フォロー
Shunsuke KITADA
Shunsuke KITADA
LY Corp., Image & Video AI Dept., Generation team.
確認したメール アドレス: lycorp.co.jp - ホームページ
タイトル
引用先
引用先
Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
S Kitada, H Iyatomi
IEEE Access 9, 92974 - 92985, 2021
282021
Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning
S Kitada, H Iyatomi
arXiv preprint arXiv:1809.02568, 2018
242018
Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creative
S Kitada, H Iyatomi, Y Seki
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019
132019
Making attention mechanisms more robust and interpretable with virtual adversarial training
S Kitada, H Iyatomi
Applied Intelligence 53 (12), 15802-15817, 2023
112023
End-to-end text classification via image-based embedding using character-level networks
S Kitada, R Kotani, H Iyatomi
IEEE Applied Imagery Pattern Recognition (AIPR) Workshop, 1-4, 2018
72018
Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
T Aoki, S Kitada, H Iyatomi
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the …, 2020
42020
AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss
M Daif, S Kitada, H Iyatomi
Proceedings of the 58th Annual Meeting of the Association for Computational …, 2020
32020
Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents
T Nakagawa, S Kitada, H Iyatomi
Proceedings of the 31st ACM International Conference on Information …, 2022
22022
DM S : Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention
S Kitada, Y Iwazaki, R Togashi, H Iyatomi
IEEE Access 10, 120023 - 120034, 2022
12022
Ad Creative Discontinuation Prediction with Multi-Modal Multi-Task Neural Survival Networks
S Kitada, H Iyatomi, Y Seki
Applied Sciences 12 (7), 3594, 2022
12022
VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction
J Zhang, R Yoshihashi, S Kitada, A Osanai, Y Nakashima
arXiv preprint arXiv:2412.04237, 2024
2024
Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition
S Nemoto, S Kitada, H Iyatomi
arXiv preprint arXiv:2401.11431, 2024
2024
Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Model
S Iwai, A Osanai, S Kitada, S Omachi
European Conference on Computer Vision, 92-110, 2024
2024
Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives
S Kitada
arXiv preprint arXiv:2303.14116, 2023
2023
Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired
K Ohata, S Kitada, H Iyatomi
IEEE 19th International Conference on Smart Communities: Improving Quality …, 2022
2022
Extended datasets from MM-IMDB and Ads-Parallelity dataset with the features from Google Cloud Vision API
S Kitada, Y Iwazaki, R Togashi, H Iyatomi
(No Title), 2022
2022
From WRIME to WRIME-TC: Enhancing Emotional Analysis of Writers and Readers with Temporal Context
T Nakagawa, S Kitada, T Kajiwara, H Iyatomi
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–17