Several methods have recently been proposed for the Single Image Super-Resolution (SISR) problem. The current methods assume that a single low-resolution image can only yield a single high-resolution image. In addition, all of these methods use low-resolution images that were artificially generated through simple bilinear down-sampling. We argue that, first and foremost, the problem of SISR is an one-to-many mapping problem between the low-resolution and all possible candidate high-resolution images and we address the challenging task of learning how to realistically degrade and down-sample high-resolution images. To circumvent this problem, we propose SR-NAM which utilizes the Non-Adversarial Mapping (NAM) technique. Furthermore, we propose a degradation model that learns how to transform high-resolution images to low-resolution images that resemble realistically taken low-resolution photos. Finally, some qualitative results for the proposed method along with the weaknesses of SR-NAM are included.

The creators of the Python language are mulling a new proposal, PEP 622, that would finally bring a pattern matching statement syntax to Python. The new pattern matching statements would give Python programmers more expressive ways of handling structured data, without having to resort to workarounds. Pattern matching is a common feature of many programming languages, such as switch/case in C. It allows one of a number of possible actions to be taken based on the value of a given variable or expression. While Python has lacked a native syntax for pattern matching, it has been possible to emulate it with if/elif/else chains or a dictionary lookup. Supported pattern match types include literals, names, constant values, sequences, a mapping (basically, the presence of a key-value pair in the expression), a class, a mixture of the above, or any of those plus conditional expressions.

Ever since Android first came into existence in 2008, it has become the world's biggest mobile platform in terms of popularity and number of users. Over the years, Android developers have built advances in machine learning, features like on-device speech recognition, real-time video interactiveness, and real-time enhancements when taking a photo/selfie. In addition, image recognition with machine learning can enable users to point their smartphone camera at text and have it live-translated into 88 different languages with the help of Google Translate. Android users can even point your camera at a beautiful flower, use Google Lens to identify what type of flower that is, and then set a reminder to order a bouquet for someone. Google Lens is able to use computer vision models to expand and speed up web search and mobile experience.

Frequent pattern mining is a key area of study that gives insights into the structure and dynamics of evolving networks, such as social or road networks. However, not only does a network evolve, but often the way that it evolves, itself evolves. Thus, knowing, in addition to patterns' frequencies, for how long and how regularly they have occurred---i.e., their persistence---can add to our understanding of evolving networks. In this work, we propose the problem of mining activity that persists through time in continually evolving networks---i.e., activity that repeatedly and consistently occurs. We extend the notion of temporal motifs to capture activity among specific nodes, in what we call activity snippets, which are small sequences of edge-updates that reoccur. We propose axioms and properties that a measure of persistence should satisfy, and develop such a persistence measure. We also propose PENminer, an efficient framework for mining activity snippets' Persistence in Evolving Networks, and design both offline and streaming algorithms. We apply PENminer to numerous real, large-scale evolving networks and edge streams, and find activity that is surprisingly regular over a long period of time, but too infrequent to be discovered by aggregate count alone, and bursts of activity exposed by their lack of persistence. Our findings with PENminer include neighborhoods in NYC where taxi traffic persisted through Hurricane Sandy, the opening of new bike-stations, characteristics of social network users, and more. Moreover, we use PENminer towards identifying anomalies in multiple networks, outperforming baselines at identifying subtle anomalies by 9.8-48% in AUC.

AntWorks is a global, artificial intelligence (AI) and intelligent automation (IA) company that creates new possibilities with data through digitization, automation, and enterprise intelligence. As the world's only integrated intelligent automation platform (IAP), powered by fractal science principles and pattern recognition, ANTstein digitises every type of data for forward-thinking companies looking to achieve straight-through processing. Asheesh Mehra, Co-founder and Group CEO, AntWorks, tells us more. Asheesh Mehra: Today, automation of business processes has moved from being a nice-to-have to a necessity. Analyst firm, Forrester, predicted that business process automation can cut operating costs by up to 90%.

