Takahiro Ogawa 研究室

主宰者：Takahiro Ogawa

北海道大学

AI 要約（直近 5 年の研究成果）

本研究室は、深層学習モデルの実用性と堅牢性の向上を主要なテーマとしています。特に、大規模言語モデルや視覚言語モデルなどの基盤モデルが、実世界の多様なデータや個人差にどう対応するかという課題に取り組んでいます。視覚感情認識や医療報告書生成など、個人ごとのニーズに合わせた予測を実現する手法を開発する一方で、敵対的攻撃への耐性向上や偏った予測の改善といった、モデルの信頼性確保も重要な研究対象です。技術的には、プロンプト学習やLoRA適応といった効率的なパラメータ調整、データの合成・拡張、複数タスクの同時学習など、多岐にわたるアプローチを採用しています。また、医療画像解析、3D場景生成、音声領域への応用拡張など、コンピュータビジョンや音声処理といった異なるモダリティ間でのモデル応用も進めています。これらの研究を通じて、汎用的で柔軟性の高い機械学習システムの実装と評価法の確立に貢献しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（100 件）

[2026] Research on compliance steers of strut type front suspension subject to lateral force and longitudinal force during cornering
DOI: https://doi.org/10.1299/transjsme.25-00186
[2026] Personalized Longitudinal Medical Report Generation via Temporally-Aware Federated Adaptation
[2026] Exiting nerve root injury during full-endoscopic trans-Kambin’s triangle lumbar interbody fusion (FE-KLIF) and how to avoid it:a multicenter study
DOI: https://doi.org/10.2152/jmi.73.26
[2026] Discrete Prompt Tuning via Recursive Utilization of Black-Box Multimodal Large Language Model for Personalized Visual Emotion Recognition
DOI: https://doi.org/10.1109/access.2026.3682871
[2026] Risk-Aware Utility Re-Ranking for Financial Asset Recommendation
DOI: https://doi.org/10.1145/3773966.3779383
[2026] Leveraging Attack Non-Transferability to Boost Adversarial Robustness for Foundation Models
DOI: https://doi.org/10.3390/app16083894
[2026] H3GM: History-Guided Global Geometric Metric for Single Image to 3D Scene Generation
DOI: https://doi.org/10.1109/icassp55912.2026.11461973
[2026] Adaptive Shared Experts with Lora-Based Mixture of Experts for Multi-Task Learning
DOI: https://doi.org/10.1109/icassp55912.2026.11462286
[2026] Predictive but Not Plannable: RC-aux for Latent World Models
[2025] Enhanced framework for generating counterfactual images with sophisticated caption and inversion-free image editing
DOI: https://doi.org/10.1117/12.3057596

