A5114804291- Emotion and Mood Recognition
- Mental Health Research Topics
- Cell Image Analysis Techniques
- AI in cancer detection
- Functional Brain Connectivity Studies
- Mental Health via Writing
- Topic Modeling
- Speech Recognition and Synthesis
- Sentiment Analysis and Opinion Mining
- CCD and CMOS Imaging Sensors
- Digital Mental Health Interventions
- Advanced Memory and Neural Computing
- Digital Imaging for Blood Diseases
The University of Tokyo
2023-2024
University of Augsburg
2023
Speech is the fundamental mode of human communication, and its synthesis has long been a core priority in human–computer interaction research. In recent years, machines have managed to master art generating speech that understandable by humans. However, linguistic content an utterance encompasses only part meaning. Affect, or expressivity, capacity turn into medium capable conveying intimate thoughts, feelings, emotions—aspects are essential for engaging naturalistic interpersonal...
Translating mental health recognition from clinical research into real-world application requires extensive data, yet existing emotion datasets are impoverished in terms of daily monitoring, especially when aiming for self-reported anxiety and depression recognition. We introduce the Japanese Daily Speech Dataset (JDSD), a large in-the-wild speech dataset consisting 20,827 samples 342 speakers 54 hours total duration. The data is annotated on Depression Anxiety Mood Scale (DAMS) – 9 emotions...
The rapid advancement of wearable sensors and machine learning technologies has opened new avenues for mental health monitoring. Despite these advancements, conventional approaches often fail to provide an accurate personalised understanding individual's multi-dimensional emotional state. This paper introduces a novel approach enhanced daily prediction, focusing on nine distinct states. Our method employs crossmodal transformer architecture that effectively integrates ZCM (Zero Crossing...
<sec> <title>BACKGROUND</title> The field of mental health technology presently has significant gaps that need addressing, particularly in the domain daily monitoring and personalized assessments. Current noninvasive devices such as wristbands smartphones are capable collecting a wide range data, which not yet been fully used for monitoring. </sec> <title>OBJECTIVE</title> This study aims to introduce novel dataset new macro-micro framework. framework is designed use multimodal multitask...
Background The field of mental health technology presently has significant gaps that need addressing, particularly in the domain daily monitoring and personalized assessments. Current noninvasive devices such as wristbands smartphones are capable collecting a wide range data, which not yet been fully used for monitoring. Objective This study aims to introduce novel dataset new macro-micro framework. framework is designed use multimodal multitask learning strategies improved personalization...
It is clinically crucial and potentially very beneficial to be able analyze model directly the spatial distributions of cells in histopathology whole slide images (WSI). However, most existing WSI datasets lack cell-level annotations, owing extremely high cost over giga-pixel images. Thus, it remains an open question whether deep learning models can effectively WSIs from semantic aspect cell distributions. In this work, we construct a large-scale dataset with more than 5 billion termed...
Histopathology plays a critical role in medical diagnostics, with whole slide images (WSIs) offering valuable insights that directly influence clinical decision-making. However, the large size and complexity of WSIs may pose significant challenges for deep learning models, both computational efficiency effective representation learning. In this work, we introduce Pixel-Mamba, novel architecture designed to efficiently handle gigapixel WSIs. Pixel-Mamba leverages Mamba module, state-space...