Digital Commons Network^™

Functional Mobility And Pain Are Improved For 6 Years After Adolescent Bariatric Surgery, Neil Thivalapill, Todd M Jenkins, Thomas H Inge, Changchun Xie, Anita P Courcoulas, Carroll M Harmon, Michael A Helmrath, Stephanie Sisley, Marc P Michalsky, Justin R Ryder, Teen‐Longitudinal Assessment Of Bariatric Surgery (Teen‐Labs) Consortium

Faculty, Staff and Students Publications

Objective: The long-term durability of improvements in functional mobility and musculoskeletal pain for adolescents after metabolic and bariatric surgery (MBS) is unknown.

Methods: We used the Teen-Longitudinal Assessment of Bariatric Surgery (Teen-LABS) study to determine the change in mobility and pain among adolescents who underwent MBS. From standardized 400-m walk tests, we analyzed walk time, heart rate (HR) parameters, and musculoskeletal pain.

Results: The mean walk time improved from 383 s (95% CI: 368-399) prior to surgery to 351 s (95% CI: 330-372) by 6 years. The mean resting HR was 90 beats per minute (bpm; 95% CI: 87-93) preoperatively …

Stress, Employment Changes, And Psychological Distress Among Caregivers Of Patients With Head And Neck Cancer, Lama Abdurrahman, Vlad C Sandulache, Cielito Reyes-Gibby, Erich M Sturgis, Pavan Jhaveri, Hoda Badr

Faculty, Staff and Students Publications

Importance: Patients undergoing external beam radiation therapy (EBRT) for head and neck cancer (HNC) often experience adverse effects that require substantial caregiving. The burdens of caregiving can impact caregiver employment and mental health over time, yet this topic remains underexplored.

Objective: To examine the associations between caregiving for patients with HNC who undergo EBRT and caregiver stress, employment status, and psychological distress.

Design, setting, and participants: This was a secondary analysis of data from a longitudinal survey study that surveyed caregivers at baseline (ie, at initiation of EBRT) and at 4-month and 12-month follow-ups. The study was conducted at 2 …

The Aging Ovary Stands On The Shoulders Of Giant Multinucleated Cells, Avery A Ahmed, Stephanie A Pangas

Faculty, Staff and Students Publications

Reproductive aging is associated with declining fertility and increasing inflammation, though these events are not well understood. An exciting new study in PLOS Biology utilizes cutting-edge technologies to characterize the role of multinucleated giant cells in ovarian aging.

Impact Of Length Of Stay On Diagnostic Yield In The Epilepsy Monitoring Unit: A Multi-Center Retrospective 12-Year Veterans Health Administration Study, Maximillian S Feygin, Autumn Smith, Sruthi Gopinath Karicheri, Khadar Haroun, Omar Khan, Maria R Lopez, Stephan Eisenschenk, John Jones, Stephanie Reeder, Alan R Towne, Christopher Ransom, Karen Medin, James Chen, Tung Tran, Nina I Garga, Noemi Rincon-Flores, Marissa Kellogg, Steven Tobochnik, Zulfi Haneef

Faculty, Staff and Students Publications

Objective: Epilepsy Monitoring Units (EMUs) in Veterans Health Administration (VHA) Epilepsy Centers of Excellence (ECoE) are critical for the diagnosis and management of seizure disorders. Whether a shorter length of stay (LOS) in the EMU due to scheduling impacts diagnostic yield is unclear.

Methods: Data from 7074 EMU visits across 15 VHA EMUs (2012-2024) were analyzed. Based on usual admission schedules, EMUs were divided into "fixed" (typically Monday-Friday) or "flexible" subgroups. Diagnostic outcomes were classified as epileptic seizures (ES), psychogenic non-epileptic seizures (PNES), other non-epileptic events, and inconclusive. Diagnostic rates were compared between fixed and flexible sites using cumulative distribution …

"Touch&Play" Wood Typification By The Masspec Pen, Adriano Reis, Caroline Pais Carvalho, Iasmim Lopes De Lima, Felipe R P Mansoldo, Alane Beatriz Vermelho, Rosineide Costa Simas, Livia S Eberlin, Marcos N Eberlin

