片岡 裕雄(かたおか ひろかつ)
国立研究開発法人 産業技術総合研究所 人工知能研究センター 研究員
東京電機大学 訪問研究員
cvpaper.challenge 主宰
博士(工学),2014年 慶應義塾大学

お仕事のご依頼・研究連携はこちら


What's new?
2021.2.5: 我々の研究「自然画像を用いない事前学習」がMIT Technology Reviewに取り上げられました.
2020.11.30: ACCV 2020 Best Paper Honorable Mention Awardを獲得しました!
2020.11.2: 新規視点画像生成の論文がWACV 2021に採択されました.
2020.10.11: 2本の論文(Cycle Consistency, Generator Compression)ICPR 2020に採択されました.
2020.10.2: 仮想試着の論文がSensors Journal (IF: 3.27)に採択されました.
2020.9.17: 数式ベース自動DB構築の論文が ACCV 2020にオーラル発表として採択されました.
2020.8.20: 変化キャプショニングの研究がSensors Journal (IF: 3.27)に採択されました.
2020.8.7: 行動セグメンテーションの論文WACV 2021に採択されました.
2020.7.15: 行動セグメンテーションの論文をarXivに掲載しました.
2020.7.3: 3Dベースの変化キャプショニングに関する論文がIROS 2020に採択されました.
2020.6.22: パーリンノイズによる初期化,生成モデルのDisentanglementの論文がICPR 2020に採択されました.
2020.6.4: 3Dベースの変化キャプショニングに関する論文がRA Lettersに採択されました.
2020.5.16: 動画認識結果の可視化に関する論文がICIP 2020に採択されました.
2020.5.8: 論文がITSC 2020に採択されました.
2020.4.14: Multi-view VQAの論文がSensors Journal (IF: 3.03)に採択されました.
2020.4.13: 3本のarXiv論文を公開しました (3D ResNet, Person Detection, Cycle Consistency).
2020.3.31: 3D ResNetの論文が産総研論文賞を獲得しました
2020.1.22: 論文がICRA 2020に採択されました
2019.12.6: ViEW2019にて若手奨励賞を受賞しました
2019.11.26: 論文がHCIi 2020に採択されました
2019.11.7: SSII2019で発表したVAIRが優秀学術賞を受賞しました
2019.7.20: 論文が3DV 2019に採択されました
2019.4.14: 2本の論文がCVPR 2019 Workshop on WiCVVQA and Dialogに採択されました



Professional Experiences
Researcher, National Institute of Advanced Industrial Science and Technology (AIST) (April 2016 - Present)
国立研究開発法人 産業技術総合研究所 研究員 (2016年4月 - 現在)

Visiting Researcher, OMRON SINIC X Corporation (May 2018 - March 2020)
オムロン サイニックエックス株式会社 訪問研究員 (2018年5月 - 2020年3月)

Postdoctoral Fellow, National Institute of Advanced Industrial Science and Technology (AIST) (April 2015 - March 2016)
国立研究開発法人 産業技術総合研究所 産総研特別研究員 (2015年4月 - 2016年3月)

JSPS Research Fellow (PD), The University of Tokyo (April 2014 - March 2015)
東京大学 学振特別研究員(PD)(2014年4月 - 2015年3月)

Visiting Scientist, Technical University of Munich (TUM) (July 2013 - September 2013, September 2014 - November 2014)
ミュンヘン工科大学 訪問研究員 (2013年7月 - 2013年9月, 2014年9月 - 2014年11月)

JSPS Research Fellow (DC2), Keio University (April 2013 - March 2014)
慶應義塾大学 学振特別研究員(DC2)(2013年4月 - 2014年3月)


Education
Ph.D. in Engineering, Keio University (April 2011 - March 2014)
Adviser: Prof. Yoshimitsu Aoki
慶應義塾大学大学院 理工学研究科 博士(工学) 指導教員:青木義満准教授

M.E. Keio University (April 2009 - March 2011)
Adviser: Prof. Yoshimitsu Aoki
慶應義塾大学大学院 理工学研究科 修士課程 指導教員:青木義満准教授

B.E. Shibaura Institute of Technology (April 2005 - March 2009)
芝浦工業大学 工学部 学士課程 指導教員:大関和夫教授

