Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
Înapoi la articole →

shunk031.me

shunk031.me/index.xml
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 183

  1. Our Presentations at IPSJ 2025

    (shunk031.me)

    We will present the following paper at IPSJ 2025: 永井 大地, 守田 竜梧, 北田 俊輔, 彌冨 仁.

  2. SciGA: A Comprehensive Dataset for Designing Graphical Abstracts in Academic Papers

    (shunk031.me)

  3. Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition

    (shunk031.me)

    This paper is an extended version of the content presented at the “Practical ML for Low Resource Settings Workshop @ ICLR 2024”.

  4. Accepted our journal paper to IEEE Access

    (shunk031.me)

    The following paper has been accepted to the IEEE Access.

  5. VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction

    (shunk031.me)

  6. ECCV 2024 速報

    (shunk031.me)

    I contributed a summary on creative graphic design to the ECCV2024 report on cvpaper.challenge group.

  7. 潜在拡散モデルにおけるプロンプトを用いた配色制御の試み

    (shunk031.me)

  8. 学術論文における Graphical Abstract 自動生成の初期検討

    (shunk031.me)

  9. 大規模言語モデルを用いたオノマトペ付与による日本語音声データセットの拡張

    (shunk031.me)

  10. text-to-image 拡散モデルにおける誘導 attention map を用いた画像生成手法の提案

    (shunk031.me)

  11. Our Presentations at YANS 2024

    (shunk031.me)

    We will present the following papers at YANS 2024: 川田 拓朗, 根本 颯汰, 北田 俊輔, 彌冨 仁.

  12. 離散拡散モデルにおけるレイアウトの“固着”を緩和する Layout-Corrector の提案

    (shunk031.me)

  13. Our Presentations at MIRU 2024

    (shunk031.me)

    We will present the following paper at MIRU 2024: 岩井 翔真, 長内 淳樹, 北田 俊輔, 大町 真一郎.

  14. [Journal Club] Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation (CVPR'24)

    (shunk031.me)

    第61回 コンピュータビジョン勉強会＠関東（後編） 目的： 2024年の6月17日～21日にかけて開催されるコンピュータビジョンのトップカンファレンスの一つである 「Conference on Computer Vision and Pattern Recognition (CVPR) 2024」の論文読み会(後編)です。

  15. 新卒社員の仕事紹介 画像生成の研究開発に携わるリサーチサイエンティスト編

    (shunk031.me)

  16. Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Model

    (shunk031.me)

  17. Accepted our paper to ECCV2024

    (shunk031.me)

    The following paper has been accepted to the ECCV2024.

  18. [Invited Presentation] SSII2024 Technical map: Creative Design Generation (SSII'24)

    (shunk031.me)

    技術マップ 文献情報

  19. Published our technical map at SSII2024

    (shunk031.me)

    Our team provided and published the following technical map at SSII2024 session. 🌐 https://bit.ly/ssii2024-techmap-creative-design-map 📃 https://bit.ly/ssii2024-techmap-creative-design-sheet See this post for more details.

  20. [Journal Club] Scaling Rectified Flow Transformers for High-Resolution Image Synthesis / Stable Diffusion 3

    (shunk031.me)

    Journal Club Stability.AI からこれまでの拡散モデルとは少し異なるパラダイムの新たな Text-to-Image モデル Stable Diffusion 3 (SD3) の提案について紹介します。

  21. Accepted our paper to PM4LRS workshop at ICLR2024

    (shunk031.me)

    The following paper has been accepted at Practical ML for Low Resource Settings Workshop (PM4LRS) @ ICLR 2024.

  22. [Journal Club] BERT4CTR: An Efficient Framework to Combine Pre-trained Language Model with Non-textual Features for CTR Prediction (KDD'23)

    (shunk031.me)

    KDD2023 論文読み会（オンライン開催） 概要 2023年8月に開催されたデータマイニング関連の国際学術会議、KDD2023に(29th ACM SIGKDD Conference on Knowledge Discovery & Data Mining) で発表された論文の読み会です。

  23. 人工知能学会誌 博士論文集 2022.10～2023.9授与

    (shunk031.me)

    該当ページ (PDF, 0.94MB) 人工知能学会誌では，過去1年間に人工知能に関連する研究で博士の学位を授与された研究者の方々の博士論文の概要を，その方々のプロフィールとともにまとめて掲載することにより，世代の異なる研究者間の交流や，その分野の研究動向の把握の一助とすることを狙いとして，博士論文概要の特集を，毎年1月号に掲載致しております．

  24. Published a special issue of doctoral dissertation in Journal of JSAI

    (shunk031.me)

    A special issue of Journal of JSAI on doctoral dissertations, including a summary of my dissertation, is now available: https://www.jstage.jst.go.jp/article/jjsai/39/1/39_50/_article/-char/ja/

  25. 画像生成 AI 入門：Python による拡散モデルの理論と実践

    (shunk031.me)

    講義について 注記 本講座は FastCampus 側で公開されています。

  26. [Invited Presentation] Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives

    (shunk031.me)

    Doctoral Dissertation Presentation Slides for the presentation of my doctoral dissertation (in Japanese).

