Person Re-Identification with Limited Supervision
暫譯: 有限監督下的人員重識別
Panda, Rameswar, Roy-Chowdhury, Amit K.
- 出版商: Morgan & Claypool
- 出版日期: 2021-09-30
- 售價: $2,090
- 貴賓價: 9.5 折 $1,986
- 語言: 英文
- 頁數: 98
- 裝訂: Hardcover - also called cloth, retail trade, or trade
- ISBN: 163639227X
- ISBN-13: 9781636392271
海外代購書籍(需單獨結帳)
商品描述
Person re-identification is the problem of associating observations of targets in different non-overlapping cameras. Most of the existing learning-based methods have resulted in improved performance on standard re-identification benchmarks, but at the cost of time-consuming and tediously labeled data. Motivated by this, learning person re-identification models with limited to no supervision has drawn a great deal of attention in recent years.
In this book, we provide an overview of some of the literature in person re-identification, and then move on to focus on some specific problems in the context of person re-identification with limited supervision in multi-camera environments. We expect this to lead to interesting problems for researchers to consider in the future, beyond the conventional fully supervised setup that has been the framework for a lot of work in person re-identification.
Chapter 1 starts with an overview of the problems in person re-identification and the major research directions. We provide an overview of the prior works that align most closely with the limited supervision theme of this book. Chapter 2 demonstrates how global camera network constraints in the form of consistency can be utilized for improving the accuracy of camera pair-wise person re-identification models and also selecting a minimal subset of image pairs for labeling without compromising accuracy. Chapter 3 presents two methods that hold the potential for developing highly scalable systems for video person re-identification with limited supervision. In the one-shot setting where only one tracklet per identity is labeled, the objective is to utilize this small labeled set along with a larger unlabeled set of tracklets to obtain a re-identification model. Another setting is completely unsupervised without requiring any identity labels. The temporal consistency in the videos allows us to infer about matching objects across the cameras with higher confidence, even with limited to no supervision. Chapter 4 investigates person re-identification in dynamic camera networks. Specifically, we consider a novel problem that has received very little attention in the community but is critically important for many applications where a new camera is added to an existing group observing a set of targets. We propose two possible solutions for on-boarding new camera(s) dynamically to an existing network using transfer learning with limited additional supervision. Finally, Chapter 5 concludes the book by highlighting the major directions for future research.
商品描述(中文翻譯)
人員重新識別是將不同非重疊攝影機中目標觀察結果進行關聯的問題。大多數現有的基於學習的方法在標準重新識別基準上取得了改進的性能，但代價是需要耗時且繁瑣的標註數據。受到此啟發，近年來在有限或無監督的情況下學習人員重新識別模型引起了廣泛的關注。
在本書中，我們提供了一些人員重新識別文獻的概述，然後專注於在多攝影機環境中有限監督下的人員重新識別的特定問題。我們期望這能引發研究者在未來考慮有趣的問題，超越傳統的完全監督設置，這一直是人員重新識別研究的框架。
第一章開始於人員重新識別問題的概述及主要研究方向。我們提供了與本書有限監督主題最密切相關的先前工作的概述。第二章展示了如何利用全球攝影機網絡約束（以一致性的形式）來提高攝影機成對人員重新識別模型的準確性，並選擇一個最小的圖像對子集進行標註而不影響準確性。第三章提出了兩種方法，這些方法有潛力開發出具有高度可擴展性的視頻人員重新識別系統，並且在有限監督的情況下運作。在一次性標註的設置中，每個身份僅標註一個追蹤片段，目標是利用這個小的標註集以及一個更大的未標註追蹤片段集來獲得重新識別模型。另一種設置是完全無監督的，無需任何身份標籤。視頻中的時間一致性使我們能夠在有限或無監督的情況下，以更高的信心推斷跨攝影機的匹配物體。第四章探討了在動態攝影機網絡中的人員重新識別。具體而言，我們考慮了一個在社群中受到很少關注但對許多應用至關重要的新問題，即在觀察一組目標的現有群組中添加新攝影機。我們提出了兩種可能的解決方案，使用有限的額外監督，通過轉移學習動態地將新攝影機納入現有網絡。最後，第五章通過強調未來研究的主要方向來結束本書。
作者簡介
Rameswar Panda obtained his Ph.D in Electrical and Computer Engineering from University of California, Riverside. Prior to joining UC Riverside, he obtained his M.S. degree from Jadavpur University and B.E. from Biju Patnaik University of Tech- nology, both in India. During Ph.D., Rameswar worked at NEC Labs America, Adobe Research and Siemens Corporate Research. His primary research interests span the areas of computer vision, machine learning and multimedia. In particular, his current focus is on making AI systems more efficient, i.e., developing novel deep learning methods that can operate with less human-annotated data (data efficient), and less computation (model efficient). He is also interested in image/video understanding, unsupervised/self-supervised representation learning and multimodal learning (e.g., combining vision, sound/speech and language). His work has been published in top- tier conferences such as CVPR, ICCV, ECCV, NeurIPS, ICML and ICLR as well as high impact journals such as TIP and TMM. He actively participates as a program committee member for many top AI conferences and was leading co-chair of the workshop on Multi-modal Video Analysis at ICCV 2019, ECCV 2020 and Workshop on Neural Architecture Search at CVPR 2020, CVPR 2021.
