Home
Projects
Research Topics
People
Publications
Contact
Light
Dark
Automatic
English
English
日本語
Yuta Nakashima
Associate Professor
Institute for Datability Science
Osaka University
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
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
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
Cite
×