Midorioka High School (April 2002 - March 2005)
茨城県立緑岡高校 普通科


Selected Projects

cvpaper.challenge
[Webpage] [Twitter] [SlideShare] [PDF1] [PDF2]
Hirokatsu Kataoka (AIST) et al.
Top Conferences
年間1,000本以上の論文を読破しまとめ資料を作成,洗練された問題設定を実装実験し,年間約20本以上トップ会議に投稿しています!
cvpaper.challengeは論文読破・論文まとめ・アイディア発想・議論・実装・実験・論文執筆(・社会実装)に取り組むことでコンピュータビジョンの今を映し,トレンドを創り出す挑戦です.2015年5月のスタート以来,現在までに2回のCVPR完全読破(CVPR 2015/CVPR 2018)を含めて3,000本以上の論文サマリを作成し,Top-tier国際会議(各分野の1位およびそれに準ずる国際会議)のCVPR/ICRAを始め,3年間で17本のGスカラTop-20論文に採択される研究コミュニティに成長しました.より詳細にはTwitter, SlideShareWeb等のページをご覧ください.論文読破/論文執筆を一緒に行う仲間や講演依頼など受け付けているのでチャレンジのメンバーまでお問い合わせください.

Weakly Supervised Person Dataset (WSPD)
[PDF] [GitHub]
Munetaka Minoguchi, Ken Okayama, Yutaka Satoh, Hirokatsu Kataoka (AIST)
arXiv pre-print, ViEW 2019 (論文奨励賞)
教師あり事前学習を凌駕する「弱」教師あり事前学習
ロバストな人物検出器を構築するために,我々は弱教師により800万の人物bboxを含むデータセットWSPDを構築しました.高品質な教師ラベルを含む大規模画像データセットを学習に用いた場合,成功がほぼ確約されていると言っても差し支えないですが,ラベル付けのコストを膨大に要します.本研究では,SNSからの画像データ収集や弱教師によるラベル付けを含め,人間による手間を最小限にしつつ大規模データセットを構築する方法を紹介しております.800万超の人物bboxを含む大規模データセットを人物検出のための事前学習に用いた場合,ベースラインである教師ありの事前学習手法を凌駕する検出率を実現(ImageNetによるベースラインと比較した場合,+13.36%を達成)しました.

Neural Joking Machine: Humorous image captioning
[PDF] [Oral] [Poster]
Kota Yoshida (TDU), Munetaka Minoguchi (TDU/AIST), Kenichiro Wani, Akio Nakamura (TDU), Hirokatsu Kataoka (AIST)
CVPR 2018 WS
ボケをかますAI
「コンピュータビジョンにより人間をいかに笑わせるか」この問いを熟慮し,笑いを引き出すための研究を行っています.私たちのシステムでは笑えるキャプションを生成するため,コンピュータビジョンのみならず自然言語処理とのクロスフィールドにおいて研究を行います.現在までに,効果的に生成したボケを評価するためのFunny Scoreを提案してボケの最適化を行って参りました.さらに,27万+画像,500+万キャプションを含むBoketeDBを構築し,日々面白さを追求しています.BoketeDBはお題(画像)とボケ(キャプション)がペアとなり,コンピュータに対して学習しやすい構成となっております.実験では日本語の画像説明文STAIR Caption DBにより学習したキャプションや人間による高スコアのボケと比較し「人間よりは面白くないが画像説明文よりは面白い」ことを明らかにしました.Neural Joking Machineはこれからもさらに面白くなることを目指し,笑いの修行を行っております.

Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
[PDF (ICRA 2018)] [PDF (CVPR 2018)] [PDF (Sensors)] [PDF (ICRA 2020)]
Hirokatsu Kataoka (AIST), Tomoyuki Suzuki, Teppei Suzuki (Keio/AIST), Yoshimitsu Aoki (Keio), Kodai Nakashima, Yutaka Satoh (AIST), Shoko Oikawa, Yasuhiro Matsui (NTSEL)
ICRA 2018, CVPR 2018, Sensors Journal (IF:2.78), ICRA 2020
交通に関する危険動画を収録した大規模データベース!
ADASや自動運転の安全性向上のため、衝突事故に直結する危険状態(ニアミス)の解析は極めて重要ですが、先端的なデータベース(e.g. KITTI, CityScapes)においても危険なシーンが含まれていないのが現状です。本研究では、交通予防システムのさらなる安全性向上のため大規模なニアミスデータベースを構築し、さらには同データにおいて危険度(低・高レベル)やニアミス要因(歩行者・自転車・自動車)を同時に判別可能な動画解析手法を新規に提案します。ニアミス検出の精度を向上させるために、交通シーンに着目した改良 -同DBを使用した追加学習および前景/背景の分離と統合- をモーション表現に取り入れています。データ収集、モデルの改良により、ヒューマンレベルのニアミス理解に接近する精度を出すことに成功しました(64.5% vs. 68.4% @6クラスのニアミス認識、61.3% vs. 78.7% @背景も含めた7クラスのニアミス検出)。

Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
[PDF] [GitHub (2,000+ stars!)]
Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh (AIST)
CVPR 2018, AIST Best Paper
時系列の3DCNNはImageNetの歴史を辿るのか?
2017年現在の動画認識用データベースがより深い構造の時系列3D-CNNに汎化するかを検証する目的で研究を行いました.最近の人物行動認識をはじめとした動画認識の精度は著しく向上しましたが,一方で動画認識用の3Dカーネルを用いたCNNは比較的浅い構造でした.3Dカーネルを用いた3D-ResNetの構造を深化させる実験では(驚くべきことに)ImageNetと2D-CNNの組み合わせと類似した精度向上になることを確認しました(左図).従って,ImageNetやディープラーニングの提案後,画像認識の性能が劇的に向上したように,今後はより高性能かつ多目的な動画認識が実現するのではないかと期待されます.

Dynamic Fashion Cultures
[PDF] [Poster] [Presen] [GitHub]
Kaori Abe (TDU/AIST), Teppei Suzuki (Keio/AIST), Shunya Ueta (Tsukuba/AIST), Akio Nakamura (TDU), Yutaka Satoh, Hirokatsu Kataoka (AIST)
arXiv Pre-print, MIRU 2017 (Oral: 28.0%, Best Student Paper)
世界的なファッション解析のデータは整った!?
SNSから収集したGPS情報付きの画像データを用いて,世界的なファッション画像解析を行いました.我々が構築したFashion Culture Database (FCDB)には76,000,000枚以上の画像が16都市にわたり収集されています.特徴累積により都市間の類似度が,量子化ベクトルの時系列差分により様々なファッションスタイルの変化を可視化しております.現在,データベースの公開に向け,FCDB_v2を作成中です.

Human Action Recognition without Human
[PDF] [Slide] [Poster]
Yun He, Soma Shirakabe (Tsukuba/AIST), Yutaka Satoh, Hirokatsu Kataoka (AIST)
ECCV 2016 Workshop (Oral, Brave New Idea), MIRU 2017 (Oral: 28.0%)
人物行動は人物を見なくても認識されてしまう!
本研究の目的は"Human Action Recognition without Human(人を見ない人物行動認識)"を実施することです.人物行動認識においてモーションを捉えることは非常に重要であり,改善案が常に議論されてきました.しかし,動画像の構成は人物領域に対して背景領域の面積が広く,我々は背景領域に含まれるコンテキスト情報が非常に強く働いているのではないかと考えました.そこで,人物行動データにおいて人物を見ないで人物行動認識を行なったところ,50%以上の確率で100カテゴリ以上を見分けられることを明らかにしました.人物行動認識の問題が背景認識の問題に置き換わっていると言えます.左図の例ではTennisSwingを認識するために人物を全く見ず,TennisCourtというコンテキストのみで行動認識を行なっています.



Publications
(#) indicates top-ranked conference/journal in Google Scholar Metrics.
----2021----
- (#) Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki, Hirokatsu Kataoka, "Alleviating Over-segmentation Errors by Detecting Action Boundaries," Winter Conference on Applications of Computer Vision (WACV), 2021. (arXiv pre-print:2007.06866) [Project] [PDF] [GitHub]
- (#) Hiroaki Aizawa, Hirokatsu Kataoka, Yutaka Satoh, Kunihito Kato, "Viewpoint-agnostic Image Rendering," Winter Conference on Applications of Computer Vision (WACV), 2021. [Project]