Faculty, Staff and Students Publications

We have investigated the ability of a MasSpec Pen (MSPen) "three-in-one" (extraction, transfer, and ionization) device coupled to a mass spectrometer to provide instantaneous chemical profiles that could promptly characterize wood samples from the mahogany (Meliaceae) family. For that, we selected a set of five representative wood species, that is, Brazilian mahogany (Swietenia macrophylla, also known as Honduran mahogany), two African mahoganies (Khaya ivorensis and Khaya senegalensis), and two "nongenuine" ("fake") mahogany woods: cedar (Cedrela odorata) and andiroba (Carapa guianensis). By simply touching the superficially polished wood surface and after 3 s of automatic extraction, profiles of highly characteristic markers …

Corrigendum To “Neuro-Ophthalmic Complications Following Eighth Cranial Nerve Microvascular Decompression” [Am J Ophthalmol Case Rep (2025) Ecollection 1–3 102258], Stanley M Saju, Patrick J Hunt, Pamela Davila-Siliezar, Noor Laylani, Andrew G Lee

Faculty, Staff and Students Publications

This corrects the article "Neuro-ophthalmic complications following eighth cranial nerve microvascularx decompression" in volume 37, 102258.

The Efficacy Of Complementary And Alternative Medicines Utilized In Cosmetic And Surgical Dermatology: A Comprehensive Review, Promise Ufomadu, Bartley Joseph Gill, Theodore Rosen, Ikue Shmizu, Ida Orengo

Faculty, Staff and Students Publications

Background: Lately, there has been a growing demand for the utilization of complementary and alternative medicines (CAMs) with dermatological applications. This is true despite limited RCT-level studies on such agents. This presents a barrier for dermatologists and fellow clinicians in counseling patients who may be using or are tempted to use these CAM modalities. This review highlights CAM agents used by patients for applications in cosmetic and surgical dermatology, exploring their efficacy and toxicity profiles.

Methods: A comprehensive review was conducted on the effectiveness of several CAMs utilized in cosmetic and surgical dermatology by patients. A literature search was performed …

Characteristic Profiling Of Cho-Cell Expressed Mers-Cov Rbd-Fc, Mashal M Almutairi, Yi-Lin Chen, Jungsoon Lee, Zhuyun Liu, Ulrich Strych, Peter J Hotez, Maria Elena Bottazzi, Wen-Hsiang Chen

Faculty, Staff and Students Publications

The ongoing circulation of the Middle East Respiratory Syndrome coronavirus (MERS-CoV) in camels across Asia, the Middle East, and Africa, along with its occasional transmission to humans, demonstrates a need for a MERS vaccine. Previously, we have reported a receptor binding domain (RBD) of MERS-CoV fused with human Fc as a promising vaccine antigen (MERS-CoV RBD-Fc). We generated a stable recombinant CHO cell line expressing such a protein and developed a basic production process suitable for future technological transfer to pilot-scale manufacture. In this study, we employed various in-house analytical assays to examine the characteristics of purified RBD-Fc protein and …

An Innovative Interprofessional Mock Trial Experience: Collaboration Between Emergency Medicine Residency Program And Law School As A Tool To Demonstrate Medical Malpractice Litigation, Adaeze Stephanie Onyechi, Cedric Dark, Vidya Eswaran

Faculty, Staff and Students Publications

Background: Due to the nature of the job and healthcare climate, emergency medicine physicians are constantly at risk for malpractice claims. Despite this, there is a gap in education around malpractice litigation. Given the considerable number of curricular topics residency programs must cover in conjunction with the volume of clinical hours residents work, we found that there is a need for an educational experience that is thorough yet compact enough to cause minimal disruption for educators and trainees. We created an easily reproducible educational session featuring collaboration between an emergency medicine residency program and a law school that covers medical …

Protein Biomarkers Of Interstitial Lung Abnormalities In Relatives Of Patients With Pulmonary Fibrosis, Jonathan A Rose, Mark P Steele, Esteban J Kosak Lopez, Gisli Thor Axelsson, Andrea G Galecio Chao, Alan Waich, Katie Regan, Swati Gulati, Anthony H Maeda, Sharmin Sultana, Claire Cutting, Ann-Marcia C Tukpah, Andrew J Synn, Mary B Rice, Hilary J Goldberg, Joyce S Lee, David A Lynch, Rachel K Putman, Hiroto Hatabu, Benjamin A Raby, David A Schwartz, Ivan O Rosas, Gary M Hunninghake

Faculty, Staff and Students Publications

Rationale: First-degree relatives of patients with pulmonary fibrosis (referred to here as relatives) are at high risk for interstitial lung abnormalities (ILA), highlighting the need for biomarkers for risk prediction. We aimed to identify blood proteins associated with and predictive of ILA among relatives of patients with pulmonary fibrosis.

