Saito Naoki 斉藤直輝

… Alternative Names

斉藤直輝サイトウナオキ

Less

Researcher Number	00798225
Other IDs	https://orcid.org/0000-0001-7611-2461
Affiliation (Current)	2026: 北海道大学, 数理・データサイエンス教育研究センター, 助教
Affiliation (based on the past Project Information) *help	2026: 北海道大学, 数理・データサイエンス教育研究センター, 助教 2024: 北海道大学, 総合IR本部, 助教
Review Section/Research Field	Principal Investigator Basic Section 60080:Database-related Except Principal Investigator Sections That Are Subject to Joint Review: Basic Section60080:Database-related , Basic Section62020:Web informatics and service informatics-related / Basic Section 62020:Web informatics and service informatics-related / Basic Section 60080:Database-related
Keywords	Principal Investigator 生成AI / データ拡張 / 因果的学習基盤 / 反実仮想生成 / 構成画像検索 Except Principal Investigator 推薦 / 強化学習 / 深層学習 / コンピュータビジョン / エッジAI … More / 知識グラフ / 大規模言語モデル / 生成AI / IoT / 人工知能 / ユーザ中心推薦 Less

Construction of a Composed Image Retrieval Framework Based on Causal Counterfactual GenerationPrincipal Investigator
- Principal Investigator
  
  斉藤直輝
- Project Period (FY)
  2026 – 2028
- Research Category
  
  Grant-in-Aid for Early-Career Scientists
- Review Section
  
  Basic Section 60080:Database-related
- Research Institution
  Hokkaido University
生成AIとの融合により潜在的嗜好を把握可能とするユーザ中心推薦技術の構築
- Principal Investigator
  
  長谷山美紀
- Project Period (FY)
  2024 – 2027
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Review Section
  
  Basic Section 60080:Database-related
  Basic Section 62020:Web informatics and service informatics-related
  Sections That Are Subject to Joint Review: Basic Section60080:Database-related , Basic Section62020:Web informatics and service informatics-related
- Research Institution
  Hokkaido University

All 2025 2024

All Journal Article Presentation

[Journal Article] Expert Comment Generation Considering Sports Skill Level Using a Large Multimodal Model with Video and Spatial-Temporal Motion Features2025
- Author(s)
  Seino Tatsuki、Saito Naoki、Ogawa Takahiro、Asamizu Satoshi、Haseyama Miki
- Journal Title
  
  Sensors
  
  Volume: 25 Issue: 2 Pages: 447-447
- DOI
  10.3390/s25020447
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23K21676, KAKENHI-PROJECT-24K02942
[Journal Article] Expert-novice level classification using engineers’ motion data in subway tunnel inspections - Introduction of explainable graph convolutional network -2024
- Author(s)
  清野竜生、斉藤直輝、前田圭介、小川貴弘、長谷山美紀
- Journal Title
  
  Artificial Intelligence and Data Science
  
  Volume: 5 Issue: 1 Pages: 101-109
- DOI
  10.11532/jsceiii.5.1_101
- ISSN
  2435-9262
- Language
  Japanese
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23K21676, KAKENHI-PROJECT-24K02942, KAKENHI-PROJECT-23K11211
[Journal Article] Multi-Modal Gaussian Process Latent Variable Model With Semi-Supervised Label Dequantization2024
- Author(s)
  Maeda Keisuke、Matsumoto Masanao、Saito Naoki、Ogawa Takahiro、Haseyama Miki
- Journal Title
  
  IEEE Access
  
  Volume: 12 Pages: 127244-127258
- DOI
  10.1109/access.2024.3437328
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23K21676, KAKENHI-PROJECT-24K02942
[Journal Article] Expert Novice Level Classification Using Graph Convolutional Network Introducing Confidence-Aware Node-Level Attention Mechanism2024
- Author(s)
  Seino Tatsuki、Saito Naoki、Ogawa Takahiro、Asamizu Satoshi、Haseyama Miki
- Journal Title
  
