Contact
- email: n-yuta@ids.
- webpage: https://www.n-yuta.jp/
Please add osaka-u.ac.jp to complete email address
Interests
- Computer Vision
- Natural Language Processing
- Pattern Recognition
- Machine Learning
Latest
- Information Extraction from Public Meeting Articles
- AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval
- Gender and Racial Bias in Visual Question Answering Datasets
- Quantifying Societal Bias Amplification in Image Captioning
- Anonymous identity sampling and reusable synthesis for sensitive face camouflage
- Depthwise spatio-temporal STFT convolutional neural networks for human action recognition
- Integration of gesture generation system using gesture library with DIY robot design kit
- The semantic typology of visually grounded paraphrases
- GCNBoost: Artwork Classificationby Label Propagation Through a Knowledge Graph
- Image Retrieval by Hierarchy-aware Deep Hashing Based on Multi-task Learning
- SCOUTER: Slot attention-based classifier for explainable image recognition
- Transferring domain-agnostic knowledge in video question answering
- Built year prediction from Buddha face with heterogeneous labels
- Explain me the painting: Multi-topic knowledgeable art description generation
- Learners' efficiency prediction using facial behavior analysis
- Museum Experience into a Souvenir: Generating Memorable Postcards from Guide Device Behavior Log
- PoseRN: A 2D pose refinement network for bias-free multi-view 3D human pose estimation
- Attending self-attention: A case study of visually grounded supervision in vision-and-language transformers
- A comparative study of language Transformers for video question answering
- 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
- Generation and detection of media clones
- Preventing fake information generation against media clone attacks
- The laughing machine: Predicting humor in video
- Cross-lingual visual grounding
- IDSOU at WNUT-2020 Task 2: Identification of informative COVID-19 English tweets
- Improving topic modeling through homophily for legal documents
- Visually grounded paraphrase identification via gating and phrase localization
- Demographic influences on contemporary art with unsupervised style embeddings
- Knowledge-based video question answering with unsupervised scene descriptions
- Knowledge VQA
- Australian History in Newspaper and AI
- MLPhys: Foundation of Machine Learning Physics
- Society 5.0 Projects
- AI Hospital
- Law and AI
- Buddha Face and AI
- Yoga-82: a new dataset for fine-grained classification of human poses
- KnowIT VQA: Answering knowledge-based questions about videos
- 3D Image Reconstruction from Multi-focus Microscopic Images
- BERT representations for video question answering
- ContextNet: representation and exploration for painting classification and retrieval in context
- IterNet: retinal image segmentation utilizing structural redundancy in vessel networks
- Joint learning of vessel segmentation and artery/vein classification with post-processing
- Speech-driven face reenactment for a video sequence
- Uncovering hidden challenges in query-based video moment retrieval
- Public meeting corpus construction and content delivery
- Human shape reconstruction with loose clothes from partially observed data by pose specific deformation
- Legal information as a complex network: Improving topic modeling through homophily
- Multimodal learning analytics: Society 5.0 project in Japan
- Buda.art: A multimodal content-based analysis and retrieval system for Buddha statues
- Context-aware embeddings for automatic art analysis
- Facial expression recognition with skip-connection to leverage low-level features
- Rethinking the evaluation of video summaries
- Video meets knowledge in visual question answering
- Representing a partially observed non-rigid 3D human using eigen-texture and eigen-deformation
- Finding important people in a video using deep neural networks with conditional random fields
- Iterative applications of image completion with CNN-based failure detection
- Summarization of user-generated sports video by using deep action recognition features
- iParaphrasing: Extracting visually grounded paraphrases via an image
- Visually grounded paraphrase extraction
- Augmented reality marker hiding with texture deformation
- Novel view synthesis with light-weight view-dependent texture mapping for a stereoscopic HMD
- Video summarization using textual descriptions for authoring video blogs
- Fine-grained video retrieval for multi-clip video
- Increasing pose comprehension through augmented reality reenactment
- Realtime novel view synthesis with eigen-texture regression
- ReMagicMirror: Action learning using human reenactment with the mirror metaphor
- Unsupervised Video Summarization using Deep Video Features
- Video question answering to find a desired video eegment