----2020----
- (#) Hideki Tsunashima, Kosuke Arase, Antony Lam, Hirokatsu Kataoka, "UVIRT—Unsupervised Virtual Try-on Using Disentangled Clothing and Person Features" Sensors, 2020.[PDF] (Impact Factor: 3.27)
- (#) Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh, “Pre-training without Natural Images”, Asian Conference on Computer Vision (ACCV), 2020. (Best Paper Honorable Mention Award; Oral Presentation; 3 Strong Accepts)
- (#) Yue Qiu, Yutaka Satoh, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka, "Indoor Scene Change Captioning based on Multi-modality Data", Sensors, 2020. [PDF] (Impact Factor: 3.27)
- (#) Yue Qiu, Yutaka Satoh, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka, "3D-Aware Scene Change Captioning from Multiview Images," IEEE Robotics and Automation Letters (RA-L) with IROS presentation, 2020.
- (#) Nakamasa Inoue*, Eisuke Yamagata*, Hirokatsu Kataoka, "Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data," International Conference on Pattern Recognition (ICPR), 2020. (* indicates equal contribution) [PDF]
- (#) Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue, “Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation”, International Conference on Pattern Recognition (ICPR), 2020. (arXiv pre-print:2003.00187) [PDF]
- (#) Hideki Tsunashima, Shigeo Morishima, Junji Yamato, Qiu Chen, Hirokatsu Kataoka, “Adversarial Knowledge Distillation for a Compact Generator”, International Conference on Pattern Recognition (ICPR), 2020.
- (#) Hiroaki Aizawa, Hirokatsu Kataoka, Yutaka Satoh, Kunihito Kato, "Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and Location," International Conference on Pattern Recognition (ICPR), 2020. [Project]
- (#) Seito Kasai, Yuchi Ishikawa, Masaki Hayashi, Yoshimitsu Aoki, Kensho Hara, Hirokatsu Kataoka, "Retrieving and Highlighting Action with Spatiotemporal Reference," IEEE International Conference on Image Processing (ICIP), 2020. [PDF]
- (#) Kensho Hara, Hirokatsu Kataoka, Masaki Inaba, Kenichi Narioka, Ryusuke Hotta, Yutaka Satoh, "Predicting Vehicles Appearing from Blind Spots Based on Pedestrian Behaviors", IEEE Intelligent Transportation Systems Conference (ITSC), 2020.
- (#) Yue Qiu, Yutaka Satoh, Ryota Suzuki, Kenji Iwata, Hirokatsu Kataoka, "Multi-view Visual Question Answering with Active Viewpoint Selection", Sensors, 2020. [PDF] (Impact Factor: 3.03)
- Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara, Yutaka Satoh, "Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?", arXiv pre-print:2004.04968, 2020. [PDF] [GitHub]
- Munetaka Minoguchi, Ken Okayama, Yutaka Satoh, Hirokatsu Kataoka, "Weakly Supervised Dataset Collection for Robust Person Detection", arXiv pre-print:2003.12263, 2020. [PDF] [GitHub]
- (#) Hirokatsu Kataoka, Teppei Suzuki, Kodai Nakashima, Yutaka Satoh, Yoshimitsu Aoki, "Joint Pedestrian Detection and Risk-level Prediction with Motion-Representation-by-Detection", International Conference on Robotics and Automation (ICRA), 2020. [PDF] (Acceptance rate: 42.0%; 1st place in Robotics at Google Scholar Metrics)
- (#) Ryota Suzuki, Kota Yoshida, Munetaka Minoguchi, Kazuki Tsubura, Takumu Ikeya, Akio Nakamura, Hirokatsu Kataoka, "Joking AI via Visual Cues", Human Computer Interaction International 2020.

----2019----
- (#) Yue Qiu, Yutaka Satoh, Ryota Suzuki, Hirokatsu Kataoka, "Incorporating 3D Information into Visual Question Answering", International Conference on 3D Vision (3DV), 2019.
- Takahiro Itazuri, Yoshihiro Fukuhara, Hirokatsu Kataoka, Shigeo Morishima, "What Do Adversarially Robust Models Look At?", arXiv pre-print:1905.07666, 2019.[PDF]
- (#) Yue Qiu, Yutaka Satoh, Hirokatsu Kataoka, Ryota Suzuki, "Incorporating Depth into Visual Question Answering", CVPR 2019 Workshop on Visual Question Answering and Dialog, 2019.
- (#) Yue Qiu, Yutaka Satoh, Hirokatsu Kataoka, Ryota Suzuki, "Visual Question Answering with RGB-D Images", CVPR 2019 Workshop on Women in Computer Vision (WiCV), 2019.
- (#) Hirokatsu Kataoka, Kaori Abe, Munetaka Minoguchi, Akio Nakamura, Yutaka Satoh, "Ten-million-order Human Database for World-wide Fashion Culture Analysis", CVPR 2019 Workshop on Understanding Subjective Attributes of Data, Focus on Fashion and Subjective Search (FFSS-USAD). (Oral) [PDF] [Oral] [Poster] [GitHub]
- (#) Hirokatsu Kataoka, Yutaka Satoh, "Unsupervised Out-of-context Action Understanding", IEEE International Conference on Robotics and Automation (ICRA), 2019. (Acceptance rate: 44.0%; 1st place in Robotics at Google Scholar Metrics)

