Zeman Shao
YOU?
Author Swipe
View article: IoT assisted fuzzy inference systems for intelligent 3D art design in movie animation scene design
IoT assisted fuzzy inference systems for intelligent 3D art design in movie animation scene design Open
Animation scene design is assisted by intelligent computing programs and Internet of Things (IoT) services with technological advancements. Animation scene creation, modeling, and rendering require extensive computational and conditional r…
View article: What's the Best Way to Retrieve Slides? A Comparative Study of Multimodal, Caption-Based, and Hybrid Retrieval Techniques
What's the Best Way to Retrieve Slides? A Comparative Study of Multimodal, Caption-Based, and Hybrid Retrieval Techniques Open
Slide decks, serving as digital reports that bridge the gap between presentation slides and written documents, are a prevalent medium for conveying information in both academic and corporate settings. Their multimodal nature, combining tex…
View article: SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement Open
Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g, images and tables. To handle mult…
View article: Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge
Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge Open
Longitudinal network data are essential for analyzing political, economic, and social systems and processes. In political science, these datasets are often generated through human annotation or supervised machine learning applied to evolvi…
View article: Food effects and pharmacokinetic evaluation of oral single-dose prednisone acetate and prednisolone in healthy Chinese subjects
Food effects and pharmacokinetic evaluation of oral single-dose prednisone acetate and prednisolone in healthy Chinese subjects Open
CTR20200093; registered in http://www.chinadrugtrials.org.cn/ at 11 March 2020.
View article: Cross-modal semantic segmentation for indoor environmental perception using single-chip millimeter-wave radar raw data
Cross-modal semantic segmentation for indoor environmental perception using single-chip millimeter-wave radar raw data Open
In the context of firefighting and rescue operations, a cross-modal semantic segmentation model based on a single-chip millimeter-wave (mmWave) radar for indoor environmental perception is proposed and discussed. To efficiently obtain high…
View article: Food Portion Estimation via 3D Object Scaling
Food Portion Estimation via 3D Object Scaling Open
Image-based methods to analyze food images have alleviated the user burden and biases associated with traditional methods. However, accurate portion estimation remains a major challenge due to the loss of 3D information in the 2D represent…
View article: Anything in Any Scene: Photorealistic Video Object Insertion
Anything in Any Scene: Photorealistic Video Object Insertion Open
Realistic video simulation has shown significant potential across diverse applications, from virtual reality to film production. This is particularly true for scenarios where capturing videos in real-world settings is either impractical or…
View article: An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image
An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image Open
Dietary assessment is a key contributor to monitoring health status. Existing self-report methods are tedious and time-consuming with substantial biases and errors. Image-based food portion estimation aims to estimate food energy values di…
View article: Image Based Food Energy Estimation With Depth Domain Adaptation
Image Based Food Energy Estimation With Depth Domain Adaptation Open
Assessment of dietary intake has primarily relied on self-report instruments, which are prone to measurement errors. Dietary assessment methods have increasingly incorporated technological advances particularly mobile, image based approach…
View article: Towards the Creation of a Nutrition and Food Group Based Image Database
Towards the Creation of a Nutrition and Food Group Based Image Database Open
Food classification is critical to the analysis of nutrients comprising foods reported in dietary assessment. Advances in mobile and wearable sensors, combined with new image based methods, particularly deep learning based approaches, have…
View article: An Active Image-Based Mobile Food Record Is Feasible for Capturing Eating Occasions among Infants Ages 3–12 Months Old in Hawai‘i
An Active Image-Based Mobile Food Record Is Feasible for Capturing Eating Occasions among Infants Ages 3–12 Months Old in Hawai‘i Open
The ability to comprehensively assess the diet of infants is essential for monitoring adequate growth; however, it is challenging to assess dietary intake with a high level of accuracy. Infants rely on surrogate reporting by caregivers. Th…
View article: Towards the creation of a nutrition and food group based image database
Towards the creation of a nutrition and food group based image database Open
Food classification is critical to the analysis of nutrients comprising foods reported in dietary assessment. Advances in mobile and wearable sensors, combined with new image based methods, particularly deep learning based approaches, have…
View article: An Integrated System for Mobile Image-Based Dietary Assessment
An Integrated System for Mobile Image-Based Dietary Assessment Open
Accurate assessment of dietary intake requires improved tools to overcome limitations of current methods including user burden and measurement error. Emerging technologies such as image-based approaches using advanced machine learning tech…
View article: An Integrated System for Mobile Image-Based Dietary Assessment
An Integrated System for Mobile Image-Based Dietary Assessment Open
Accurate assessment of dietary intake requires improved tools to overcome limitations of current methods including user burden and measurement error. Emerging technologies such as image-based approaches using advanced machine learning tech…
View article: Improving Dietary Assessment Via Integrated Hierarchy Food Classification
Improving Dietary Assessment Via Integrated Hierarchy Food Classification Open
Image-based dietary assessment refers to the process of determining what someone eats and how much energy and nutrients are consumed from visual data. Food classification is the first and most crucial step. Existing methods focus on improv…
View article: Towards Learning Food Portion From Monocular Images With Cross-Domain Feature Adaptation
Towards Learning Food Portion From Monocular Images With Cross-Domain Feature Adaptation Open
We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting. Specifically, we are interested in end-to-end estimation of food po…
View article: An End-to-End Food Image Analysis System
An End-to-End Food Image Analysis System Open
Modern deep learning techniques have enabled advances in image-based dietary assessment such as food recognition and food portion size estimation. Valuable information on the types of foods and the amount consumed are crucial for preventio…
View article: Multi-Task Image-Based Dietary Assessment for Food Recognition and Portion Size Estimation
Multi-Task Image-Based Dietary Assessment for Food Recognition and Portion Size Estimation Open
Deep learning based methods have achieved impressive results in many applications for image-based diet assessment such as food classification and food portion size estimation. However, existing methods only focus on one task at a time, mak…
View article: Incremental Learning In Online Scenario
Incremental Learning In Online Scenario Open
Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life app…
View article: Semi-Automatic Crowdsourcing Tool for Online Food Image Collection and Annotation
Semi-Automatic Crowdsourcing Tool for Online Food Image Collection and Annotation Open
Assessing dietary intake accurately remains an open and challenging research problem. In recent years, image-based approaches have been developed to automatically estimate food intake by capturing eat occasions with mobile devices and wear…
View article: An End-to-End Image-Based Automatic Food Energy Estimation Technique Based on Learned Energy Distribution Images: Protocol and Methodology
An End-to-End Image-Based Automatic Food Energy Estimation Technique Based on Learned Energy Distribution Images: Protocol and Methodology Open
Obtaining accurate food portion estimation automatically is challenging since the processes of food preparation and consumption impose large variations on food shapes and appearances. The aim of this paper was to estimate the food energy n…
View article: Single-View Food Portion Estimation: Learning Image-to-Energy Mappings Using Generative Adversarial Networks
Single-View Food Portion Estimation: Learning Image-to-Energy Mappings Using Generative Adversarial Networks Open
Due to the growing concern of chronic diseases and other health problems related to diet, there is a need to develop accurate methods to estimate an individual's food and energy intake. Measuring accurate dietary intake is an open research…