Contact
- email: nagahara@ids.
- webpage: https://researchmap.jp/read0054705
Please add osaka-u.ac.jp to complete email address
Interests
- Computational Photography
- Computer Vision
- Sensing
Latest
- Learning bottleneck concepts in image classification
- Real-time estimation of the remaining surgery duration for cataract surgery using deep convolutional neural networks and long short-term memory
- Automated grading system of retinal arterio-venous crossing patterns: A deep learning approach replicating ophthalmologist’s diagnostic process of arteriolosclerosis
- Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization
- Cross-language font style transfer
- Development of a vertex finding algorithm using Recurrent Neural Network
- Human-Imperceptible Identification With Learnable Lensless Imaging
- Inverse Rendering of Translucent Objects using Physical and Neural Renderers
- Computational Optical Imaging for Endoscopic Surgery
- Acquiring a Dynamic Light Field Through a Single-Shot Coded Image
- Information Extraction from Public Meeting Articles
- Corpus Construction for Historical Newspapers: A Case Study on Public Meeting Corpus Construction Using OCR Error Correction
- Emotional Intensity Estimation based on Writer’s Personality
- Match them up: visually explainable few-shot image classification
- Multi-label disengagement and behavior prediction in online learning
- GCNBoost: Artwork Classificationby Label Propagation Through a Knowledge Graph
- SCOUTER: Slot attention-based classifier for explainable image recognition
- Built year prediction from Buddha face with heterogeneous labels
- Learners' efficiency prediction using facial behavior analysis
- MTUNet: Few-shot image classification with visual explanations
- WRIME: A new dataset for emotional intensity estimation with subjective and objective annotations
- Noisy-LSTM: Improving temporal awareness for video semantic segmentation
- CFA Handling and Quality Analysis for Compressive Light Field Camera
- IDSOU at WNUT-2020 Task 2: Identification of informative COVID-19 English tweets
- Diagnostic performance for pulmonary adenocarcinoma on CT: comparison of radiologists with and without three-dimensional convolutional neural network
- Improving topic modeling through homophily for legal documents
- Acquiring dynamic light fields through coded aperture camera
- YOLO in the Dark - Domain adaptation method for merging multiple models -
- MLPhys: Foundation of Machine Learning Physics
- CREST 3D Image Recognition AI for Cancer Diagnosis Support
- In Silico Optical Analysis of Dental Esthetic Restorations
- 全組織細胞イメージング／分子病態解析
- AI Hospital
- Development of Multilingual Neural Machine Translation System for Comparison and Statistics Analysis of Multi-Country Legislation
- Study on Analysis and Genealogy of Face Style of Buddha Images by Artificial Intelligence
- Detecting learner drowsiness based on facial expressions and head movements in online courses
- 3D Image Reconstruction from Multi-focus Microscopic Images
- 5D Light Field Synthesis from a Monocular Video
- Action recognition from a single coded image
- IterNet: retinal image segmentation utilizing structural redundancy in vessel networks
- Joint learning of vessel segmentation and artery/vein classification with post-processing
- Public meeting corpus construction and content delivery
- Reflectance and Shape Estimation with a Light Field Camera Under Natural Illumination
- Legal information as a complex network: Improving topic modeling through homophily
- Deep compressive sensing for visual privacy protection in flatcam imaging
- A 3-D Display Pipeline from Coded-Aperture Camera to Tensor Light-Field Display Through CNN
- Multimodal learning analytics: Society 5.0 project in Japan
- Fall detection using optical level anonymous image sensing system
- Buda.art: A multimodal content-based analysis and retrieval system for Buddha statues
- Facial expression recognition with skip-connection to leverage low-level features
- High-Speed Imaging Using CMOS Image Sensor With Quasi Pixel-Wise Exposure
- Space-time-brightness sampling using an adaptive pixel-wise coded exposure
- Society 5.0 Projects
- Australian History and AI
- Designing coded aperture camera based on PCA and NMF for light field acquisition
- PCA-coded aperture for light field photography
- Joint optimization for compressive video sensing and reconstruction under hardware constraints
- Learning to capture light fields through a coded aperture camera
- Adapting local features for face detection in thermal image
- Sophistication of Machine Learning-Based Chest CT Image Diagnosis
- Adaptive background model registration for moving cameras
- Hyperspectral imaging using flickerless active LED illumination
- High-speed imaging using CMOS image sensor with quasi pixel-wise exposure
- Dynamic photometric stereo method using multi-tap CMOS image sensor