About
- I'm a DataScientist.
- I received my master degree in Computer Science at the University of Kyushu in 2023. I was very fortunate to be advised by Prof. Ryoma Bise.
- During my Bachelor and Master, I worked in the intersection of machine learning, optimization and statistics. My research centered around developing novel computationally efficient methods with theoretical guarantees for challenging machine learning problems.
- My current reseach focuses on solving the Learning from Label Proportions (LLP) problem, which is one of the promising weakly supervised problems. We developed new data augmentation technique for LLP which is designed as statistically guaranteed. I really appreciate Dr.Matsuo, Prof. Suehiro, and Prof. Bise for supporting my research.
Favorites
Python 70%
HTML & CSS 40%
Raspberry-pi 10%
Travel 80%
Papers
-
MixBag: Bag-Level Data Augumentation for Leaning from Label Proportions
Takanori Asanomi, Shinosuke Matsuo, Daiki Suehiro, Ryoma Bise.
IEEE/CVF International Conference on Computer Vision (ICCV) 2023
[code] -
Multi-Frame Attention with Feature-Level Warping for Drone Crowd Tracking
Takanori Asanomi, Kazuya Nishimura, Ryoma Bise.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023(Oral)
[paper] [code] -
Unsupervised Deep Robust Non-Rigid Alignment by Low-Rank Loss and Multi-Input Attention
Takanori Asanomi, Kazuya Nishimura, Heon Song, et al.
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022
[paper] [code]
↓ Click Here for Other Papers -
クラス比率学習におけるバッグ単位のデータ拡張
Takanori Asanomi, Shinnosuke Matsuo, Daiki Suehiro, Ryoma Bise.
画像の認識・理解シンポジウム (MIRU) 2023(Long Oral) [Acceptance rate: 16%]
[code] -
Deep Non-Rigid Registration for Noisy-and-Corrupted Images
Takanori Asanomi, Kazuya Nishimura, Heon Song, et al.
画像の認識・理解シンポジウム (MIRU) 2022(Oral)
[code] -
Self-Attentionによる大局的時間情報を考慮した複数物体トラッキング Takanori Asanomi, Kazuya Nishimura, Junya Hayashida, et al.
画像の認識・理解シンポジウム (MIRU) 2022(Oral)
[code] -
特徴量ワーピングを導入した時間情報集約によるマルチオブジェクトトラッキング Takanori Asanomi, Kazuya Nishimura, Ryoma Bise.
電子情報通信学会 パターン認識・メディア理解研究会 (PRMU) 2022
[paper] [code] -
ノイズあり複数画像の非剛体位置合わせ Takanori Asanomi, Kazuya Nishimura, Heon Song, et al.
電子情報通信学会 パターン認識・メディア理解研究会 (PRMU) 2021
[paper] [code]
Awards
- Kyushu University Student Award
Kyushu University 2023 - Young Researcher's Award
Institute of Electronics, Information and Communication Engineers 2022 [url] - Best Presenation Award
Institute of Electronics, Information and Communication Engineers 2021 - JEES・ソフトバンクAI人材育成奨学金
Softbank 2021