Methods: Relatives enrolled in two independent cohorts had protein levels measured using an aptamer-based proteomic platform. ILA were assessed with computed tomography scans as per Fleischner Society recommendations. Protein associations with ILA were assessed using regression. Significant proteins were used with clinical variables to detect ILA.

Results: Of 237 relatives from …

Targeting S1pr2 In Sepsis, One Fragmented Mitochondrion At A Time, Chao He, Jennifer L Larson-Casey

Faculty, Staff and Students Publications

No abstract provided.

Aged Regulatory T Cells Fail To Control Autoimmune Lacrimal Gland Pathogenic Cd4+ T Cells, Kaitlin K Scholand, Laura Schaefer, Gowthaman Govindarajan, Zhiyuan Yu, Jeremias G Galletti, Cintia S De Paiva

Faculty, Staff and Students Publications

CD25KO mice are a model of Sjögren disease. CD25KO mice have severe inflammation and infiltrating lymphocytes to the lacrimal glands (LG). Whether the pathogenicity of CD25KO CD4+ T cells can be controlled in vivo by Tregs is unknown. Eight-week-old B6 and CD25KO mice LGs were submitted for RNA bulk sequencing. A total of 3481 genes were differentially expressed in CD25KO LG compared to B6. Tear washing analysis identified CD25KO mice had elevated protein levels of TNF, IFN-γ, and CCL5 and decreased protein levels of IL-12p40 and VEGF-A. Co-adoptive transfer of CD25KO CD4+ T cells with either young or aged B6 …

Sci – U: Validation Of An Updated Self-Care Inventory For Contemporary Diabetes Management In Adolescents With Type 1 Diabetes, Sarah S Jaser, Tamim A Hamdan, Marisa E Hilliard, Joyce P Yi-Frazier, Randi Streisand, Faisal S Malik, Daniel J Desalvo, Maeve B O'Donnell, Annette M La Greca

Faculty, Staff and Students Publications

Aims: The Self-Care Inventory is a widely used measure to assess diabetes self-management behaviors. We sought to adapt and streamline the measure to reflect advances in diabetes management, including increased use of continuous glucose monitor and automated insulin delivery systems.

Methods: Through an expert-driven, iterative process, the updated Self-Care Inventory (SCI-U) was created by modifying items to reflect modern diabetes management and reducing the measure to 8 items. The measure was administered to 369 adolescents with type 1 diabetes in 4 regions of the United States, at baseline of two separate intervention trials (mean age = 15.5 ± 1.5, 56 …

Pedagogical Content Knowledge As A Lens For Transforming Teaching In Medical And Health Professions Education, Peter J Boedeker, Nancy P Moreno, Alana D Newell, Atul Maheshwari, Matthew A Mcmillin, Samantha P Tippen, Malford T Pillow, Andrew D Bergemann

Faculty, Staff and Students Publications

Pedagogical content knowledge (PCK) is the separate, topic-specific, specialized knowledge of educators that integrates subject matter expertise with effective teaching strategies in response to an identified learner misconception or to optimize teaching. Although PCK has been used for decades as a framework for understanding the often-tacit ability of an educator to educate well, little has been done to bring this framework into medical and health professions education. We provide examples of PCK in various contexts, including large -group lectures, problem-based learning sessions, and bedside teaching. Finally, we present a tool for capturing instances of PCK that can be used to …