----2018----
- Naofumi Akimoto, Hirokatsu Kataoka, Yoshimitsu Aoki, "Generating Effect Animation with Conditional GANs", SIGGRAPH Asia 2018 Posters, 2018. [Video]
- Shintaro Yamamoto, Yoshihiro Fukuhara, Ryota Suzuki, Shigeo Morishima, Hirokatsu Kataoka, "Automatic Paper Summary Generation from Visual and Textual Information", International Conference on Machine Vision (ICMV) 2018
- Kaori Abe, Munetaka Minoguchi, Teppei Suzuki, Tomoyuki Suzuki, Naofumi Akimoto, Yue Qiu, Ryota Suzuki, Kenji Iwata, Yutaka Satoh, Hirokatsu Kataoka, "Fashion Culture Database: Construction of Database for World-wide Fashion Analysis", IEEE ICARCV 2018. [PDF]
- Tomoyuki Suzuki, Munetaka Minoguchi, Ryota Suzuki, Akio Nakamura, Kenji Iwata, Yutaka Satoh, Hirokatsu Kataoka, "Semantic Change Detection", IEEE ICARCV 2018. [PDF]
- Tomoyuki Suzuki, Takahiro Itazuri, Kensho Hara, Hirokatsu Kataoka, "Learning Spatiotemporal 3D Convolution with Video Order Self-Supervision", ECCV 2018 Workshop on Person in Context (PIC).
- Ryota Natsume*, Kazuki Inoue*, Shintaro Yamamoto, Yoshihiro Fukuhara, Shigeo Morishima, Hirokatsu Kataoka, "Understanding Fake-Faces", ECCV 2018 Workshop on Brain-Driven Computer Vision (BDCV), 2018. [PDF]
- (#) Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh, "Towards Good Practice for Action Recognition with Spatiotemporal 3D Convolutions", International Conference on Pattern Recognition (ICPR), 2018. [PDF]
- (#) Hirokatsu Kataoka Shuhei Ohki, Kenji Iwata, Yutaka Satoh, "Occlusion Handling Human Detection with Refocused Images", International Conference on Pattern Recognition (ICPR), 2018. [PDF]
- Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh, "AIST Submission to ActivityNet Challenge 2018", ActivityNet Large Scale Activity Recognition Challenge in Conjunction with CVPR 2018. [PDF]
- Tenga Wakamiya, Takumu Ikeya, Akio Nakamura, Kensho Hara, Hirokatsu Kataoka, "TDU&AIST Submission for ActivityNet Challenge 2018 in Video Caption Task", ActivityNet Large Scale Activity Recognition Challenge in Conjunction with CVPR 2018. [PDF]
- (#) Yue Qiu, Fangge Chen, Shuhei Oki, Hirokatsu Kataoka, “Image generation associated with music data”, CVPR 2018 Workshop on Sight and Sound (WSS). [PDF]
- (#) Kota Yoshida, Munetaka Minoguchi, Kenichiro Wani, Akio Nakamura, Hirokatsu Kataoka, "Neural Joking Machine: An image captioning for a humor", CVPR 2018 Language and Vision Workshop. [PDF] [Oral] [Poster]
- (#) Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh, "Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?", IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [PDF] [Poster] [GitHub] (Acceptance rate: 29.6%; 1st place in Computer Vision at Google Scholar Metrics)
- (#) Tomoyuki Suzuki*, Hirokatsu Kataoka*, Yoshimitsu Aoki, Yutaka Satoh, "Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB", IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [PDF] [Poster] (Acceptance rate: 29.6%; 1st place in Computer Vision at Google Scholar Metrics; * indicates equal contribution)
- (#) Hirokatsu Kataoka, Yutaka Satoh, Yoshimitsu Aoki, Shoko Oikawa, Yasuhiro Matsui, "Temporal and Fine-grained Pedestrian Action Recognition on Driving Recorder Database", Sensors, 2018. [PDF] (Impact Factor: 2.67)
- (#) Hirokatsu Kataoka, Teppei Suzuki, Shoko Oikawa, Yasuhiro Matsui, Yutaka Satoh, "Drive Video Analysis for the Detection of Traffic Near-Miss Incidents", IEEE International Conference on Robotics and Automation (ICRA), May 2018. [PDF] [Poster] [Digest] (Acceptance rate: 40.6%; 1st place in Robotics at Google Scholar Metrics)

