The following paper was accepted for the PRMU Monthly Best Presentation Award
SVGEditBench V2: テキストプロンプトに基づくSVG編集モデルの評価ベンチマーク, K.Nishina, Y.Matsui
SVGEditBench V2: テキストプロンプトに基づくSVG編集モデルの評価ベンチマーク, K.Nishina, Y.Matsui
News
- MOVIE MAP
- FOOD LOG
Track and analyze your daily food choices with our Food Log project!
- MANGA PROJECT
- LECTURES
Links for lectures.
- IEEE Student Branch
PRMU Monthly Best Presentation Award
2025/03
Accepted for IEEE MultiMedia
2025/03
The following paper was accepted for Large Multimodal Models Special Issue of IEEE MultiMedia.
MangaUB: A Manga Understanding Benchmark for Large Multimodal Models, H.Ikuta, L.Woehler, K.Aizawa
MangaUB: A Manga Understanding Benchmark for Large Multimodal Models, H.Ikuta, L.Woehler, K.Aizawa
Accepted for ACM CHI2025 LBW
2025/02
The following paper was accepted for CHI2025 Late Breaking Work. Leslie Wöhler, Takubon Son, Satoshi Ikehata, Kiyoharu Aizawa, Analyzing Viewer Perception of Generative AI-Based Editing in 360° Images Across Display Modalities.
Accepted for CVPR
2025/02
The following paper was accepted for CVPR2025.
Yusuke Matsui, "LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table"
Yusuke Matsui, "LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table"
Accepted for NAACL
2025/01
The following paper was accepted for Nations of the Americas Chapter of the Association for Computational Linguistics.
JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation, Shota Onohara, Atsuyuki Miyai, Yuki Imajuku, Kazuki Egashira, Jeonghun Baek, Xiang Yue, Graham Neubig, Kiyoharu Aizawa.
JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation, Shota Onohara, Atsuyuki Miyai, Yuki Imajuku, Kazuki Egashira, Jeonghun Baek, Xiang Yue, Graham Neubig, Kiyoharu Aizawa.
Accepted for IJCV
2025/01
The following paper was accepted for International Journal of Computer Vision.
GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection, Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa
GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection, Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa
MMM 2025 Keynote Lecture
2025/01
At Multimedia Modeling 2025, Professor Aizawa presented a keynote lecture titled "Manga109 and MangaUB: How Far Can Large Multimodal Models (LMMs) Go in Understanding Manga?"