Assessment Of Frailty In Patients With Heart Failure: A New Heart Failure Frailty Score Developed By Delphi Consensus, Cristiana Vitale, Emmanuelle Berthelot, Andrew J S Coats, Hill Loreena, Nancy M Albert, Michal Tkaczyszyn, Stamatis Adamopoulos, Lisa Anderson, Markus S Anker, Stefan D Anker, Derek Bell, Tuvia Ben-Gal, Vasiliki Bistola, Biykem Bozkurt, Poppy Brooks, Miguel Camafort, Juan Jesus Carrero, Ovidiu Chioncel, Dong-Ju Choi, Wook-Jin Chung, Wolfram Doehner, Daniel Fernández-Bergés, Roberto Ferrari, Mona Fiuzat, Juan Esteban Gomez-Mesa, Finn Gustafsson, Ewa Jankowska, Seok-Min Kang, Koichiro Kinugawa, Kamlesh Khunti, F D Richard Hobbs, Christopher Lee, Yuri Lopatin, Matthew Maddocks, Giuseppe Maltese, Elena Marques-Sule, Yuya Matsue, Òscar Miró, Brenda Moura, Massimo Piepoli, Piotr Ponikowski, Giovanni Pulignano, Amina Rakisheva, Robin Ray, Angela Sciacqua, Petar Seferovic, Trinidad Sentandreu-Mañó, Shirley Sze, Alan Sinclair, Anna Strömberg, Olga Theou, Hiroyuki Tsutsui, Izabella Uchmanowicz, Maria Teresa Vidan, Maurizio Volterrani, Stephan Von Haehling, Byungsu Yoo, Jian Zhang, Yuhui Zhang, Marco Metra, Giuseppe Massimo Claudio Rosano

Faculty, Staff and Students Publications

Aims: The Heart Failure Frailty Score (HFFS) is a novel, multidimensional tool to assess frailty in patients with heart failure (HF). It has been developed to overcome limitations of existing frailty assessment tools while being practical for clinical use. The HFFS reflects the concept of frailty as a multidimensional, dynamic and potentially reversible state, which increases vulnerability to stressors and risk of poor outcomes in patients with HF.

Methods and results: The HFFS was developed through a Delphi consensus process involving 54 international experts. This approach involved iterative rounds of questionnaires and interviews, where a panel of experts provided their …

Anti-Mullerian Hormone (Amh) Protects Ovarian Follicle Loss By Downregulating Granulosa Cell Function In In Vitro And In Vivo Models, Laura Detti, Michael C Mari, Michael P Diamond, Ghassan M Saed

Faculty, Staff and Students Publications

Purpose: AMH inhibits hormone production in luteinized granulosa cells (GCs) and stalls ovarian follicle development in vitro and in vivo. We sought to confirm AMH's mechanism of action through SMAD activation and investigate AMH inhibition of follicle development and function, in vitro and in vivo.

Methods: A primary culture of GCs isolated from follicular fluid was used, and cells were treated with recombinant AMH (rAMH) or placebo for 24 h. For the mouse model, 18-weeks old C57BL female mice were either euthanized at the beginning or treated with rAMH or normal saline for 3 weeks. Primordial (PDF), primary follicle (PRF), …

Recreational Outdoor Injury And Mortality In Texas State Parks Between 2012 And 2021, Mohammad I Hirzallah, Ebubechi K Adindu, Julliet C Ogu, Tania Allison, May Kamleh

Faculty, Staff and Students Publications

Introduction

Methods

Efficient Bilateral Trade With Interdependent Values: The Use Of Two-Stage Mechanisms, Takashi Kunimoto, Cuiling Zhang

Research Collection School Of Economics

Efficient, voluntary bilateral trades are generally not implementable in an interdependent values environment with two-sided asymmetric information. To obtain more positive results, we consider two-stage mechanisms in which (i) the outcome (e.g., allocation of the goods) is determined first; (ii) the agents partially learn the state via their own outcome-decision payoffs; and (iii) transfers are finally made. We propose the approximate shoot-the-liar (AS) mechanism and identify Assumption 1, under which “approximately” efficient, voluntary trades are implementable. We further illustrate the permissiveness of the assumption, and characterize it in terms of the nature of interdependence in valuation functions—delineating the boundary between …

Do Government Benefit Programs Reduce Child Labor?: Causal Evidence From The Midday Meal Scheme In India, Vardaan Chawla, Tomoki Fujii, Arpita Khanna, Ray Rohan

Research Collection School Of Economics

This study evaluates the impact of the midday meal program in India on the prevalence of child labor for upper primary school going children. The staggered implementation of the largest school feeding program in the world across states provides exogenous variation in exposure. Using the nationally representative National Sample Survey Office (NSSO) data, we find that exposure to the program reduced prevalence of child labor by 47 percent relative to children in never-treated states, with no significant difference in impact between boys and girls. The effects were primarily driven by a decline in household labor supply, especially performance of household …

