[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-139513-105":59,"doc-detail-139513-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","holistic-bias-mitigation-in-computer-vision-and-beyond-dissertation","Holistic Bias Mitigation in Computer Vision and Beyond - Dissertation","","The dissertation presents a data-centric framework for holistic bias mitigation in computer vision models, focusing on representation bias and its downstream impacts. It analyzes biases in action recognition datasets, proposes methods for measuring bias at multiple levels, and introduces debiasing strategies including minimum-bias dataset resampling and reweighting via adversarial examples. The work further develops dynamic scoring and dynamic representation learning to improve temporal video understanding, supported by extensive experiments and ablations.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/holistic-bias-mitigation-in-computer-vision-and-beyond-dissertation/139513/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/holistic-bias-mitigation-in-computer-vision-and-beyond-dissertation/139513.png","ImageObject",300,407,{"name":92,"@type":93},"Sophia Brooks","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-27","2026-08-24",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the central focus of this dissertation?","Question",{"text":112,"@type":113},"It focuses on holistic bias mitigation in computer vision, emphasizing representation bias and its effects on action recognition and multimodal models.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the dissertation approach debiasing from a data-centric perspective?",{"text":117,"@type":113},"It frames debiasing around dataset and representation bias, including calibrated measurement and debiasing through minimum-bias dataset resampling and adversarial example reweighting.",{"name":119,"@type":110,"acceptedAnswer":120},"What is dynamic scoring and how is it used?",{"text":121,"@type":113},"Dynamic scoring measures bias-related dynamics in video representations, and the dissertation uses it to guide dynamic representation learning for improved temporal understanding.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},139513,1787551588,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144},962084925636,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","UC San Diego  \nUC San Diego Electronic Theses and Dissertations  \nTitle  \nHolistic Bias Mitigation in Computer Vision and Beyond  \nPermalink  \n[https://escholarship.org/uc/item/4h78p6rq](https://escholarship.org/uc/item/4h78p6rq)  \nAuthor  \nLi, Yi  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA SAN DIEGO  \nHolistic Bias Mitigation in Computer Vision and Beyond  \nA dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy  \nin  \nElectrical Engineering (Signal and Image Processing)  \nby  \nYi Li  \nCommittee in charge:  \nProfessor Nuno Vasconcelos, Chair  \nProfessor Nikolay Atanasov  \nProfessor Truong Nguyen  \nProfessor Zhuowen Tu  \nProfessor Xiaolong Wang  \nCopyright Yi Li, 2024 All rights reserved.  \nThe Dissertation of Yi Li is approved, and it is acceptable in quality and form for publication on microfilm and electronically.  \nUniversity of California San Diego  \n2024  \nDEDICATION  \nTo my family.  \nTABLE OF CONTENTS  \nDissertation Approval Page .................................................... iii  \nDedication .................................................................. iv  \nTable of Contents ............................................................ v  \nList of Figures ............................................................... viii  \nList of Tables ................................................................ x  \nAcknowledgements ........................................................... xii  \nVita ........................................................................ xiv  \nAbstract of the Dissertation .................................................... xv  \nChapter 1 Introduction ..................................................... 1  \n1.1 A Data-centric View of Debiasing ....................................... 3  \n1.2 Challenges in Bias Mitigation .......................................... 4  \n1.3 Contributions of the Thesis ............................................. 6  \n1.3.1 Representation Bias in Video Action Recognition ................... 6  \n1.3.2 Temporal Learning of Video Representations ....................... 7  \n1.3.3 Holistic Debiasing of Multimodal Models ......................... 9  \nPart I Representation Unbiased Datasets ..................................... 10  \nChapter 2 Representation Bias in Action Recognition ........................... 11  \n2.1 Introduction ......................................................... 11  \n2.2 Related Work ........................................................ 14  \n2.3 Representation Bias ................................................... 16  \n2.3.1 Dataset Bias .................................................. 16  \n2.3.2 Representation Bias ............................................ 17  \n2.3.3 Calibrated Datasets ............................................ 18  \n2.3.4 Measuring Representation Bias .................................. 20  \n2.3.5 Measuring Bias at the Class Level ................................ 21  \n2.4 RESOUND Dataset Collection ......................................... 22  \n2.4.1 Explicit RESOUND ............................................ 22  \n2.4.2 Implicit RESOUND: the Diving48 Dataset ......................... 23  \n2.5 Experiments ......................................................... 25  \n2.5.1 Datasets ...................................................... 26  \n2.5.2 RESOUND Experiments ........................................ 26  \n2.5.3 Class-level Dominant Bias ...................................... 28  \n2.5.4 Explicit RESOUND ............................................ 28  \n2.5.5 Classification with Dynamics .................................... 29  \n2.6 Conclusion .......................................................... 30  \nChapter 3 Representation Bias Mitigation ..................................... 31  \n3.1 Introduc","cbCaiqDerX3w4USb","https://ap.wps.com/l/cbCaiqDerX3w4USb","pdf",14733497,159,"English","# Dissertation Approval Page\n# Dedication\n# Table of Contents\n# List of Figures\n# List of Tables\n# Acknowledgements\n# Vita\n# Abstract of the Dissertation\n# Chapter 1 Introduction\n## A Data-centric View of Debiasing\n## Challenges in Bias Mitigation\n## Contributions of the Thesis\n# Chapter 2 Representation Bias in Action Recognition\n## Introduction\n## Related Work\n## Representation Bias\n## RESOUND Dataset Collection\n## Experiments\n## Conclusion\n# Chapter 3 Representation Bias Mitigation\n## Introduction\n## Related Work\n## Minimum-bias Dataset Resampling\n## Case studies\n## Conclusion\n# Chapter 4 Dynamic Representation Learning\n## Introduction\n## Related Work\n## Dynamic Scoring\n## Dynamic Representation Learning\n## Experiments","[{\"question\":\"What is the central focus of this dissertation?\",\"answer\":\"It focuses on holistic bias mitigation in computer vision, emphasizing representation bias and its effects on action recognition and multimodal models.\"},{\"question\":\"How does the dissertation approach debiasing from a data-centric perspective?\",\"answer\":\"It frames debiasing around dataset and representation bias, including calibrated measurement and debiasing through minimum-bias dataset resampling and adversarial example reweighting.\"},{\"question\":\"What is dynamic scoring and how is it used?\",\"answer\":\"Dynamic scoring measures bias-related dynamics in video representations, and the dissertation uses it to guide dynamic representation learning for improved temporal understanding.\"}]","Holistic Bias Mitigation in Computer Vision and Beyond - Dissertation | PDF",401]