過去のお知らせ
-
コンシューマエレクトロニクス系の国際会議ICCT-Pacific2026に当研究室から2件の論文が採択されました！
[1] T. Seino, N. Saito, T. Ogawa, S. Asamizu, M. Haseyama, “Unified Scene Graph Forecasting Considering Node Birth and Disappearance”
[2] R. Takahashi, N. Saito, K. Maeda, T. Yoshioka, T. Konno, T. Ogawa, M. Haseyama, “LLM-in-the-Loop Descriptor Prompt Refinement for Dialogue-Based Big Five Personality Recognition”
[2]の論文は、富士通株式会社との共同研究成果です。
-
継続学習によるパーソナライズド画像生成に関する以下の論文が国際論文誌IEEE Access (IF:3.6)に採択されました！
Haruka Matsuda, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama “Deep Generative Replay-based Personalization with Conditional Latent Attenmtion For Diffusion Models” (Accepted)
-
Objectness similarity: Capturing object-level fidelity in 3D scene evaluation
Yuiko Uchida, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
IEEE/CVF International Conference on Computer Vision (ICCV 2025) Workshops
-
Task-specific generative dataset distillation with difficulty-guided sampling
Mingzhuo Li, Guang Li, Jiafeng Mao, Linfeng Ye, Takahiro Ogawa, Miki Haseyama
IEEE/CVF International Conference on Computer Vision (ICCV 2025) Workshops
-
Stream voice diffusion: real-time image generation from speech
Hideo Kodama, Masaki Yoshida, Ren Togo, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Enhancing medical dataset distillation based on classifier-guided diffusion model
Shuailin Du, Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Similar image generation via human-like iterative prompt refinement with multimodal large language model
Taiyo Sato, Keisuke Maeda, Naoki Saito, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Patch-wise extension of EVA score for semi-supervised lung field segmentation
Taiyo Ikeido, Ren Togo, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Graph-based pass receiver prediction in soccer with consideration of passer’s body orientation
Riku Yoshida, Ryota Goka, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Foul severity classification from multi-view soccer videos with attention and class characteristics
Kotone Mutsuna, Ryota Goka, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Enhancing image classifier robustness via prompt-based counterfactual data-augmentation with intermediate transitions
Tomoya Mitsui, Ren Togo, Naoki Saito, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
An investigation of data augmentation for image classification network based on graph convolution
Ryusei Mikami, Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Rethinking continual learning with pre-trained models: knowledge-preserving approach
Makoto Misaizu, Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa, Rafal Rzepka, Toshihiko Itoh, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
SSM-based sequential recommendation considering short-term dependencies of time and adjacency
Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Image-guided 360-degree scene generation with structural and visual consistency
Yuki Katayama, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
2025 IEEE 14th Global Conference on Consumer Electronics (GCCE 2025)
-
Diversity-driven generative dataset distillation based on diffusion model with self-adaptive memory
Mingzhuo Li, Guang Li, Jiafeng Mao, Takahiro Ogawa, Miki Haseyama
2025 IEEE International Conference on Image Processing (ICIP 2025)
-
Out-of-distribution sample selection generated by diffusion model toward model generalization
Kaede Hayakawa, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama
2025 IEEE International Conference on Image Processing (ICIP 2025)
-
Enhancing adversarial robustness of foundation models without data centralization
Koshiro Toishi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama
2025 IEEE International Conference on Image Processing (ICIP 2025)
-
文字領域検出および LMM によるスキャン図面の数値識別
福井 千菜美, 王 暢, 蘭 子文, 李 広, 田村 彰浩, 花田 剛志, 前田 圭介, 高橋 翔, 小川 貴弘, 長谷山 美紀
AI・データサイエンス論文集
-
Robust adversarial defense against multiple attacks without data centralization
Koshiro Toishi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama
第28回 画像の認識・理解シンポジウム (MIRU2025)