続きを表示（残り 90 件）

[2025] Expert comment generation from sports videos using multimodal LLM
DOI: https://doi.org/10.1117/12.3057887
[2025] Balancing generalization and personalization by sharing layers in clustered federated learning
DOI: https://doi.org/10.1117/12.3057727
[2025] Learning hierarchical video-text relationship via large language model for cross-modal video retrieval
DOI: https://doi.org/10.1117/12.3057615
[2025] Multistage deep learning for classification of Helicobacter pylori infection status using endoscopic images
DOI: https://doi.org/10.1007/s00535-024-02209-5
[2025] Analysis of Model Merging for Open-Vocabulary Models with Parameter Efficient Fine-Tuning Leveraging Distributed Data
DOI: https://doi.org/10.1109/icce-taiwan66881.2025.11207863
[2025] Evaluation of Effectiveness of Adversarial Defense Model Using Only Brain Activity Information
DOI: https://doi.org/10.1109/icce-taiwan66881.2025.11207822
[2025] Personalized Visual Emotion Classification through Discrete Prompt Tuning of Large Multimodal Model
DOI: https://doi.org/10.1109/icce-taiwan66881.2025.11207879
[2025] Stabilizing Self-consuming Training Loop on Music Generation Based on Music Embeddings
DOI: https://doi.org/10.1109/icce-taiwan66881.2025.11208005
[2025] Corrosion Detection through Integration of Multi-resolution Semantic Segmentation
DOI: https://doi.org/10.1109/itc-cscc66376.2025.11137686
[2025] Extending Gaussian Splatting to Audio: Optimizing Audio Points for Novel-View Acoustic Synthesis
DOI: https://doi.org/10.1109/vrw66409.2025.00352
[2025] Answer to the Letter to the Editor from Hinpetch Daungsupawong Concerning "Development of New Surgical Training for Full Endoscopic Surgery Using 3D-Printed Models"
DOI: https://doi.org/10.22603/ssrr.2025-0009
[2025] Improving robustness of CLIP by adversarial training enhanced by brain activity
DOI: https://doi.org/10.1117/12.3058026
[2025] Application of Principal Component Analysis in Hyperspectral Analysis of Rubber Materials
DOI: https://doi.org/10.1109/gcce65946.2025.11275031
[2025] Enhancing Medical Dataset Distillation Based on Classifier-Guided Diffusion Model
DOI: https://doi.org/10.1109/gcce65946.2025.11275151
[2025] Image-guided 360-degree Scene Generation with Structural and Visual Consistency
DOI: https://doi.org/10.1109/gcce65946.2025.11275093
[2025] Enhancing Image Classifier Robustness via Prompt-Based Counterfactual Data-Augmentation with Intermediate Transitions
DOI: https://doi.org/10.1109/gcce65946.2025.11274759
[2025] Rethinking Continual Learning with Pre-Trained Models: Knowledge-Preserving Approach
DOI: https://doi.org/10.1109/gcce65946.2025.11274647
[2025] Patch-wise Extension of EVA Score for Semi-supervised Lung Field Segmentation
DOI: https://doi.org/10.1109/gcce65946.2025.11274929
[2025] Generalizing Stylized Motion Generation Method by Introducing Metadata-Independent Learning and Unified Multiple Motion Dataset
DOI: https://doi.org/10.1109/tmm.2025.3645612
[2025] Abstract 4359624: Automated Frailty Evaluation Using Machine Learning in Elderly Patients with Heart Failure
DOI: https://doi.org/10.1161/circ.152.suppl_3.4359624
[2025] An attempt at management and operation indicators to improve the social value of parks (Part3)
DOI: https://doi.org/10.5632/jila.89.234
[2025] Context-aware Image-to-Music Generation via Bridging Modalities through Musical Captions
DOI: https://doi.org/10.1145/3746027.3755794
[2025] Deep-learning-based automatic liver segmentation using computed tomography images in dogs
DOI: https://doi.org/10.3389/fvets.2025.1681820
[2025] Stream Voice Diffusion: Real-Time Image Generation from Speech
DOI: https://doi.org/10.1109/gcce65946.2025.11275506
[2025] Graph-based Pass Receiver Prediction in Soccer with Consideration of Passer’s Body Orientation
DOI: https://doi.org/10.1109/gcce65946.2025.11274936
[2025] Foul Severity Classification from Multi-View Soccer Videos with Attention and Class Characteristics
DOI: https://doi.org/10.1109/gcce65946.2025.11274603
[2025] An Investigation of Data Augmentation for Image Classification Network Based on Graph Convolution
DOI: https://doi.org/10.1109/gcce65946.2025.11275254
[2025] Similar Image Generation via Human-like Iterative Prompt Refinement with Multimodal Large Language Model
DOI: https://doi.org/10.1109/gcce65946.2025.11275204
[2025] SSM-based Sequential Recommendation Considering Short-term Dependencies of Time and Adjacency
DOI: https://doi.org/10.1109/gcce65946.2025.11274789
[2025] Novel predictors of tumor growth by exploratory quantitative analysis of radiomics features from MRI data for incidentally discovered meningioma
