Graph Learning for Fashion Compatibility Modeling
暫譯: 時尚相容性建模的圖學習

Guan, Weili, Song, Xuemeng, Chang, Xiaojun

Graph Learning for Fashion Compatibility Modeling
  • 出版商: Springer
  • 出版日期: 2023-11-04
  • 售價: $2,800
  • 貴賓價: 9.5 折 $2,660
  • 語言: 英文
  • 頁數: 112
  • 裝訂: Quality Paper - also called trade paper
  • ISBN: 3031188195
  • ISBN-13: 9783031188190
  • 相關分類: 人工智慧、大數據 Big-data、Machine Learning

    • 海外代購書籍(需單獨結帳)

相關主題

商品描述

This book sheds light on state-of-the-art theories for more challenging outfit compatibility modeling scenarios. In particular, this book presents several cutting-edge graph learning techniques that can be used for outfit compatibility modeling. Due to its remarkable economic value, fashion compatibility modeling has gained increasing research attention in recent years. Although great efforts have been dedicated to this research area, previous studies mainly focused on fashion compatibility modeling for outfits that only involved two items and overlooked the fact that each outfit may be composed of a variable number of items. This book develops a series of graph-learning based outfit compatibility modeling schemes, all of which have been proven to be effective over several public real-world datasets. This systematic approach benefits readers by introducing the techniques for compatibility modeling of outfits that involve a variable number of composing items. To deal with the challenging task of outfit compatibility modeling, this book provides comprehensive solutions, including correlation-oriented graph learning, modality-oriented graph learning, unsupervised disentangled graph learning, partially supervised disentangled graph learning, and metapath-guided heterogeneous graph learning. Moreover, this book sheds light on research frontiers that can inspire future research directions for scientists and researchers.

商品描述(中文翻譯)

本書闡述了針對更具挑戰性的服裝相容性建模場景的最先進理論。特別是，本書介紹了幾種可用於服裝相容性建模的尖端圖學習技術。由於其顯著的經濟價值，時尚相容性建模在近年來獲得了越來越多的研究關注。儘管在這一研究領域投入了大量努力，但以往的研究主要集中在僅涉及兩件物品的服裝相容性建模，忽略了每套服裝可能由變數數量的物品組成的事實。本書開發了一系列基於圖學習的服裝相容性建模方案，所有方案在幾個公共真實世界數據集上均已證明有效。這種系統化的方法使讀者受益，因為它介紹了涉及變數數量組成物品的服裝相容性建模技術。為了應對服裝相容性建模的挑戰性任務，本書提供了全面的解決方案，包括以相關性為導向的圖學習、以模態為導向的圖學習、無監督的解耦圖學習、部分監督的解耦圖學習以及基於元路徑的異質圖學習。此外，本書還闡明了可以啟發科學家和研究人員未來研究方向的研究前沿。

作者簡介

Weili Guan received a master degree from National University of Singapore. After that, she joined Hewlett Packard Enterprise in Singapore as a Software Engineer and worked there for several years. She is currently a PhD student with the Faculty of Information Technology, Monash University (Clayton Campus), Australia. Her research interests are multimedia computing and information retrieval. She has authored or co-authored more than 30 papers at first-tier conferences and journals, like ACM MM, SIGIR, and IEEE TIP.
Xuemeng Song received a B.E. from the University of Science and Technology of China in 2012, and a Ph.D. from the School of Computing, National University of Singapore in 2016. She is currently an Associate Professor of Shandong University, Jinan, China. Her research interests include the information retrieval and social network analysis. She has published several papers in top venues, such as ACM SIGIR, MM, TIP, and TOIS. In addition, she has served as a reviewer for many top conferences and journals.

Dr. Xiaojun Chang is a Professor at the Australian Artificial Intelligence Institute, Faculty of Engineering and Information Technology, University of Technology Sydney. He is the Director of The ReLER Lab. He is also an Honorary Professor in the School of Computing Technologies, RMIT University, Australia. Before joining UTS, he was an Associate Professor at School of Computing Technologies, RMIT University, Australia. After graduation, he subsequently worked as a Postdoc Research Fellow at School of Computer Science, Carnegie Mellon University, Lecturer and Senior Lecturer in the Faculty of Information Technology, Monash University, Australia. He has focused his research on exploring multiple signals (visual, acoustic, textual) for automatic content analysis in unconstrained or surveillance videos. His team has won multiple prizes from international grand challenges which hosted competitive teams from MIT, University of Maryland, Facebook AI Research (FAIR) and Baidu VIS, and aim to advance visual understanding using deep learning. For example, he won the first place in the TrecVID 2019 - Activity Extended Video (ActEV) challenge, which was held by National Institute of Standards and Technology, US.