----2017----
- (#) Fangge Chen, Hirokatsu Kataoka, Yutaka Satoh, "Text Detection in Traffic Informatory Signs Using Synthetic Data", International Conference on Document Analysis and Recognition (ICDAR 2017), Nov. 2017.
- (#) Kensho Hara, Hirokatsu Kataoka, Yutaka Satoh, "Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition", ICCV 2017 Workshop on ChaLearn Looking at People, Oct. 2017. [PDF] [GitHub]
- Kaori Abe*, Teppei Suzuki*, Shunya Ueta, Akio Nakamura, Yutaka Satoh, Hirokatsu Kataoka, "Dynamic Fashion Cultures", arXiv pre-print:1703.07920, 2017. (* indicates equal contribution) [PDF] [Poster] [Presen] (Acceptance rate (oral): 28.0%, Best Student Award)
- Kensho Hara, Hirokatsu Kataoka, Yusuke Goutsu, Yutaka Satoh, Ryozo Yamashita, "NIAD Submission to ActivityNet Challenge 2017", ActivityNet Large Scale Activity Recognition Challenge, in conjuction with CVPR, Jul. 2017. [PDF] [Result]
- 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, "cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey", arXiv pre-print, 1707.06436, Jul. 2017. [PDF] [PDF2]
- (#) Yuta Matsuzaki, Kazushige Okayasu, Akio Nakamura, Hirokatsu Kataoka, "Generated Motion Maps", CVPR 2017 Workshop on Brave New Ideas for Motion Representations in Videos (BNMW), Jul. 2017. [PDF]
- (#) Yue Qiu, Yutaka Satoh, Ryota Suzuki, Hirokatsu Kataoka, "Sensing and recognition of typical indoor family scenes using an RGB-D camera", CVPR 2017 Workshop, WiCV, Jul. 2017.
- (#) Kaori Abe, Hirokatsu Kataoka, Akio Nakamura, "Weighted Feature Integration for Person Re-identification", CVPR 2017 Workshop, WiCV, Jul. 2017.
- Hirokatsu Kataoka, Kaori Abe, Akio Nakamura, Yutaka Satoh, "Collaborative Descriptors: Convolutional Maps for Preprocessing", arXiv pre-print:1705.03595, May 2017. [PDF]
- Yuta Matsuzaki*, Kazushige Okayasu*, Takaaki Imanari, Naomichi Kobayashi, Yoshihiro Kanehara, Ryousuke Takasawa, Akio Nakamura, Hirokatsu Kataoka, "Could you guess an interesting movie from the posters?: An evaluation of vision-based features on movie poster database", IAPR Conference on Machine Vision Applications (MVA2017), May 2017. (* equal contribution) [PDF] [Poster]
- Teppei Suzuki, Yoshimitsu Aoki, Hirokatsu Kataoka, "Pedestrian Near-Miss Analysis on Vehicle-Mounted Driving Recorders", IAPR Conference on Machine Vision Applications (MVA2017), May 2017.
- Yudai Miyashita, Hirokatsu Kataoka, Akio Nakamura, "Analyzing Fine Motion Considering Individual Habits for Appearance-based Proficiency Evaluation", IEICE Transactions on Information and Systems, vol.E100-D, no.1, Jan. 2017. [PDF]