Building Narratives And Probing Concepts: Preparing Materials For Co-Design With Autistic Livestreamers, Terrance Mok, Tyson Hartley, Anthony Tang, Adam Mccrimmon, Lora Oehlberg

Research Collection School Of Computing and Information Systems

Based on ten semi-structured interviews with autistic Twitch streamers, we introduce a series of scenario-based design narratives coupled with technology design concepts as a starting point for co-design discussion about autistic streaming. This work builds on prior thematic analysis of the unique intersection between autism and livestreaming. Our user-centered scenarios highlight the needs, goals, and challenges of autistic individuals in livestreaming contexts. By using evocative narratives, the scenarios serve to facilitate empathy and deeper engagement with the needs of autistic users, and help facilitate and support co-creative dialogues and discussions about new technology designs. We contribute this starting point for …

Meta-Learning Hyperparameters For Foundation Model Adaptation In Remote-Sensing Imagery, Zichen Tian, Yaoyao Liu, Qianru Sun

Research Collection School Of Computing and Information Systems

Training large foundation models of remote-sensing (RS) images is almost impossible due to the limited and long-tailed data problems. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient fine-tuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -- such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module …

Chatgpt’S Performance Evaluation In Spreadsheets Modeling To Inform Assessments Redesign, Michelle L. F. Cheong

Research Collection School Of Computing and Information Systems

Background: Increasingly, students are using ChatGPT to assist them in learning and even completing their assessments, raising concerns of academic integrity and loss of critical thinking skills. Many articles suggested educators to redesign assessments which are more “Generative-AI-resistant” and to focus on assessing students on higher order thinking skills. However, there is a lack of articles that attempt to quantify assessments at different cognitive levels to provide empirical study insights on ChatGPT’s performance at different levels, which will affect how educators redesign their assessments.Objectives: Educators need new information on how well ChatGPT performs to redesign future assessments to assess their …

Ai Governance And Algorithmic Auditing In Financial Institutions: Lessons From Singapore, Nydia Remolina Leon

Research Collection Yong Pung How School Of Law

This paper examines the role of algorithmic auditing as a mechanism for responsible AI development and deployment in the financial sector, with a particular focus on Singapore’s regulatory and institutional initiatives. Against the backdrop of fragmented global artificial intelligence (AI) governance frameworks, the study analyses how Singapore has developed operational tools — such as the Veritas Toolkit, AI Verify, Project Moonshot and Project Mindforge — that go beyond abstract ethical principles to provide measurable, use-case-specific standards for auditing AI systems. These initiatives contribute to standardising audit practices, enhancing transparency and bridging trust gaps between financial institutions, regulators and stakeholders. The …

Treaties Establishing Dispute Settlement Frameworks, N. Jansen Calamita, Stefanie Schacherer, Facundo Perez-Aznar, Aikaterini Florou

Research Collection Yong Pung How School Of Law

The purpose of the present report is to provide an overview and analysis of the measures that States adopt domestically to implement treaties that establish mechanisms for the resolution of international disputes. The report’s scope subsumes both treaties that include dispute settlement mechanisms to resolve disputes concerning the substantive obligations contained therein as well as treaties that establish frameworks for dispute resolution simpliciter which may be used to resolve disputes arising under a variety of substantive treaties (collectively “international dispute settlement mechanism” or “IDSM” treaties). The approach of the research contained within this report has been to gather information about …

Outperforming The Best With Minimal Effort: Algorithm Selection For Constrained Multi-Objective Optimization, Mustafa Misir, Aldy Gunawan

Research Collection School Of Computing and Information Systems

The present study performs algorithm selection on a suite of optimization algorithms targeting the constrained multi-objective optimization problems. The idea is to utilize the existing, relevant algorithmic experience in the literature to deliver an improved solver with limited effort. The reason being that algorithm development, in general, is a challenging and time-consuming process, especially with the goal of outperforming the existing methods from varying perspectives such as performance, speed, and robustness. Concerning the multi-objective optimization problems, the required development efforts happen to be even harder than addressing the single-objective ones. Furthermore, referring to the fact that the number of candidate …

