学術論文（Journal Papers）
2024
-
MaskDiffusion: Exploiting Pre-trained Diffusion Models for Semantic Segmentation
Yasufumi Kawano, Yoshimitsu Aoki
IEEE Access, Vo.12, pp.127283-127293, Sept 2024. -
RetinaViT: Efficient Visual Backbone for Online Video Streams
Tomoyuki Suzuki, Yoshimitsu Aoki
Sensors, Vol.24, No.17, 5457, Aug 2024. -
TAG: Guidance-free Open-Vocabulary Semantic Segmentation
Yasufumi Kawano, Yoshimitsu Aoki
IEEE Access, Vol.12, pp.88322-88331, June 2024. -
Proto-Adapter: Efficient Training-Free CLIP-Adapter for Few-Shot Image Classification
Naoki Kato, Yoshiki Nota, Yoshimitsu Aoki
Sensors, Vol.24, No.11, 3624, June 2024. -
Secrets of Event-based Optical Flow, Depth and Ego-motion Estimation by Contrast Maximization
Shintaro Shiba, Yannick Klose, Yoshimitsu Aoki, Guillermo Gallego
IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2024.3396116, May 2024. -
Synthetic Document Images with Diverse Shadows for Deep Shadow Removal Networks
Yuhi Matsuo and Yoshimitsu Aoki
Sensors, Vol.24, No.2, 654. https://doi.org/10.3390/s24020654, Jan. 2024. -
Event-based Background-Oriented Schlieren
Shiba, Shintaro; Hamann, Friedhelm; Aoki, Yoshimitsu; Gallego, Guillermo
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.46, No.4, pp.2011-2026, April 2024. -
超解像のための画像及び言語の統合特徴を利用したPerceptual Lossの改善
大谷豪，片岡裕雄，青木義満
精密工学会誌, Vol.90, No.10, pp.217-223, 2024.
国際会議論文（Conference Papers）
2024
-
Acoustic-based 3D human pose estimation robust to human position
usuke Oumi, Yuto Shibata, Go Irie, Akisato Kimura, Yoshimitsu Aoki, Mariko Isogawa
British Machine Vision Conference 2024 (BMVC2024), to appear, 2024. (acceptance rate: 25.88%) -
Unsupervised Metric Learning for Expressing Color and Shape Information to Uncover Abstract Connections in Image Datasets
Shun Obikane, Haruna Tagawa, Yoshimitsu Aoki
ICPR2024, Kolkata, Dec 2024. -
Rethinking Image Super Resolution from Training Data Perspectives
Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue , Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki
ECCV2024, No.9, Milano, Oct 2024. -
Data Collection-free Masked Video Modeling
Yuchi Ishikawa, Masayoshi Kondo, Yoshimitsu Aoki
ECCV2024, Milano, No.199, Oct 2024. -
Predicting Grade of Execution in Figure Skating Jump: An Analysis of Ladies’ Double Axel Jumps at World Championships
Seiji Hirosawa, Yoshimitsu Aoki
The 14th World Congress of Performance Analysis of Sport, England, Aug 2024. -
Perspective Cue Training Framework for Multi-Camera BEV Segmentation
Haruya Ishikawa, Takumi Iida, Yoshinori Konishi, Yoshimitsu Aoki
IROS2024, Abu Dhabi, Oct. 2024. (Accepted as Oral) -
Guided by the Way: The Role of On-the-route Objects and Scene Text in Enhancing Outdoor Navigation
Yanjun Sun, Yue Qiu, Yoshimitsu Aoki, Hirokatsu Kataoka
ICRA2024, Yokohama, June 2024. -
3D Human Scan With A Moving Event Camera
Kai Kohyama, Shintaro Shiba, Yoshimitsu Aoki
Computer Vision for Mixed Reality workshop[CV4MR] in CVPR2024, pp.5586-5596, June 2024.
シンポジウム・研究会（Symposium）
2024
論文はありません
2015以前はこちら