----2016----
- Yun He, Soma Shirakabe, Yutaka Satoh, Hirokatsu Kataoka, "Human Action Recognition without Human", ECCV 2016 Workshop on Brave New Ideas for Motion Representations in Videos (BNMW), Oct. 2016. (Oral, Best Paper) [PDF] [Slide] [Poster]
- Hirokatsu Kataoka, Yun He, Soma Shirakabe, Yutaka Satoh, "Motion Representation with Acceleration Images", ECCV 2016 Workshop on Brave New Ideas for Motion Representations in Videos (BNMW), Oct. 2016. [PDF] [Poster]
- (#) Hirokatsu Kataoka, Yudai Miyashita, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, "Recognition of Transitional Action for Short-Term Action Prediction using Discriminative Temporal CNN Feature", British Machine Vision Conference (BMVC), Sep. 2016. (Acceptance rate: 39.4%) [PDF] [Abstract] [Poster] [Slide] [Video]
- 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, "cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey", arXiv pre-print 1605.08247, May. 2016. [PDF]
- (#) Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, Yoshimitsu Aoki, Slobodan Ilic, "Dominant Codewords Selection with Topic Model for Action Recognition", IEEE CVPR 2016 Workshop on ChaLearn Looking at People, Jul. 2016. [PDF] [Slide]
- Hirokatsu Kataoka, Soma Shirakabe, Yudai Miyashita, Akio Nakamura, Kenji Iwata, Yutaka Satoh, "Semantic Change Detection with Hypermaps", arXiv pre-print arXiv:1604.07513, Apr. 2016. [PDF]
- Hirokatsu Kataoka, Yoshimitsu Aoki, Kenji Iwata, Yutaka Satoh, "Activity Prediction Using a Space-Time CNN and Bayesian Framework", 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Feb. 2016. [PDF] [Slide]

----2015----
- 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, "cvpaper.challenge in CVPR2015 - A review of CVPR2015", Special Talk at Pattern Recognition and Media Understanding (PRMU), Dec. 2015. [PDF] [Slide]
- Hirokatsu Kataoka, Kenji Iwata, Yoshimitsu Aoki, Yutaka Satoh, "Evaluation of Vision-based Human Activity Recognition in Dense Trajectory Framework", 11th International Symposium on Visual Computing (ISVC), Dec. 2015. [PDF] [Slide]
- Tomoaki Yamabe, Yudai Miyashita, Shin'ichi Sato, Yudai Yamamoto, Akio Nakamura, Hirokatsu Kataoka, "What is an Effective Feature for a Detection Problem? -Feature Evaluation in Multiple Scenes-", IEEE International Conference on Systems, Man, and Cybernetics (SMC), Oct. 2015.
- Hirokatsu Kataoka, Kenji Iwata, Yutaka Satoh, "Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection", arXiv preprint arXiv:1509.07627, Sep. 2015. [PDF] [Slide]
- (#) Hirokatsu Kataoka, Yoshimitsu Aoki, Yutaka Satoh, Shoko Oikawa, Yasuhiro Matsui, "Fine-grained Walking Activity Recognition via Driving Recorder Dataset", IEEE Intelligent Transportation Systems Conference (ITSC), Sep. 2015. [PDF] [Slide]
- Yudai Miyashita, Hirokatsu Kataoka, Akio Nakamura, "Appearance-based Proficiency Evaluation of Micro-operation Skill in Removing Individual Habit", Chinese Control Conference and SICE annual Conference (CCC&SICE), Jul. 2015.
- (#) Masamichi Shimosaka, Nishi Kentaro, Junichi Sato, Hirokatsu Kataoka, "Predicting Driving Behavior Using Inverse Reinforcement Learning with Multiple Reward Functions towards Environmental Diversity", IEEE Intelligent Vehicles Symposium (IV), May 2015. (Acceptance rate (oral): 6.6%) [PDF]
- Tomoaki Yamabe, Hirokatsu Kataoka, Akio Nakamura, "Quantized Feature with Angular Displacement for Activity Recognition", IEEJ Trans. information and systems, Vol.135, No.4, pp.372-380, Apr. 2015. [PDF]
- Junji Kurano, Masaki Hayashi, Taiki Yamamoto, Hirokatsu Kataoka, Masamoto Tanabiki, Junko Furuyama, Yoshimitsu Aoki, "Ball Trajectory Extraction in Team Sports Videos by Focusing on Ball Holder Candidates for a Play Search and 3D Virtual Display System", Journal of Signal Processing, Vol.19, No.4, pp.147-150, 2015. [Link]