Liqiang Nie, Ph.D., is Dean with the Department of Computer Science and Technology at Harbin Institute of Technology (Shenzhen). He received his B.Eng. and Ph.D. degrees from Xi'an Jiaotong University and National University of Singapore (NUS), respectively. His research interests lie primarily in multimedia computing and information retrieval. Dr. Nie has co-/authored more than 100 papers and four books and has received more than 15,000 Google Scholar citations. He is an Associate Editor of IEEE TKDE, IEEE TMM, IEEE TCSVT, ACM ToMM, and Information Science. He is also a regular area chair of ACM MM, NeurIPS, IJCAI, and AAAI and a member of ICME steering committee. Dr. Nie has received many awards, including ACM MM and SIGIR best paper honorable mention in 2019, SIGMM rising star in 2020, TR35 China 2020, DAMO Academy Young Fellow in 2020, and SIGIR best student paper in 2021.

作者簡介(中文翻譯)

韋莉·關（Weili Guan）於新加坡國立大學獲得碩士學位。之後，她在新加坡的惠普企業（Hewlett Packard Enterprise）擔任軟體工程師，並在那裡工作了幾年。她目前是澳洲莫納什大學（Monash University，克萊頓校區）資訊科技學院的博士生。她的研究興趣包括多媒體計算和資訊檢索。她已在一流的會議和期刊上發表或共同發表了超過30篇論文，如ACM MM、SIGIR和IEEE TIP。

熊夢（Xuemeng Song）於2012年獲得中國科學技術大學的工學學士學位，並於2016年在新加坡國立大學計算學院獲得博士學位。她目前是中國濟南的山東大學副教授。她的研究興趣包括資訊檢索和社交網絡分析。她在頂尖會議上發表了多篇論文，如ACM SIGIR、MM、TIP和TOIS。此外，她還擔任多個頂尖會議和期刊的審稿人。

張小軍（Xiaojun Chang）博士是澳洲悉尼科技大學（University of Technology Sydney）工程與資訊科技學院的教授。他是ReLER實驗室的主任。他同時也是澳洲RMIT大學計算技術學院的榮譽教授。在加入UTS之前，他曾是RMIT大學計算技術學院的副教授。畢業後，他隨後在卡內基梅隆大學（Carnegie Mellon University）計算機科學學院擔任博士後研究員，並在澳洲莫納什大學資訊科技學院擔任講師和高級講師。他的研究專注於探索多種信號（視覺、聲音、文本）以進行無約束或監控視頻的自動內容分析。他的團隊在國際大賽中獲得多個獎項，這些大賽吸引了來自麻省理工學院（MIT）、馬里蘭大學（University of Maryland）、Facebook AI Research（FAIR）和百度視覺（Baidu VIS）的競爭團隊，旨在利用深度學習推進視覺理解。例如，他在由美國國家標準與技術研究所（National Institute of Standards and Technology）舉辦的TrecVID 2019 - Activity Extended Video (ActEV)挑戰賽中獲得第一名。

聶立強（Liqiang Nie）博士是哈爾濱工業大學（深圳）計算機科學與技術系的系主任。他分別在西安交通大學和新加坡國立大學獲得工學學士和博士學位。他的研究興趣主要集中在多媒體計算和資訊檢索。聶博士已共同或獨立發表了超過100篇論文和四本書籍，並獲得超過15,000次Google Scholar引用。他是IEEE TKDE、IEEE TMM、IEEE TCSVT、ACM ToMM和資訊科學的副編輯。他還是ACM MM、NeurIPS、IJCAI和AAAI的常任區域主席，以及ICME指導委員會的成員。聶博士獲得了多項獎項，包括2019年ACM MM和SIGIR最佳論文榮譽提名、2020年SIGMM新星、2020年TR35中國、2020年DAMO Academy青年研究員，以及2021年SIGIR最佳學生論文。

類似商品

最後瀏覽商品 (10)