaro Yamamoto, Yoshihiro Fukuhara, Ryota Suzuki, Shigeo Morishima, Hirokatsu Kataoka

* International Conference on Machine Vision 2018, Munich, Germany 

  Access Paper or Ask Questions

Understanding Fake Faces

Sep 22, 2018
Ryota Natsume, Kazuki Inoue, Yoshihiro Fukuhara, Shintaro Yamamoto, Shigeo Morishima, Hirokatsu Kataoka

* 11 pages, 3 figures, ECCV 2018 Workshop on Brain-Driven Computer Vision (BDCV) 

  Access Paper or Ask Questions

Neural Joking Machine : Humorous image captioning

May 30, 2018
Kota Yoshida, Munetaka Minoguchi, Kenichiro Wani, Akio Nakamura, Hirokatsu Kataoka

* Accepted to CVPR 2018 Language & Vision Workshop 

  Access Paper or Ask Questions

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

Apr 08, 2018
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

Apr 07, 2018
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?

Apr 02, 2018
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

Aug 25, 2017
Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh

* To appear in ICCV 2017 Workshop (Chalearn) 

  Access Paper or Ask Questions

cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey

Jul 20, 2017
Hirokatsu Kataoka, Soma Shirakabe, Yun He, Shunya Ueta, Teppei Suzuki, Kaori Abe, Asako Kanezaki, Shin'ichiro Morita, Toshiyuki Yabe, Yoshihiro Kanehara, Hiroya Yatsuyanagi, Shinya Maruyama, Ryosuke Takasawa, Masataka Fuchida, Yudai Miyashita, Kazushige Okayasu, Yuta Matsuzaki


  Access Paper or Ask Questions

Collaborative Descriptors: Convolutional Maps for Preprocessing

May 10, 2017
Hirokatsu Kataoka, Kaori Abe, Akio Nakamura, Yutaka Satoh

* CVPR 2017 Workshop Submission 

  Access Paper or Ask Questions

Could you guess an interesting movie from the posters?: An evaluation of vision-based features on movie poster database

Apr 07, 2017
Yuta Matsuzaki, Kazushige Okayasu, Takaaki Imanari, Naomichi Kobayashi, Yoshihiro Kanehara, Ryousuke Takasawa, Akio Nakamura, Hirokatsu Kataoka

* 4 pages, 4 figures 

  Access Paper or Ask Questions

Changing Fashion Cultures

Mar 23, 2017
Kaori Abe, Teppei Suzuki, Shunya Ueta, Akio Nakamura, Yutaka Satoh, Hirokatsu Kataoka

* 9 pages, 9 figures 

  Access Paper or Ask Questions

Semantic Change Detection with Hypermaps

Mar 16, 2017
Teppei Suzuki, Soma Shirakabe, Yudai Miyashita, Akio Nakamura, Yutaka Satoh, Hirokatsu Kataoka


  Access Paper or Ask Questions

Motion Representation with Acceleration Images

Aug 30, 2016
Hirokatsu Kataoka, Yun He, Soma Shirakabe, Yutaka Satoh


  Access Paper or Ask Questions

Human Action Recognition without Human

Aug 29, 2016
Yun He, Soma Shirakabe, Yutaka Satoh, Hirokatsu Kataoka


  Access Paper or Ask Questions

cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey

May 26, 2016
Hirokatsu Kataoka, Yudai Miyashita, Tomoaki Yamabe, Soma Shirakabe, Shin'ichi Sato, Hironori Hoshino, Ryo Kato, Kaori Abe, Takaaki Imanari, Naomichi Kobayashi, Shinichiro Morita, Akio Nakamura

* Survey Paper 

  Access Paper or Ask Questions

Dominant Codewords Selection with Topic Model for Action Recognition

May 01, 2016
Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, Yoshimitsu Aoki, Slobodan Ilic

* in CVPRW16 

  Access Paper or Ask Questions

Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection

Sep 25, 2015
Hirokatsu Kataoka, Kenji Iwata, Yutaka Satoh

* 5 pages, 3 figures 

  Access Paper or Ask Questions