----2014----
- (#) Hirokatsu Kataoka, Kiyoshi Hashimoto, Kenji Iwata, Yutaka Satoh, Nassir Navab, Slobodan Ilic, Yoshimitsu Aoki, "Extended Co-occurrence HOG with Dense Trajectories for Fine-grained Activity Recognition", Asian Conference on Computer Vision (ACCV), Nov. 2014. (Acceptance rate: 27.8%) [PDF] [Slide]
- Hirokatsu Kataoka, Kiyoshi Hashimoto, Yoshimitsu Aoki, "Feature Integration with Random Forests for Real-time Human Activity Recognition", International Conference on Machine Vision (ICMV), Nov. 2014. (Acceptance rate: 40.0%) [PDF]
- Hirokatsu Kataoka, Yoshimitsu Aoki, "An Analysis of Edge Orientation and Magnitude in Co-occurrence Feature Descriptor", SICE Annual Conference, Sep. 2014. [PDF]
- Tomoaki Yamabe, Hirokatsu Kataoka, Akio Nakamura, "A Study on Features for Early Recognition of Human Activities", SICE Annual Conference, Sep. 2014.
- Hirokatsu Kataoka, Kimimasa Tamura, Kenji Iwata, Yutaka Satoh, Yasuhiro Matsui, Yoshimitsu Aoki, "Extended Feature Descriptor and Vehicle Motion Model with Tracking-by-detection for Pedestrian Active Safety", IEICE Transactions on Information and Systems, Vol.E97-D, No.2, 2014. [PDF]
- Junji Kurano, Taiki Yamamoto, Hirokatsu Kataoka, Masaki Hayashi, Yoshimitsu Aoki, "Ball Tracking in Team Sports by Focusing on Ball Holder Candidates", International Workshop on Advanced Imate Technology (IWAIT2014), Jan. 2014.

Please see My Google Scholar/Full List for other publications.


Awards
- ACCV 2020 Best Paper Honorable Mention Award.
- AIST Best Paper Award, Mar. 2020.
- YANS Award, YANS2018, Aug. 2018.
- Best Student Award, MIRU2017, Aug. 2017.
- Fujiwara Award, Fuculty of Science and Technology at Keio University, Mar. 2014.
- IEEJ Best Journal Award 2012, IEEJ Transactions on Electrical and Electronic Engineering, Sep. 2013.
- IEEE IECON2012 Best Presentation Award, IEEE IECON2012, Oct. 2012.
- Global COE Excellent Achievement Award, GCOE Symposium, Feb. 2012.
- Odawara Award, ViEW2011, Dec. 2011.
- Graduate School Award of Society of Automotive Engineers of Japan, Mar. 2011.
- Best Master Course Student Award of School of Integrated Design Engineering in Master Course, Mar. 2011.
- Best Paper Award of SICE pattern analysis symposium, Dec. 2010.
- Encouragement Award of Dynamic Image Processing for Real Application Workshop 2010 (DIA2010), Mar. 2010.
- Best Presentation Award of School of Integrated Design Engineering Award, Feb. 2010.
- Best Presentation Award of Summer Seninar 2009, Aug. 2009.


Invited Talks
- STAIR Lab., May 2018. [Slide]
- OITDA, Apr. 2018. [Slide]
- Waseda University, Apr. 2018. [Slide]
- A Company, Jan. 2018.
- Nagoya CV/PRML, Dec. 2017. [Slide]
- teamLab, Dec. 2017. [Slide]
- Tokyo Denki University, Nov. 2017. [Slide]
- Abeja Innovation Meetup, Sep. 2017. [Slide]
- Waseda University, Sep. 2017. [Slide]
- Chukyo University, Feb. 2017. [Slide]
- Keio University, Jan. 2017.
- STAIR Lab., Jan. 2017. [Slide]
- The University of Tokyo, Sep. 2016. [Slide]
- IAIP, Jul. 2016. [Slide]
- Pattern Recognition and Media Understanding (PRMU), Dec. 2015. [Slide]
- SSII2015, Jun. 2015. [Slide]
- Max Planck Institute for Infomatics (MPII), Oct. 2014. [Slide]
- The University of Tokyo, Jun. 2012.


Most-viewed Slides
- CVPR 2018 Report(CVPR 2018 速報) (50,000+ views)
- 物体検知(Object Detection) (30,000+ views)
- CVPR 2017 Report(CVPR 2017 速報) (20,000+ views)
- Dense Trajectories Tutorial(Dense Trajectories チュートリアル資料) (20,000+ views)
- 敵対的生成ネットワーク(GAN) (20,000+ views)
- CVPR 2019 Report(CVPR 2019 速報) (18,000+ views)
- CVPR 2015 Survey (13,000+ views)

Hirokatsu Kataoka