Person Re Identification With Limited Supervision

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.

This book provides an overview of different deep learning-based methods for face recognition and related problems. Specifically, the authors present methods based on autoencoders, restricted Boltzmann machines, and deep convolutional neural networks for face detection, localization, tracking, recognition, etc. The authors also discuss merits and drawbacks of available approaches and identifies promising avenues of research in this rapidly evolving field. Even though there have been a number of different approaches proposed in the literature for face recognition based on deep learning methods, there is not a single book available in the literature that gives a complete overview of these methods. The proposed book captures the state of the art in face recognition using various deep learning methods, and it covers a variety of different topics related to face recognition. This book is aimed at graduate students studying electrical engineering and/or computer science. Biometrics is a course that is widely offered at both undergraduate and graduate levels at many institutions around the world: This book can be used as a textbook for teaching topics related to face recognition. In addition, the work is beneficial to practitioners in industry who are working on biometrics-related problems. The prerequisites for optimal use are the basic knowledge of pattern recognition, machine learning, probability theory, and linear algebra.

Solving problems with deep neural networks typically relies on massive amounts of labeled training data to achieve high performance. While in many situations huge volumes of unlabeled data can be and often are generated and available, the cost of acquiring data labels remains high. Transfer learning (TL), and in particular domain adaptation (DA), has emerged as an effective solution to overcome the burden of annotation, exploiting the unlabeled data available from the target domain together with labeled data or pre-trained models from similar, yet different source domains. The aim of this book is to provide an overview of such DA/TL methods applied to computer vision, a field whose popularity has increased significantly in the last few years. We set the stage by revisiting the theoretical background and some of the historical shallow methods before discussing and comparing different domain adaptation strategies that exploit deep architectures for visual recognition. We introduce the space of self-training-based methods that draw inspiration from the related fields of deep semi-supervised and self-supervised learning in solving the deep domain adaptation. Going beyond the classic domain adaptation problem, we then explore the rich space of problem settings that arise when applying domain adaptation in practice such as partial or open-set DA, where source and target data categories do not fully overlap, continuous DA where the target data comes as a stream, and so on. We next consider the least restrictive setting of domain generalization (DG), as an extreme case where neither labeled nor unlabeled target data are available during training. Finally, we close by considering the emerging area of learning-to-learn and how it can be applied to further improve existing approaches to cross domain learning problems such as DA and DG.

The 30-volume set, comprising the LNCS books 12346 until 12375, constitutes the refereed proceedings of the 16th European Conference on Computer Vision, ECCV 2020, which was planned to be held in Glasgow, UK, during August 23-28, 2020. The conference was held virtually due to the COVID-19 pandemic. The 1360 revised papers presented in these proceedings were carefully reviewed and selected from a total of 5025 submissions. The papers deal with topics such as computer vision; machine learning; deep neural networks; reinforcement learning; object recognition; image classification; image processing; object detection; semantic segmentation; human pose estimation; 3d reconstruction; stereo vision; computational photography; neural networks; image coding; image reconstruction; object recognition; motion estimation.

The six-volume set LNCS 11764, 11765, 11766, 11767, 11768, and 11769 constitutes the refereed proceedings of the 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2019, held in Shenzhen, China, in October 2019. The 539 revised full papers presented were carefully reviewed and selected from 1730 submissions in a double-blind review process. The papers are organized in the following topical sections: Part I: optical imaging; endoscopy; microscopy. Part II: image segmentation; image registration; cardiovascular imaging; growth, development, atrophy and progression. Part III: neuroimage reconstruction and synthesis; neuroimage segmentation; diffusion weighted magnetic resonance imaging; functional neuroimaging (fMRI); miscellaneous neuroimaging. Part IV: shape; prediction; detection and localization; machine learning; computer-aided diagnosis; image reconstruction and synthesis. Part V: computer assisted interventions; MIC meets CAI. Part VI: computed tomography; X-ray imaging.

This three-volume set LNCS 13338-13340 constitutes the thoroughly refereed proceedings of the 8th International Conference on Artificial Intelligence and Security, ICAIS 2022, which was held in Qinghai, China, in July 2022. The total of 166 papers included in the 3 volumes were carefully reviewed and selected from 1124 submissions. The papers present research, development, and applications in the fields of artificial intelligence and information security

The four-volume proceedings LNCS 13108, 13109, 13110, and 13111 constitutes the proceedings of the 28th International Conference on Neural Information Processing, ICONIP 2021, which was held during December 8-12, 2021. The conference was planned to take place in Bali, Indonesia but changed to an online format due to the COVID-19 pandemic. The total of 226 full papers presented in these proceedings was carefully reviewed and selected from 1093 submissions. The papers were organized in topical sections as follows: Part I: Theory and algorithms; Part II: Theory and algorithms; human centred computing; AI and cybersecurity; Part III: Cognitive neurosciences; reliable, robust, and secure machine learning algorithms; theory and applications of natural computing paradigms; advances in deep and shallow machine learning algorithms for biomedical data and imaging; applications; Part IV: Applications.

The 7-volume set of LNCS 13841-13847 constitutes the proceedings of the 16th Asian Conference on Computer Vision, ACCV 2022, held in Macao, China, December 2022. The total of 277 contributions included in the proceedings set was carefully reviewed and selected from 836 submissions during two rounds of reviewing and improvement. The papers focus on the following topics: Part I: 3D computer vision; optimization methods; Part II: applications of computer vision, vision for X; computational photography, sensing, and display; Part III: low-level vision, image processing; Part IV: face and gesture; pose and action; video analysis and event recognition; vision and language; biometrics; Part V: recognition: feature detection, indexing, matching, and shape representation; datasets and performance analysis; Part VI: biomedical image analysis; deep learning for computer vision; Part VII: generative models for computer vision; segmentation and grouping; motion and tracking; document image analysis; big data, large scale methods.