山口 光太
CyberAgent AI Lab 主席研究員
Google Scholar / Semantic Scholar / Github / X / LinkedIn
株式会社サイバーエージェントの主席研究員．研究組織AI Labの黎明期から全体の研究開発活動をリードしつつ，クリエイティブ制作のためのコンピュータビジョン，機械学習の研究に取り組む．2014年から2017年まで東北大学大学院情報科学研究科助教．2014年米国ニューヨーク州Stony Brook大学にてコンピュータ科学のPh.D.取得．2008年東京大学大学院情報理工学系研究科修士課程修了，2006年東京大学工学部計数工学科卒業．
Tomoyuki Suzuki, Kangjun Liu, Naoto Inoue, Kota Yamaguchi, "LayerD: Decomposing Raster Graphic Designs into Layers", ICCV 2025.
Jan Zdenek, Wataru Shimoda, Kota Yamaguchi, "OTR: Synthesizing Overlay Text Dataset for Text Removal", ACMMM Dataset Track 2025.
Kotaro Kikuchi, Ukyo Honda, Naoto Inoue, Mayu Otani, Edgar Simo-Serra, Kota Yamaguchi, "Multimodal Markup Document Models for Graphic Design Completion", ACMMM 2025. [arXiv] [Project]
Daichi Haraguchi, Wataru Shimoda, Kota Yamaguchi, Seiichi Uchida, "Total Disentanglement of Font Images into Style and Character Class Features", ICDAR 2025. [arXiv]
Wataru Shimoda, Naoto Inoue, Daichi Haraguchi, Hayato Mitani, Seichi Uchida, Kota Yamaguchi, "Type-R: Automatically Retouching Typos for Text-to-Image Generation", CVPR 2025. [arXiv]
Daichi Haraguchi, Naoto Inoue, Wataru Shimoda, Hayato Mitani, Seiichi Uchida, Kota Yamaguchi, "Can GPTs Evaluate Graphic Design Based on Design Principles?" SIGGRAPH Asia Technical Communications 2024. [arXiv]
Wataru Shimoda, Naoto Inoue, Daichi Haraguchi, Hayato Mitani, Seichi Uchida, Kota Yamaguchi, "Type-R: Automatically Retouching Typos for Text-to-Image Generation", CVPR 2025. [arXiv]
Tomoyuki Suzuki, Kotaro Kikuchi, Kota Yamaguchi, "Fast Sprite Decomposition from Animated Graphics", ECCV 2024. [arXiv] [Project]
Naoto Inoue, Kento Masui, Wataru Shimoda, Kota Yamaguchi, "OpenCOLE: Towards Reproducible Automatic Graphic Design Generation", CVPR Workshops 2024. [arXiv] [Project]
Daichi Horita, Naoto Inoue, Kotaro Kikuchi, Kota Yamaguchi, Kiyoharu Aizawa, "Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation", CVPR 2024. [arXiv] [Project]
Shoko Sawada, Tomoyuki Suzuki, Kota Yamaguchi, Masashi Toyoda, "Visual Explanation for Advertising Creative Workflow", CHI EA 2024. [ACM]
Wataru Shimoda, Daichi Haraguchi, Seiichi Uchida, Kota Yamaguchi, "Towards Diverse and Consistent Typography Generation", WACV 2024. [arXiv]
Naoto Inoue, Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi, “LayoutDM: Discrete Diffusion Model for Controllable Layout Generation”, CVPR 2023. [arXiv] [Project]
Naoto Inoue, Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi, “Towards Flexible Multi-modal Document Models”, CVPR 2023. [arXiv] [Project]
Kotaro Kikuchi, Naoto Inoue, Mayu Otani, Edgar Simo-Serra, Kota Yamaguchi, "Generative Colorization of Structured Mobile Web Pages", WACV 2023. [arXiv] [Project]
Kotaro Kikuchi, Mayu Otani, Kota Yamaguchi, Edgar Simo-Serra, "Modeling Visual Containment for Web Page Layout Optimization", Pacific Graphics 2021. [PDF] [Project]
