Hitoshi Iyatomi

Latest

• Accepted our journal paper to IEEE Access
• Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition
• Accepted our paper to PM4LRS workshop at ICLR2024
• DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention
• Accepted our journal paper to IEEE Access
• Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training
• Accepted our journal paper to Springer Applied Intelligence journal
• Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired
• Accepted our paper to IEEE HONET2022
• Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents
• Accepted our paper to ACM CIKM2022
• Ad Creative Discontinuation Prediction with Multi-Modal Multi-Task Neural Survival Networks
• Accepted our journal paper to MDPI Applied Sciences journal
• Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
• Accepted our paper to IEEE Access journal
• Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training for Semi-Supervised Text Classification
• Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
• Accepted our paper to AACL-IJCNLP2020 SRW
• AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss
• Accepted our paper to ACL2020 SRW
• Image-based Character Embedding for Arabic Document Classification
• Honorable Mention in YANS 2019
• Image Based Character Embeddings for Arabic Document Classification
• Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creative
• Accepted our paper to ACM KDD2019 Applied Data Science Track
• End-to-End Text Classification via Image-based Embedding using Character-level Networks
• Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning
• Accepted our paper to IEEE AIPR2018 Workshop