This volume presents the results of the Neural Information Processing Systems Competition track at the 2018 NeurIPS conference. The competition follows the same format as the 2017 competition track for NIPS. Out of 21 submitted proposals, eight competition proposals were selected, spanning the area of Robotics, Health, Computer Vision, Natural Language Processing, Systems and Physics. Competitions have become an integral part of advancing state-of-the-art in artificial intelligence (AI). They exhibit one important difference to benchmarks: Competitions test a system end-to-end rather than evaluating only a single component; they assess the practicability of an algorithmic solution in addition to assessing feasibility. The eight run competitions aim at advancing the state of the art in deep reinforcement learning, adversarial learning, and auto machine learning, among others, including new applications for intelligent agents in gaming and conversational settings, energy physics, and prosthetics.

This book summarizes the organized competitions held during the first NIPS competition track. It provides both theory and applications of hot topics in machine learning, such as adversarial learning, conversational intelligence, and deep reinforcement learning. Rigorous competition evaluation was based on the quality of data, problem interest and impact, promoting the design of new models, and a proper schedule and management procedure. This book contains the chapters from organizers on competition design and from top-ranked participants on their proposed solutions for the five accepted competitions: The Conversational Intelligence Challenge, Classifying Clinically Actionable Genetic Mutations, Learning to Run, Human-Computer Question Answering Competition, and Adversarial Attacks and Defenses.

This book presents a selection of chapters, written by leading international researchers, related to the automatic analysis of gestures from still images and multi-modal RGB-Depth image sequences. It offers a comprehensive review of vision-based approaches for supervised gesture recognition methods that have been validated by various challenges. Several aspects of gesture recognition are reviewed, including data acquisition from different sources, feature extraction, learning, and recognition of gestures.

The problem of dealing with missing or incomplete data in machine learning and computer vision arises in many applications. Recent strategies make use of generative models to impute missing or corrupted data. Advances in computer vision using deep generative models have found applications in image/video processing, such as denoising, restoration, super-resolution, or inpainting. Inpainting and Denoising Challenges comprises recent efforts dealing with image and video inpainting tasks. This includes winning solutions to the ChaLearn Looking at People inpainting and denoising challenges: human pose recovery, video de-captioning and fingerprint restoration. This volume starts with a wide review on image denoising, retracing and comparing various methods from the pioneer signal processing methods, to machine learning approaches with sparse and low-rank models, and recent deep learning architectures with autoencoders and variants. The following chapters present results from the Challenge, including three competition tasks at WCCI and ECML 2018. The top best approaches submitted by participants are described, showing interesting contributions and innovating methods. The last two chapters propose novel contributions and highlight new applications that benefit from image/video inpainting.

This work presents a full generic approach to the detection and recognition of traffic signs. The approach is based on the latest computer vision methods for object detection, and on powerful methods for multiclass classification. The challenge was to robustly detect a set of different sign classes in real time, and to classify each detected sign into a large, extensible set of classes. To address this challenge, several state-of-the-art methods were developed that can be used for different recognition problems. Following an introduction to the problems of traffic sign detection and categorization, the text focuses on the problem of detection, and presents recent developments in this field. The text then surveys a specific methodology for the problem of traffic sign categorization - Error-Correcting Output Codes - and presents several algorithms, performing experimental validation on a mobile mapping application. The work ends with a discussion on future research and continuing challenges.

The problem of dealing with missing or incomplete data in machine learning and computer vision arises in many applications. Recent strategies make use of generative models to impute missing or corrupted data. Advances in computer vision using deep generative models have found applications in image/video processing, such as denoising, restoration, super-resolution, or inpainting. Inpainting and Denoising Challenges comprises recent efforts dealing with image and video inpainting tasks. This includes winning solutions to the ChaLearn Looking at People inpainting and denoising challenges: human pose recovery, video de-captioning and fingerprint restoration. This volume starts with a wide review on image denoising, retracing and comparing various methods from the pioneer signal processing methods, to machine learning approaches with sparse and low-rank models, and recent deep learning architectures with autoencoders and variants. The following chapters present results from the Challenge, including three competition tasks at WCCI and ECML 2018. The top best approaches submitted by participants are described, showing interesting contributions and innovating methods. The last two chapters propose novel contributions and highlight new applications that benefit from image/video inpainting.

For the last ten years, face biometric research has been intensively studied by the computer vision community. Face recognition systems have been used in mobile, banking, and surveillance systems. For face recognition systems, face spoofing attack detection is a crucial stage that could cause severe security issues in government sectors. Although effective methods for face presentation attack detection have been proposed so far, the problem is still unsolved due to the difficulty in the design of features and methods that can work for new spoofing attacks. In addition, existing datasets for studying the problem are relatively small which hinders the progress in this relevant domain. In order to attract researchers to this important field and push the boundaries of the state of the art on face anti-spoofing detection, we organized the Face Spoofing Attack Workshop and Competition at CVPR 2019, an event part of the ChaLearn Looking at People Series. As part of this event, we released the largest multi-modal face anti-spoofing dataset so far, the CASIA-SURF benchmark. The workshop reunited many researchers from around the world and the challenge attracted more than 300 teams. Some of the novel methodologies proposed in the context of the challenge achieved state-of-the-art performance. In this manuscript, we provide a comprehensive review on face anti-spoofing techniques presented in this joint event and point out directions for future research on the face anti-spoofing field.

This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning. Research progress in computer vision and pattern recognition has led to a variety of modeling techniques with almost human-like performance. Although these models have obtained astounding results, they are limited in their explainability and interpretability: what is the rationale behind the decision made? what in the model structure explains its functioning? Hence, while good performance is a critical required characteristic for learning machines, explainability and interpretability capabilities are needed to take learning machines to the next step to include them in decision support systems involving human supervision. This book, written by leading international researchers, addresses key topics of explainability and interpretability, including the following: * Evaluation and Generalization in Interpretable Machine Learning * Explanation Methods in Deep Learning * Learning Functional Causal Models with Generative Neural Networks * Learning Interpreatable Rules for Multi-Label Classification * Structuring Neural Networks for More Explainable Predictions * Generating Post Hoc Rationales of Deep Visual Classification Decisions * Ensembling Visual Explanations * Explainable Deep Driving by Visualizing Causal Attention * Interdisciplinary Perspective on Algorithmic Job Candidate Search * Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions * Inherent Explainability Pattern Theory-based Video Event Interpretations

This accessible and classroom-tested textbook/reference presents an introduction to the fundamentals of the emerging and interdisciplinary field of data science. The coverage spans key concepts adopted from statistics and machine learning, useful techniques for graph analysis and parallel programming, and the practical application of data science for such tasks as building recommender systems or performing sentiment analysis. Topics and features: provides numerous practical case studies using real-world data throughout the book; supports understanding through hands-on experience of solving data science problems using Python; describes techniques and tools for statistical analysis, machine learning, graph analysis, and parallel programming; reviews a range of applications of data science, including recommender systems and sentiment analysis of text data; provides supplementary code resources and data at an associated website.