DOI: https://doi.org/10.1007/s11060-025-05186-8
[2025] GeoJapan Fusion Framework: A Large Multimodal Model for Regional Remote Sensing Recognition
DOI: https://doi.org/10.3390/rs17173044
[2025] Enhancing Adversarial Robustness of Foundation Models Without Data Centralization
DOI: https://doi.org/10.1109/icip55913.2025.11084716
[2025] Cross-domain multi-step thinking: Zero-shot fine-grained traffic sign recognition in the wild
DOI: https://doi.org/10.1016/j.knosys.2025.114172
[2025] Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memory
DOI: https://doi.org/10.1109/icip55913.2025.11084758
[2025] Out-of-Distribution Sample Selection Generated by Diffusion Model toward Model Generalization
DOI: https://doi.org/10.1109/icip55913.2025.11084593
[2025] Information-Guided Diffusion Sampling for Dataset Distillation
[2025] Linear Structure Analysis of Embeddings for Bias Disparity Reduction in Collaborative Filtering
DOI: https://doi.org/10.1109/tsc.2025.3570852
[2025] A propensity score–matched analysis of stereotactic radiotherapy for metastatic brain tumors using the Leksell Gamma Knife Icon Mask system: a single-center retrospective comparative study of cases meeting and not meeting the JLGK0901 Criteria
DOI: https://doi.org/10.3171/2025.1.jns242424
[2025] Analysis of Model Merging Methods for Continual Updating of Foundation Models in Distributed Data Settings
DOI: https://doi.org/10.3390/app15095196
[2025] Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples
DOI: https://doi.org/10.3390/s25092736
[2025] Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
DOI: https://doi.org/10.1609/aaai.v39i4.32391
[2025] Triplet Synthesis for Enhancing Composed Image Retrieval via Counterfactual Image Generation
DOI: https://doi.org/10.1109/icassp49660.2025.10887762
[2025] Robust Adversarial Defense Based on Non-Transferability of Attack Across Foundation Models
DOI: https://doi.org/10.1109/icassp49660.2025.10888691
[2025] Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images
DOI: https://doi.org/10.1109/icassp49660.2025.10889714
[2025] Generative Dataset Distillation Based on Self-knowledge Distillation
DOI: https://doi.org/10.1109/icassp49660.2025.10888970
[2025] Gradient-Oriented Clustered Federated Learning With Efficient Knowledge Sharing in Non-IID Settings
DOI: https://doi.org/10.1109/icassp49660.2025.10890238
[2025] Expert Comment Generation Considering Sports Skill Level Using a Large Multimodal Model with Video and Spatial-Temporal Motion Features
DOI: https://doi.org/10.3390/s25020447
[2025] Enhancing Classification Models With Sophisticated Counterfactual Images
DOI: https://doi.org/10.1109/ojsp.2025.3530843
[2025] Enhancing Generative Class Incremental Learning Performance With a Model Forgetting Approach
DOI: https://doi.org/10.1109/ojsp.2025.3528900
[2025] Exponential Dissimilarity-Dispersion Family for Domain-Specific Representation Learning
DOI: https://doi.org/10.1109/tip.2025.3608661
[2025] [Paper] Few-shot Personalized Saliency Prediction Based on Interpersonal Gaze Patterns
DOI: https://doi.org/10.3169/mta.13.382
[2024] Discriminator-enhanced Music Generation Based on Multitrack Music Transformer
DOI: https://doi.org/10.1109/icce-taiwan62264.2024.10674555
[2024] Improving Zero-shot Adversarial Robustness via Integrating Image Features of Foundation Models
DOI: https://doi.org/10.1109/gcce62371.2024.10760921
[2024] Structured Polyphonic Music Generation with Diffusion Transformer
DOI: https://doi.org/10.1109/gcce62371.2024.10760546
[2024] Lung Disease Classification with Limited Training Data Based on Weight Selection Technique
DOI: https://doi.org/10.1109/gcce62371.2024.10760434
[2024] DQG: Database Question Generation for Exact Text-based Image Retrieval
DOI: https://doi.org/10.1145/3664647.3681469
[2024] Introducing Class Replacement Technique in Class Incremental Learning in Generative Models
DOI: https://doi.org/10.1109/icce-taiwan62264.2024.10674134
[2024] Motion-STUDiO : Motion Style Transfer Utilized for Dancing Operation by Considering Both Style and Dance Features
DOI: https://doi.org/10.1109/icce-taiwan62264.2024.10674583
[2024] ConcVAE: Conceptual Representation Learning
DOI: https://doi.org/10.1109/tnnls.2024.3404496
[2024] Zero-shot High-risk Situation Detection Based on Semantic Segmentation and Pose Estimation Using Fixed-point Cameras at Construction Sites
DOI: https://doi.org/10.1109/itc-cscc62988.2024.10628198
[2024] Graph Convolutional Network-based Sports Skill-level Recognition via Deep Metric Learning
DOI: https://doi.org/10.1109/itc-cscc62988.2024.10628219