Amit K. Roy-Chowdhury received his PhD from the University of Maryland, Col- lege Park (UMCP) in 2002 and joined the University of California, Riverside (UCR) in 2004 where he is a Professor and Bourns Family Faculty Fellow of Electrical and Computer Engineering, Director of the Center for Robotics and Intelligent Systems, and Cooperating Faculty in the department of Computer Science and Engineering. He leads the Video Computing Group at UCR, working on foundational principles of computer vision, image processing, and statistical learning, with applications in cyber-physical, autonomous and intelligent systems. He co-directs the US Depart- ment of Defense Center of Excellence NC4: Networked, Configurable Command, Control and Communications for Rapid Situational Awareness. He has published over 200 papers in peer-reviewed journals and conferences. He is the first author of the book Camera Networks: The Acquisition and Analysis of Videos Over Wide Areas. He is on the editorial boards of major journals and program committees of the main conferences in his area. His students have been first authors on multiple papers that received Best Paper Awards at major international conferences, includ- ing ICASSP and ICMR. He is a Fellow of the IEEE and IAPR, received the Doctoral Dissertation Advising/Mentoring Award 2019 from UCR, and the ECE Distinguished Alumni Award from UMCP.
作者簡介(中文翻譯)
**Rameswar Panda** 於加州大學河濱分校獲得電機與計算機工程博士學位。在加入加州大學河濱分校之前，他在印度的賈達普爾大學獲得碩士學位，並在比朱·帕特奈克科技大學獲得工程學士學位。在攻讀博士學位期間，Rameswar 曾在 NEC Labs America、Adobe Research 和 Siemens Corporate Research 工作。他的主要研究興趣涵蓋計算機視覺、機器學習和多媒體領域。特別是，他目前專注於提高 AI 系統的效率，即開發能夠在較少人類標註數據（數據效率）和較少計算（模型效率）下運行的新型深度學習方法。他還對圖像/視頻理解、無監督/自我監督表示學習和多模態學習（例如，結合視覺、聲音/語音和語言）感興趣。他的研究成果已發表在頂級會議上，如 CVPR、ICCV、ECCV、NeurIPS、ICML 和 ICLR，以及高影響力的期刊，如 TIP 和 TMM。他積極參與多個頂級 AI 會議的程序委員會，並在 ICCV 2019、ECCV 2020 的多模態視頻分析研討會及 CVPR 2020、CVPR 2021 的神經架構搜索研討會擔任聯合主席。
**Amit K. Roy-Chowdhury** 於 2002 年在馬里蘭大學學院市（UMCP）獲得博士學位，並於 2004 年加入加州大學河濱分校（UCR），目前擔任電機與計算機工程教授及 Bourns 家族教職獎學金獲得者，並擔任機器人與智能系統中心主任，以及計算機科學與工程系的合作教員。他領導 UCR 的視頻計算小組，專注於計算機視覺、圖像處理和統計學習的基礎原則，並應用於網絡物理、自主和智能系統。他共同指導美國國防部卓越中心 NC4：網絡化、可配置的指揮、控制和通信以快速情境感知。他在同行評審的期刊和會議上發表了超過 200 篇論文。他是書籍《Camera Networks: The Acquisition and Analysis of Videos Over Wide Areas》的第一作者。他在主要期刊的編輯委員會和其領域主要會議的程序委員會中任職。他的學生在多個國際會議上獲得最佳論文獎，包括 ICASSP 和 ICMR，並擔任第一作者。他是 IEEE 和 IAPR 的會士，於 2019 年獲得 UCR 的博士論文指導/輔導獎，並獲得 UMCP 的電機與計算機工程傑出校友獎。