  27. Successfully Defended my Ph.D. Dissertation

    (shunk031.me)

    I am thrilled to announce that I have successfully defended my PhD on March 24, 2023.

  28. Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives

    (shunk031.me)

  29. Our Presentations at ANLP 2023

    (shunk031.me)

    We will present the following paper at ANLP 2023: 根本 颯汰, 北田 俊輔, 彌冨 仁.

  30. Majority or Minority: 固有表現抽出におけるデータの不均衡性に着目した損失関数の提案

    (shunk031.me)

  31. Got Hosei University Research Grant 2022

    (shunk031.me)

    Got Hosei University Research Grant for Doctoral Course Adopters in 2022 (480,000 JPY).

  32. DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention

    (shunk031.me)

  33. [Journal Club] Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents (CIKM'22)

    (shunk031.me)

    IR Reading 2022 秋 概要 情報アクセス分野に関する主要国際会議（SIGIR や WSDM など）の論文読み合わせを行う IR Reading をオンラインにて開催します．多人数で協力しあって論文を紹介しあうことで，論文への理解を深めたり，分野全体のトレンドを掴んだりする場となれば幸いです．これまでの勉強会の内容につきましては，過去のページ をご覧ください．

  34. Accepted our journal paper to IEEE Access

    (shunk031.me)

    The following paper has been accepted to the IEEE Access.

  35. Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training

    (shunk031.me)

    arXiv Springer SCImago

  36. Accepted our journal paper to Springer Applied Intelligence journal

    (shunk031.me)

    The following paper has been accepted to the Springer Applied Intelligence.

  37. Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired

    (shunk031.me)

  38. Accepted our paper to IEEE HONET2022

    (shunk031.me)

    The following paper has been accepted to the IEEE HONET2022.

  39. 固有表現認識タスクにおけるデータセットの偏りに着目した動的重み付け損失関数の提案

    (shunk031.me)

  40. Our Presentations at YANS 2022

    (shunk031.me)

    We will present the following papers at YANS 2022: 北田 俊輔, 井上 直人, 大谷 まゆ, 彌冨 仁.

  41. Document AI タスクに向けた大規模事前学習済みモデルを活用した Layout-aware Prompting

    (shunk031.me)

  42. Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents

    (shunk031.me)

  43. Accepted our paper to ACM CIKM2022

    (shunk031.me)

    The following paper has been accepted to the ACM CIKM2022.

  44. [Invited Talk] Introduction to AllenNLP to accelerate NLP research

    (shunk031.me)

    【NLP Hacks vol.6】NLP の研究を加速させる AllenNLP 入門 動画 - Video 資料 - Slides

  45. Got JASSO Scholarship for Top 30% Excellent Graduate School Students

    (shunk031.me)

    Got JASSO Scholarship for Top 30% Excellent Graduate School Students (793,000 JPY) from Japan Student Services Organization.

  46. 法政大学大学院入学案内 2023 - 学生・修了生の声

    (shunk031.me)

    法政大学大学院入学案内 2023 該当ページのみ (PDF, 1.7MB） 全体 (PDF, 9.9MB） 人工知能と人がよりよく共存するため AI 技術の拡張に取り組んでいます 北田俊輔 博士後期課程在学中 / 日本学術振興会特別研究員 研究テーマ 摂動に頑健で解釈可能な深層学習モデルの開発とその解釈性の評価 私の研究 AI 技術の一つ、自然言語処理について研究を進める中で、特に深層学習と呼ばれる、人間の脳を模倣した手法をベースに人間の言葉を理解させる方法について考えています。

  47. My comments were published in the admission guide of Hosei University

    (shunk031.me)

    My comments as a representative of alumni were published in the admission guide of Hosei University.

  48. Ad Creative Discontinuation Prediction with Multi-Modal Multi-Task Neural Survival Networks

    (shunk031.me)

    arXiv MDPI SCImago

  49. [Invited Talk] My experience about JSPS Research Fellowship

    (shunk031.me)

  50. Accepted our journal paper to MDPI Applied Sciences journal

    (shunk031.me)

    The following paper has been accepted to the MDPI Applied Sciences.