[2024] Generative Dataset Distillation: Balancing Global Structure and Local Details
DOI: https://doi.org/10.1109/cvprw63382.2024.00762
[2024] Multimodal Adversarial Defense Trained on Features Extracted from Images and Brain Activity
DOI: https://doi.org/10.1109/gcce62371.2024.10760752
[2024] Zero-shot Controllable Music Generation from Videos Using Facial Expressions
DOI: https://doi.org/10.1109/gcce62371.2024.10760865
[2024] Zero-shot Composed Video Retrieval with Projection Module Bridging Modality Gap
DOI: https://doi.org/10.1109/gcce62371.2024.10760666
[2024] Emotion-conditional Image Generation Reflecting Semantic Alignment with Text-to-Image Models
DOI: https://doi.org/10.1109/gcce62371.2024.10760298
[2024] Lung Cancer Classification Using Masked Autoencoder Pretrained on J-MID Database
DOI: https://doi.org/10.1109/gcce62371.2024.10760886
[2024] An Evaluation Metric for Single Image-to-3D Models Based on a Class Confidence Score of Object Detection Models
DOI: https://doi.org/10.1109/gcce62371.2024.10761036
[2024] Personalized Visual Emotion Classification via In-context Learning in Multimodal LLM
DOI: https://doi.org/10.1109/gcce62371.2024.10760527
[2024] Generative Dataset Distillation Based on Large Model Pool
DOI: https://doi.org/10.1109/gcce62371.2024.10760861
[2024] MLLM-based Automatic Exploration of Editing Prompt for High Engagement Image Generation
DOI: https://doi.org/10.1109/gcce62371.2024.10760859
[2024] Snow‐ or ice‐covered road detection in winter road surface conditions using deep neural networks
DOI: https://doi.org/10.1111/mice.13233
[2024] Multimodal Shot Prediction Based on Spatial-Temporal Interaction between Players in Soccer Videos
DOI: https://doi.org/10.3390/app14114847
[2024] Multimodal Transformer Model Using Time-Series Data to Classify Winter Road Surface Conditions
DOI: https://doi.org/10.3390/s24113440
[2024] Trial Analysis of Brain Activity Information for the Presymptomatic Disease Detection of Rheumatoid Arthritis
DOI: https://doi.org/10.3390/bioengineering11060523
[2024] Algal Bed Region Segmentation Based on a ViT Adapter Using Aerial Images for Estimating CO2 Absorption Capacity
DOI: https://doi.org/10.3390/rs16101742
[2024] Analysis of Continual Learning Techniques for Image Generative Models with Learned Class Information Management
DOI: https://doi.org/10.3390/s24103087
[2024] Expert–Novice Level Classification Using Graph Convolutional Network Introducing Confidence-Aware Node-Level Attention Mechanism
DOI: https://doi.org/10.3390/s24103033
[2024] A Novel Frame-Selection Metric for Video Inpainting to Enhance Urban Feature Extraction
DOI: https://doi.org/10.3390/s24103035
[2024] Generalizing Human Motion Style Transfer Method Based on Metadata-independent Learning
DOI: https://doi.org/10.1145/3681756.3697890
[2024] 10128- COT-15 CURRENT STATUS AND CHALLENGES OF COMPREHENSIVE GENOME PROFILING FOR CNS TUMORS
DOI: https://doi.org/10.1093/noajnl/vdae173.103
[2024] 10093- MNG-4 PREDICTION MODEL FOR TUMOR GROWTH BY QUANTITATIVE IMAGE ANALYSIS FOR INCIDENTALLY DISCOVERED MENINGIOMAS
DOI: https://doi.org/10.1093/noajnl/vdae173.090
[2024] 10099- MET-10 A PROPENSITY SCORE-MATCHED ANALYSIS OF STEREOTACTIC RADIOTHERAPY FOR METASTATIC BRAIN TUMORS USING THE LEKSELL GAMMA KNIFE ICON MASK SYSTEM: A SINGLE-CENTER RETROSPECTIVE COMPARATIVE STUDY OF CASES MEETING AND NOT MEETING THE JLGK0901 CRITERIA
DOI: https://doi.org/10.1093/noajnl/vdae173.083
[2024] 10154- ACT-8 CURRENT STATUS AND PROBLEMS OF GLIOBLASTOMA TREATMENT USING THE NOVOTTF-100A SYSTEM
DOI: https://doi.org/10.1093/noajnl/vdae173.029
[2024] An Evaluation Metric for Single Image-to-3D Models Based on Object Detection Perspective
DOI: https://doi.org/10.1145/3681758.3697992
[2024] Damage‐level classification considering both correlation between image and text data and confidence of attention map
DOI: https://doi.org/10.1111/mice.13366
[2024] What to Do and Where to Go Next? Action Prediction in Soccer Using Multimodal Co-Attention Transformer
DOI: https://doi.org/10.1145/3689061.3689076
[2024] Cross-Domain Few-Shot In-Context Learning For Enhancing Traffic Sign Recognition
DOI: https://doi.org/10.1109/icip51287.2024.10647129
[2024] Zero-Shot Composed Image Retrieval Considering Query-Target Relationship Leveraging Masked Image-Text Pairs
DOI: https://doi.org/10.1109/icip51287.2024.10648023
[2024] Reinforcing Pre-Trained Models Using Counterfactual Images
DOI: https://doi.org/10.1109/icip51287.2024.10647654

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（100 件）

科研費（0 件）

所属学会・役職（0 件）