  Sensors
  
  Volume: 24 Issue: 10 Pages: 3033-3033
- DOI
  10.3390/s24103033
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-23K21676, KAKENHI-PROJECT-24K02942
[Presentation] Expert comment generation from sports videos using multimodal LLM2025
- Author(s)
  Tatsuki Seino, Naoki Saito, Takahiro Ogawa, Huang-Chia Shih, Satoshi Asamizu, Miki Haseyama
- Organizer
  2025 International Workshop on Advanced Image Technology (IWAIT 2025)
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] 反実仮想画像生成モデルを用いた構成画像検索におけるデータ拡張に関する検討2024
- Author(s)
  上杉健大, 斉藤直輝, 前田圭介, 小川貴弘, 長谷山美紀
- Organizer
  令和6年度電気・情報関係学会北海道支部連合大会
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] 半導体製造装置のセンサデータを用いた深層距離学習による類似事例検索に関する検討2024
- Author(s)
  斉藤直輝, 藤後廉, 前田圭介, 小林累輝, 中村隆央, 岡谷基弘, 数井誠人, 松沢貴仁, 小川貴弘, 長谷山美紀
- Organizer
  第38回人工知能学会全国大会 (JSAI2024)
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] Zero-shot composed video retrieval with projection module bridging modality gap2024
- Author(s)
  Kenta Uesugi, Naoki Saito, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
- Organizer
  2024 IEEE 13th Global Conference on Consumer Electronics (GCCE 2024)
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] 個人の感情誘起の類似性を考慮したMultimodal LLMによる画像の感情分類に関する検討2024
- Author(s)
  高橋諒, 斉藤直輝, 前田圭介, 小川貴弘, 長谷山美紀
- Organizer
  令和6年度電気・情報関係学会北海道支部連合大会
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] Confidence-aware spatial-temporal attention graph convolutional network for skeleton-based expert-novice level classification2024
- Author(s)
  Tatsuki Seino, Naoki Saito, Takahiro Ogawa, Satoshi Asamizu, Miki Haseyama
- Organizer
  2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024)
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] [特別講演] 高速道路における橋梁点検効率化のための大規模視覚言語モデルを用いた技術者所見生成技術2024
- Author(s)
  清野竜生, 斉藤直輝, 前田圭介, 小川貴弘, 長谷山美紀
- Organizer
  映像情報メディア学会技術報告
- Invited
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] Personalized visual emotion classification via in-context learning in multimodal LLM2024
- Author(s)
  Ryo Takahashi, Naoki Saito, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
- Organizer
  2024 IEEE 13th Global Conference on Consumer Electronics (GCCE 2024)
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] [特別講演] 高速道路の日常点検効率化に向けたセマンティックセグメンテーションおよび深度推定による枯損木検出技術2024
- Author(s)
  斉藤直輝, 山本一輝, 前田圭介, 小川貴弘, 長谷山美紀
- Organizer
  映像情報メディア学会技術報告
- Invited
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] モーションおよび視線データを用いたSpatial temporal attention GCNによる熟練度分類に関する検討2024
- Author(s)
  清野竜生, 斉藤直輝, 小川貴弘, 浅水仁, 長谷山美紀
- Organizer
  第38回人工知能学会全国大会 (JSAI2024)
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] Graph convolutional network-based sports skill-level recognition via deep metric learning2024
- Author(s)
  Tatsuki Seino, Naoki Saito, Takahiro Ogawa, Satoshi Asamizu, Miki Haseyama
- Organizer
  2024 International Conference on Circuits, Systems, Computers and Communications (ITC-CSCC 2024)
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-24K02942
[Presentation] テキストプロンプト最適化を導入したマルチモーダルLLMによる画像の感情分類の高精度化に関する検討2024
- Author(s)
  高橋諒, 斉藤直輝, 前田圭介, 小川貴弘, 長谷山美紀
- Organizer
  映像情報メディア学会技術報告
- Data Source
  KAKENHI-PROJECT-24K02942

1. 長谷山美紀 (00218463)

# of Collaborated Projects: 1 results

# of Collaborated Products: 12 results
2. 小川貴弘 (20524028)

# of Collaborated Projects: 1 results

# of Collaborated Products: 15 results
3. 藤後廉 (60840395)

# of Collaborated Projects: 1 results

# of Collaborated Products: 1 results
4. 前田圭介

# of Collaborated Projects: 0 results

# of Collaborated Products: 1 results

Saito Naoki 斉藤 直輝

斉藤 直輝 サイトウ ナオキ

Research Projects

Research Products

Co-Researchers

Construction of a Composed Image Retrieval Framework Based on Causal Counterfactual GenerationPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

生成AIとの融合により潜在的嗜好を把握可能とするユーザ中心推薦技術の構築

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

[Journal Article] Expert Comment Generation Considering Sports Skill Level Using a Large Multimodal Model with Video and Spatial-Temporal Motion Features2025

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Expert-novice level classification using engineers’ motion data in subway tunnel inspections - Introduction of explainable graph convolutional network -2024

Author(s)

Journal Title

DOI

ISSN

Language

Data Source

[Journal Article] Multi-Modal Gaussian Process Latent Variable Model With Semi-Supervised Label Dequantization2024

Author(s)

Journal Title

DOI

Data Source

[Journal Article] Expert Novice Level Classification Using Graph Convolutional Network Introducing Confidence-Aware Node-Level Attention Mechanism2024

Author(s)

Journal Title

DOI

Data Source

[Presentation] Expert comment generation from sports videos using multimodal LLM2025

Author(s)

Organizer

Data Source

[Presentation] 反実仮想画像生成モデルを用いた構成画像検索におけるデータ拡張に関する検討2024

Author(s)

Organizer

Data Source

[Presentation] 半導体製造装置のセンサデータを用いた深層距離学習による類似事例検索に関する検討2024

Author(s)

Organizer

Data Source

[Presentation] Zero-shot composed video retrieval with projection module bridging modality gap2024

Author(s)

Organizer

Data Source

[Presentation] 個人の感情誘起の類似性を考慮したMultimodal LLMによる画像の感情分類に関する検討2024

Author(s)

Organizer

Data Source

[Presentation] Confidence-aware spatial-temporal attention graph convolutional network for skeleton-based expert-novice level classification2024

Author(s)

Organizer

Data Source

[Presentation] [特別講演] 高速道路における橋梁点検効率化のための大規模視覚言語モデルを用いた技術者所見生成技術2024

Author(s)

Organizer

Data Source

[Presentation] Personalized visual emotion classification via in-context learning in multimodal LLM2024

Author(s)

Organizer

Data Source

[Presentation] [特別講演] 高速道路の日常点検効率化に向けたセマンティックセグメンテーションおよび深度推定による枯損木検出技術2024

Author(s)

Organizer

Data Source

[Presentation] モーションおよび視線データを用いたSpatial temporal attention GCNによる熟練度分類に関する検討2024

Author(s)

Organizer

Data Source

[Presentation] Graph convolutional network-based sports skill-level recognition via deep metric learning2024

Saito Naoki 斉藤直輝

斉藤直輝サイトウナオキ