Alayadb: The Data Foundation For Efficient And Effective Long-Context Llm Inference, Yangshen Deng, Zhengxin You, Long Xiang, Qilong Li, Peiqi Yuan, Zhaoyang Hong, Yitao Zheng, Wanting Li, Runzhong Li, Haotian Liu, Kyriakos Mouratidis, Man Lung Yiu, Huan Li, Qiaomu Shen, Rui Mao, Bo Tang

Research Collection School Of Computing and Information Systems

AlayaDB is a cutting-edge vector database system natively architected for efficient and effective long-context inference for Large Language Models (LLMs) at AlayaDB AI. Specifically, it decouples the KV cache and attention computation from the LLM inference systems, and encapsulates them into a novel vector database system. For the Model as a Service providers (MaaS), AlayaDB consumes fewer hardware resources and offers higher generation quality for various workloads with different kinds of Service Level Objectives (SLOs), when compared with the existing alternative solutions (e.g., KV cache disaggregation, retrieval-based sparse attention). The crux of AlayaDB is that it abstracts the attention computation …

Reaccept: Automated Co-Evolution Of Production And Test Code Based On Dynamic Validation And Large Language Models, Jianlei Chi, Xiaotian Wang, Yuhan Huang, Lechen Yu, Di Cui, Jianguo Sun, Jun Sun

Research Collection School Of Computing and Information Systems

Synchronizing production and test code, known as PT co-evolution, is critical for software quality. Given the significant manual effort involved, researchers have tried automating PT co-evolution using predefined heuristics and machine learning models. However, existing solutions are still incomplete. Most approaches only detect and flag obsolete test cases, leaving developers to manually update them. Meanwhile, existing solutions may suffer from low accuracy, especially when applied to real-world software projects. In this paper, we propose ReAccept, a novel approach leveraging large language models (LLMs), retrievalaugmented generation (RAG), and dynamic validation to fully automate PT co-evolution with high accuracy. ReAccept employs an …

De-Duplicating Silent Compiler Bugs Via Deep Semantic Representation, Junjie Chen, Xingyu Fan, Chen Yang, Shuang Liu, Jun Sun

Research Collection School Of Computing and Information Systems

The compiler bug duplication problem (where many test failures are caused by the same compiler bug) can lead to huge waste of time and resource in diagnosing test failures produced by compiler testing. It is particularly challenging with regard to the silent compiler bugs that do not produce any error messages. To address this problem, multiple white-box techniques were proposed, but they are inapplicable in many practical scenarios. Black-box techniques are more practical, but the existing ones are less effective as they often rely on irrelevant syntactic information. To bridge this gap, we propose a novel black-box technique (BLADE), which …

A Comprehensive Study Of Oop-Related Bugs In C++ Compilers, Bo Wang, Chong Chen, Junjie Chen, Bowen Xu, Chen Ye, Youfang Lin, Guoliang Dong, Jun Sun

Research Collection School Of Computing and Information Systems

Modern C++, a programming language characterized by its extensive use of object-oriented programming (OOP) features, is widely used for system programming. However, C++ compilers often struggle to correctly handle these sophisticated OOP features, resulting in numerous high-profile compiler bugs that can lead to crashes or miscompilation. Despite the significance of OOP-related bugs, existing studies largely overlook OOP features, hindering their ability to discover such bugs. To assist both compiler fuzzer designers and compiler developers, we conduct a comprehensive study of the compiler bugs caused by incorrectly handling C++ OOP-related features. First, we systematically extract 788 OOP-related C++ compiler bugs from …

Hd-Epic: A Highly-Detailed Egocentric Video Dataset, Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha, Omar Emara, Sam Pollard, Kranti Kumar Parida, Kaiting Liu, Prajwal Gatti, Siddhant Bansal, Kevin Flanagan, Jacob Chalk, Zhifan Zhu, Rhodri Guerrier, Fahd Abdelazim, Bin Zhu, Davide Moltisanti, Michael Wray, Hazel Doughty, Dima Damen

Research Collection School Of Computing and Information Systems

We present a validation dataset of newly-collected kitchenbased egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those in controlled lab environments. We show the potential of our highly-detailed annotations through a challenging VQA benchmark of 26K questions assessing the capability to …