A5030519168- Multimodal Machine Learning Applications
- Advanced Image and Video Retrieval Techniques
- Topic Modeling
- Human Pose and Action Recognition
- Domain Adaptation and Few-Shot Learning
- Context-Aware Activity Recognition Systems
- Human Mobility and Location-Based Analysis
- Cardiac Health and Mental Health
- Speech and dialogue systems
- Video Analysis and Summarization
- Recommender Systems and Techniques
- Mobile Health and mHealth Applications
- Heart Failure Treatment and Management
- Geographic Information Systems Studies
- Underwater Vehicles and Communication Systems
- Physical Activity and Health
- Cardiovascular and exercise physiology
- Digital Storytelling and Education
- Image Retrieval and Classification Techniques
- Augmented Reality Applications
- Expert finding and Q&A systems
- Gaze Tracking and Assistive Technology
- Identity, Memory, and Therapy
Dublin City University
2020-2024
Developing interactive lifelog retrieval systems is a growing research area. There are many international competitions for that encourage researchers to build effective can address the multimodal challenge of lifelogs. The Lifelog Search Challenge (LSC) was first organised in 2018 and currently only benchmarking evaluation systems. Participating should have an accurate search engine user-friendly interface help users retrieve relevant content. In this paper, we upgrade our previous MyScéal,...
The Lifelog Search Challenge (LSC) is an interactive benchmarking evaluation workshop for lifelog retrieval systems. challenge was first organised in 2018 aiming to find the system that can quickly retrieve relevant images a given semantic query. This paper provides analysis of performance all 17 systems participating 4th LSC held at 2021 Annual ACM International Conference on Multimedia Retrieval (ICMR). LSC'21 largest effort comparing different approaches seen thus far. Findings from...
Lifelogging is an activity of recording all events that happen in the daily life individual. The can contain images, audio, health index, etc which are collected through various devices such as wearable cameras, smartwatches, and other digital services. Exploiting lifelog data bring significant benefits for lifeloggers from creating personalized healthcare plans to retrieving past. In recent years, there has been a growing development interactive retrieval systems, competitors at annual...
The advent of large language models (LLMs) has energised research in Question-Answering (QA) tasks, enabling responses across varied domains like economics and mathematics. Despite their capabilities, LLMs often lack explainability due to complex parameter embeddings. Additionally, integrating multimedia data into QA systems introduces challenges processing interpreting diverse types such as text, images, audio, video. This necessitates sophisticated algorithms for accurate information...
Retrieval is a fundamental challenge within the research community of lifelog and Lifelog Search Challenge (LSC) has been an important annual benchmarking activity for interactive retrieval systems since 2018. This paper proposes MyEachtra (/mai-AK-truh/), system designed upcoming LSC'23 workshop. Improved upon MyScéal, which was top performing from LSC'20 to LSC'22, includes modifications address challenges non-owner user understanding contexts open-ended question answering. Specifically,...
Building an interactive retrieval system for lifelogging contains many challenges due to massive multi-modal personal data besides the requirement of accuracy and rapid response such a tool. The Lifelog Search Challenge (LSC) is international lifelog competition that inspires researchers develop their systems cope with evaluates effectiveness solutions. In this paper, we upgrade our previous Myscéal present 2.0 LSC'21 improved features inspired by novice users experiments. experiments show...
The Lifelog Search Challenge (LSC), is an annual comparative bench-marking activity for comparing approaches to interactive retrieval from multi-modal lifelogs. Being search challenge, issues such as accuracy, speed and usability of inter-faces are key challenges that must be addressed by every participant. In this paper, we introduce Myscéal, lifelog engine designed support novice users retrieve items interest a large multimodal lifelog. Additionally, also anew similarity measure called...
Your whole life in your pocket. That is the premise of lifelogging, a technology that captures and stores every moment digital form. Built on top MyEachtra lifelog question-answering pipeline, MyEachtraX mobile-based application addresses overlook mobile platforms area. Furthermore, leveraging latest advancements natural language processing, such as Large Language Models (LLMs) Multimodal (MLLMs), system enhances query-parsing, post-processing, processes retrieval. Official questions from...
In this paper, we attempt to fine-tune the CLIP (Contrastive Language-Image Pre-Training) model on Lifelog Question Answering dataset (LLQA) investigate retrieval performance of fine-tuned over zero-shot baseline model. We train adopting a weight space ensembling approach using modified loss function take into account differences in our when compared with was originally pretrained on. further evaluate visual as well multimodal queries multiple tasks, demonstrating improved
Globally, heart failure (HF) affects more than 64 million people, and attempts to reduce its social economic burden are a public health priority. Interventions support people with HF self-manage have been shown hospitalizations, improve quality of life, mortality rates. Understanding how is imperative future interventions; however, most approaches date, used self-report methods achieve this. Wearable cameras provide unique tool understand the lived experiences daily activities they...
Personal data includes the digital footprints that we leave behind as part of our everyday activities, both online and offline in real world. It collect ourselves, such from wearables, well collected by others about behaviour activities. Sometimes are able to use personal ourselves collect, order examine some parts lives but for most part, is leveraged third parties including internet companies, services like targeted advertising recommendations. Lifelogging a form extreme gathering this...
<sec> <title>BACKGROUND</title> Globally, heart failure (HF) affects more than 64 million people, and attempts to reduce its social economic burden are a public health priority. Interventions support people with HF self-manage have been shown hospitalizations, improve quality of life, mortality rates. Understanding how is imperative future interventions; however, most approaches date, used self-report methods achieve this. Wearable cameras provide unique tool understand the lived experiences...