Wataru Shimoda, Daichi Haraguchi, Seiichi Uchida, Kota Yamaguchi, "De-rendering Stylized Texts", ICCV 2021. [arXiv] [Github]
Kota Yamaguchi, "CanvasVAE: Learning to Generate Vector Graphic Documents", ICCV 2021. [arXiv] [Github]
Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, Kota Yamaguchi, "Constrained Graphic Layout Generation via Latent Optimization", ACMMM 2021. [arXiv] [Github] [Project]
Kotaro Kikuchi, Kota Yamaguchi, Edgar Simo-Serra, Tetsunori Kobayashi, "Regularized Adversarial Training for Single-Shot Virtual Try-On", ICCV Workshops 2019. [CVF]
Yuto Shinahara, Takuro Karamatsu, Daisuke Harada, Kota Yamaguchi, Seiichi Uchida, "Serif or Sans: Visual Font Analytics on Book Covers and Online Advertisements", ICDAR 2019. [arXiv]
Tianlu Wang, Kota Yamaguchi, Vicente Ordonez, "Feedback-prop: Convolutional Neural Network Inference under Partial Evidence", CVPR 2018. [arXiv] [Github]
Kota Yamaguchi, Takayuki Okatani, Takayuki Umeda, Kazuhiko Murasaki, Kyoko Sudo, "End-to-end learning potentials for structured attribute prediction", arXiv preprint arXiv:1708.01892. [arXiv]
Shuohao Li, Kota Yamaguchi, Takayuki Okatani, "Attention to Describe Products with Attributes", MVA 2017. [IEEE]
Pongsate Tangseng, Kota Yamaguchi, Takayuki Okatani, "Recommending outfits from personal closet", ICCV Workshops 2017. [arXiv] [project]
Takuya Yashima, Naoaki Okazaki, Kentaro Inui, Kota Yamaguchi, Takayuki Okatani, "Learning to Describe E-Commerce Images from Noisy Online Data", ACCV 2016. [Springer]
Masayasu Muraoka, Sumit Maharjan, Masaki Saito, Kota Yamaguchi, Naoaki Okazaki, Takayuki Okatani, Kentaro Inui, "Recognizing Open-Vocabulary Relations between Objects in Images", PACLIC 2016. [PDF]
Pongsate Tangseng, Zhipeng Wu, Kota Yamaguchi, "Looking at Outfit to Parse Clothing", arXiv preprint arXiv:1703.01386. [arXiv] [project]
Sirion Vittayakorn, Takayuki Umeda, Kazuhiko Murasaki, Kyoko Sudo, Takayuki Okatani, Kota Yamaguchi, "Automatic Attribute Discovery with Neural Activations", ECCV 2016. [arXiv]
Vicente Ordonez, Xufeng Han, Polina Kuznetsova, Girish Kulkarni, Margaret Mitchell, Kota Yamaguchi, Karl Stratos, Amit Goyal, Jesse Dodge, Alyssa Mensch, Hal Daume III, Alexander C Berg, Yejin Choi, Tamara L Berg, "Large Scale Retrieval and Generation of Image Descriptions", IJCV 2015. [Springer]
Kota Yamaguchi, Takayuki Okatani, Kyoko Sudo, Kazuhiko Murasaki, Yukinobu Taniguchi, "Mix and Match: Joint Model for Clothing and Attribute Recognition", BMVC 2015. [BMVA]
Sirion Vittayakorn, Kota Yamaguchi, Alexander C Berg, Tamara L Berg, "Runway to Realway: Visual Analysis of Fashion", WACV 2015. [IEEE]
Kota Yamaguchi, Tamara L Berg, Luis E Ortiz, "Chic or Social: Visual Popularity Analysis in Online Fashion Networks", ACM Multimedia 2014. [ACM]
M Hadi Kiapour, Kota Yamaguchi, Alexander C Berg, Tamara L Berg, "Hipster Wars: Discovering Elements of Fashion Styles", ECCV 2014. [Springer]