Google has said that it will begin fact-checking images that appear from its search results. Starting today, a'Fact Check' label will start appearing under thumbnails. Clicking on the thumbnail will show a quick summary of the fact check, including the claim and a rating from a fact-checker such as Politifact. This tool is organised using ClaimReview, which is a method used by publishers to indicate fact-checked content to search engines, which are already used by Google Search and Google News. Fact-checkers have to meet Google's criteria before they can be used as the source.

In this incredibly fast paced and noisy world, it's getting increasingly more difficult to get and retain people's attention. We're on 24 hour news overload, social media demands our attention, and the barrage of email and messages continues without losing steam. It's a relative wonder that companies can get their messages across and communicate their offerings to prospective customers. Leaping into the foray are AI solutions that are aiming to help identify potential customers, hyperpersonalize and tailor messages to their specific needs, and identify the most effective means to communicate the message. In fact, AI is particularly good at all those things: identifying potential customers through clustering and pattern matching, tailoring messages through AI-enabled hyperpersonalization, and finding the best times and means to communicate through pattern identification.

In May, the same week Facebook announced Shops, a way for businesses to set up online stores for customers across Facebook, WhatsApp, Messenger, and Instagram, the tech giant detailed the AI and machine learning systems behind its ecommerce experiences. Facebook said its goal is to one day develop an assistant that can serve up product recommendations on the fly, and that can learn preferences by analyzing images of what's in a person's wardrobe while allowing the person to try new items on self-replicas and sell apparel that others can preview. A flurry of Facebook-authored papers accepted to the Conference on Computer Vision and Pattern Recognition (CVPR) 2020 suggest the company is on its way to developing the components of this assistant. One paper describes an algorithm that uncovers and quantifies fashion influences from images taken around the world. Another demonstrates an AI model that generates 3D models of people from single images.

We present MCRapper, an algorithm for efficient computation of Monte-Carlo Empirical Rademacher Averages (MCERA) for families of functions exhibiting poset (e.g., lattice) structure, such as those that arise in many pattern mining tasks. The MCERA allows us to compute upper bounds to the maximum deviation of sample means from their expectations, thus it can be used to find both statistically-significant functions (i.e., patterns) when the available data is seen as a sample from an unknown distribution, and approximations of collections of high-expectation functions (e.g., frequent patterns) when the available data is a small sample from a large dataset. This feature is a strong improvement over previously proposed solutions that could only achieve one of the two. MCRapper uses upper bounds to the discrepancy of the functions to efficiently explore and prune the search space, a technique borrowed from pattern mining itself. To show the practical use of MCRapper, we employ it to develop an algorithm TFP-R for the task of True Frequent Pattern (TFP) mining. TFP-R gives guarantees on the probability of including any false positives (precision) and exhibits higher statistical power (recall) than existing methods offering the same guarantees. We evaluate MCRapper and TFP-R and show that they outperform the state-of-the-art for their respective tasks.

Deep neural networks (DNNs) are inherently susceptible to adversarial attacks even under black-box settings, in which the adversary only has query access to the target models. In practice, while it may be possible to effectively detect such attacks (e.g., observing massive similar but non-identical queries), it is often challenging to exactly infer the adversary intent (e.g., the target class of the adversarial example the adversary attempts to craft) especially during early stages of the attacks, which is crucial for performing effective deterrence and remediation of the threats in many scenarios. In this paper, we present AdvMind, a new class of estimation models that infer the adversary intent of black-box adversarial attacks in a robust and prompt manner. Specifically, to achieve robust detection, AdvMind accounts for the adversary adaptiveness such that her attempt to conceal the target will significantly increase the attack cost (e.g., in terms of the number of queries); to achieve prompt detection, AdvMind proactively synthesizes plausible query results to solicit subsequent queries from the adversary that maximally expose her intent. Through extensive empirical evaluation on benchmark datasets and state-of-the-art black-box attacks, we demonstrate that on average AdvMind detects the adversary intent with over 75% accuracy after observing less than 3 query batches and meanwhile increases the cost of adaptive attacks by over 60%. We further discuss the possible synergy between AdvMind and other defense methods against black-box adversarial attacks, pointing to several promising research directions.