Rchr
J-GLOBAL ID：201701009002985118   Update date: Mar. 17, 2023

Otani Mayu

Otani Mayu
Affiliation and department：
CyberAgent, Inc. AI Lab

About CyberAgent, Inc. AI Lab


Job title： Research Scientist
Homepage URL  (1)： https://mayu-ot.github.io
Research field  (1)： Perceptual information processing
Research theme for competitive and other funds  (1)：
  • 2017 - 2019 映像とテキストを組み合わせたストーリー理解の実現
Papers (37)：
  • Yutaro Yamada, Mayu Otani. Does Robustness on ImageNet Transfer to Downstream Tasks?. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022
  • Riku Togashi, Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkila, Tetsuya Sakai. AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022
  • Mayu Otani, Riku Togashi, Yuta Nakashima, Esa Rahtu, Janne Heikkila, Shin'ichi Satoh. Optimal Correction Cost for Object Detection Evaluation. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022
  • Chenhui Chu, Vinicius Oliveira, Felix Giovanni Virgo, Mayu Otani, Noa Garcia, Yuta Nakashima. The semantic typology of visually grounded paraphrases. Computer Vision and Image Understanding. 2022. 215. 103333-103333
  • Yusuke Hirota, Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima, Ittetsu Taniguchi, Takao Onoye. Visual Question Answering with Textual Representations for Images. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). 2021
ｍore...
MISC (5)：
  • Yuta Kayatani, Mayu Otani, Chenhui Chu, Yuta Nakashima, Haruo Takemura. Predicting Laughters in Comedy Drama with Subtitles and Facial Expression. The 33rd Annual Conference of the Japanese Society for Artificial Intelligence, 2019 (JSAI 2019). 2019
  • Chenhui Chu, Mayu Otani, Yuta Nakashima. Towards Image-pivoted Paraphrase Extraction. YANS 2017. 2017
  • OTANI Mayu, NAKASHIMA Yuta, SATO Tomokazu, YOKOYA Naokazu. Video Summarization Based on Contents Similarity between User Specified-description and Video. Technical report of IEICE. Multimedia and virtual environment. 2015. 114. 410. 99-104
  • Video Summarization Based on Contents Similarity between User Specified-description and Video. IPSJ SIG Notes. CVIM. 2015. 2015. 19. 1-6
  • OTANI Mayu, HIOKI Hirohisa. Video Colorization Based on Motion Vector Estimation and Edge-Oriented Color Propagation. 2013. 112. 467. 13-18
Lectures and oral presentations  (6)：
  • 広告を例とした深層生成モデルの応用と課題
    (第25回情報論的学習理論ワークショップ(IBIS2022) 2022)
  • コンピュータビジョンタスクの評価
    (映像情報メディア学会関西支部専門講習会 2022)
  • サイバーエージェントAI Labにおけるコンピュータビジョン研究の取り組み
    (第58回人工知能セミナー 2022)
  • 有名企業のキャリアと働き方の実際
    (第3回インダストリアルAIシンポジウム 2022)
  • AIは映像を理解しているのか ー深層学習以後の映像理解研究と評価・分析ー
    (東京大学学部横断型教育プログラムメディアコンテンツ特別講義II 2022)
ｍore...
Professional career (1)：
  • 博士(工学) (奈良先端科学技術大学院大学)
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page

TOP

BOTTOM