Kota Yamaguchi, M Hadi Kiapour, Luis E Ortiz, Tamara L Berg, "Retrieving Similar Styles to Parse Clothing", TPAMI 2014. [IEEE]
Kota Yamaguchi, M Hadi Kiapour, Tamara L Berg, "Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing Items", ICCV 2013. [IEEE] [Github]
Kota Yamaguchi, M Hadi Kiapour, Luis E Ortiz, Tamara L Berg, "Parsing Clothing in Fashion Photographs", CVPR 2012. [IEEE]
Alexander C Berg, Tamara L Berg, Hal Daume III, Jesse Dodge, Amit Goyal, Xufeng Han, Alyssa Mensch, Margaret Mitchell, Aneesh Sood, Karl Stratos, Kota Yamaguchi, "Understanding and Predicting Importance in Images", CVPR 2012. [IEEE]
Jesse Dodge, Amit Goyal, Xufeng Han, Alyssa Mensch, Margaret Mitchell, Karl Stratos, Kota Yamaguchi, Yejin Choi, Hal Daume III, Alexander C Berg, Tamara L Berg, "Detecting visual text", NAACL 2012. [ACM]
Margaret Mitchell, Jesse Dodge, Amit Goyal, Kota Yamaguchi, Karl Stratos, Xufeng Han, Alyssa Mensch, Alexander C Berg, Tamara L Berg, Hal Daume III, "Midge: Generating Image Descriptions From Computer Vision Detections", European Chapter of the Association for Computational Linguistics, EACL 2012. [PDF]
Kota Yamaguchi, Alexander C Berg, Luis E Ortiz, Tamara L Berg, "Who are you with and where are you going?", CVPR 2011. [IEEE]
Kota Yamaguchi, Takashi Komuro, Masatoshi Ishikawa, "PTZ Control with Head Tracking for Video Chat", ACM CHI 2009 Extended Abstracts.
Kota Yamaguchi, Yoshihiro Watanabe, Takashi Komuro, Masatoshi Ishikawa, "Interleaved Pixel Lookup for Embedded Computer Vision", Fourth IEEE Workshop on Embedded Computer Vision (ECVW).
Kota Yamaguchi, Yoshihiro Watanabe, Takashi Komuro, Masatoshi Ishikawa, "Design of a Massively Parallel Vision Processor based on Multi-SIMD Architecture", 2007 IEEE International Symposium on Circuits and Systems (ISCAS2007), pp.3498-3501.
村岡雅康, Sumit Maharjan, 齋藤真樹, 山口光太, 岡崎直観, 岡谷貴之, 乾健太郎, 画像説明文生成に向けた物体間の関係の認識. 言語処理学会第22回年次大会, pp.669-672, March 2016.
Maharjan Sumit, 齋藤真樹, 山口光太, 岡崎直観, 岡谷貴之, 乾健太郎, Learning Visual Attributes from Image and Text. 言語処理学会第21回年次大会, pp.1048-1051, March 2015.
Kota Yamaguchi, Yoshihiro Watanabe, Takashi Komuro, Masatoshi Ishikawa, "An Interface for Peering inside Remote Field of View", Proc. 13th Image Media Processing Symposium (IMPS2008), pp. 83-84.
Kota Yamaguchi, Yoshihiro Watanabe, Takashi Komuro, Masatoshi Ishikawa, "Design of a Massively Parallel Vision Processor for High Speed Image Recognition", Proc of Forum on Information Technology 2006, Vol. 1, pp 181-184.
Kota Yamaguchi, Yoshihiro Watanabe, Takashi Komuro, Masatoshi Ishikawa, "Design of a High-Performance Vision Processor with Shared-Memory Multi-SIMD Architecture", Technical Report, Technical Committee on Integrated Circuits and Devices (ICD), Vol. 106, No. 92, pp 89-94.
ACCV AC (2020, 2022), Tutorial Chair (2024), Financial Chair (2026)
ICCV AC (2023)
CVPR GDUG workshop organizer (2024)
MIRU program co-chair (2015), AC (2016-2018), financial chair (2022), industry chair (2024)