Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual semantics within and between character instances, making them not generalize well to arbitrary shape scene text. To address this issue, we make the first attempt to perform textual reasoning based on visual semantics in this paper. Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity. Then, these subgraphs are sequentially connected by their root nodes and merged into a complete graph. Based on this graph, we devise a graph convolutional network for textual reasoning (GTR) by supervising it with a cross-entropy loss. GTR can be easily plugged in representative STR models to improve their performance owing to better textual reasoning. Specifically, we construct our model, namely S-GTR, by paralleling GTR to the language model in a segmentation-based STR baseline, which can effectively exploit the visual-linguistic complementarity via mutual learning. S-GTR sets new state-of-the-art on six challenging STR benchmarks and generalizes well to multi-linguistic datasets. Code is available at https://github.com/adeline-cs/GTR.

Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream," specialized datasets. Generally, it is understood that more accurate models on the "upstream" dataset will provide better transfer accuracy "downstream". In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned - that is, compressed by sparsifiying their connections. Specifically, we consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, re-growth and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods.

Fully automatic semantic segmentation of highly specific semantic classes and complex shapes may not meet the accuracy standards demanded by scientists. In such cases, human-centered AI solutions, able to assist operators while preserving human control over complex tasks, are a good trade-off to speed up image labeling while maintaining high accuracy levels. TagLab is an open-source AI-assisted software for annotating large orthoimages which takes advantage of different degrees of automation; it speeds up image annotation from scratch through assisted tools, creates custom fully automatic semantic segmentation models, and, finally, allows the quick edits of automatic predictions. Since the orthoimages analysis applies to several scientific disciplines, TagLab has been designed with a flexible labeling pipeline. We report our results in two different scenarios, marine ecology, and architectural heritage.

The EU has concluded Microsoft's $19.7 billion acquisition of Nuance doesn't pose competition concerns. Nuance gained renown for originally creating the backend of that little old virtual assistant called Siri (you might have heard of it?) The company has since continued to focus on building its speech recognition capabilities and has a number of solutions which span particular industries such as healthcare to general omni-channel customer experience services. Earlier this year, Microsoft decided Nuance is worth coughing up $19.7 billion for. As such large deals often do, the proposed acquisition caught the eyes of several global regulators.

Disruptive technology is the technology that affects the normal operation of a market or an industry. Digital disruption entails established companies and start-ups alike enlisting new technologies in the fight to dislodge incumbents, protect entrenched positions, or to re-invent entire industries and business activities. And to remain disruptive in the market, it is really important to keep innovating. This is crucial because, innovations occur now and then in every industry, however, to be truly disruptive, and innovation must entirely transform a product or solution that historically was so complicated only a few could access it. On a minimum level, digital transformation enables an organization to address the needs of its customers more simply and directly. But through disruptive innovation, companies can offer a far better way to users of doing things that current incumbents simply cannot compete with. Artificial intelligence (AI), E-Commerce, cloud, social networking, Internet of Things, 5G, blockchain and other emerging technologies are being leveraged to blur the lines between industries, creating new business models and converging sectors. A company that disrupts its market is in a great position to take advantage of new opportunities. Sometimes offering something different can change the whole market for the better. Most of the top disruptive companies get this label by offering highly innovative products and services and here are 100 such top disruptive companies listed below. The company provides innovative, managed cloud services to help its customers succeed. With best-in-class service and technology, 403Tech protects companies against cybercrimes while enabling greater efficiency and productivity. Some of its popular services include desktop support, server support, wired and wireless networking, virus removal, data recovery, and backup and hosted cloud services. Aegeus Technologies aims to design and develop robotic technologies and solutions.

This month marks a year since we launched our focus series on the UN sustainable development goals (SDGs). Since then, we've published AI work pertaining to eight of the goals. We've had the pleasure of hearing from many experts with interesting stories to tell about their research. Here, we compile some of our favourite interviews and articles from the across the series. Interview with Lily Xu – applying machine learning to the prevention of illegal wildlife poaching Lily Xu tells us about her work applying machine learning and game theory to wildlife conservation.

Flux inversion is the process by which sources and sinks of a gas are identified from observations of gas mole fraction. The inversion often involves running a Lagrangian particle dispersion model (LPDM) to generate sensitivities between observations and fluxes over a spatial domain of interest. The LPDM must be run backward in time for every gas measurement, and this can be computationally prohibitive. To address this problem, here we develop a novel spatio-temporal emulator for LPDM sensitivities that is built using a convolutional variational autoencoder (CVAE). With the encoder segment of the CVAE, we obtain approximate (variational) posterior distributions over latent variables in a low-dimensional space. We then use a spatio-temporal Gaussian process emulator on the low-dimensional space to emulate new variables at prediction locations and time points. Emulated variables are then passed through the decoder segment of the CVAE to yield emulated sensitivities. We show that our CVAE-based emulator outperforms the more traditional emulator built using empirical orthogonal functions and that it can be used with different LPDMs. We conclude that our emulation-based approach can be used to reliably reduce the computing time needed to generate LPDM outputs for use in high-resolution flux inversions.

We introduce a curriculum learning algorithm, Variational Automatic Curriculum Learning (VACL), for solving challenging goal-conditioned cooperative multi-agent reinforcement learning problems. We motivate our paradigm through a variational perspective, where the learning objective can be decomposed into two terms: task learning on the current task distribution, and curriculum update to a new task distribution. Local optimization over the second term suggests that the curriculum should gradually expand the training tasks from easy to hard. Our VACL algorithm implements this variational paradigm with two practical components, task expansion and entity progression, which produces training curricula over both the task configurations as well as the number of entities in the task. Experiment results show that VACL solves a collection of sparse-reward problems with a large number of agents. Particularly, using a single desktop machine, VACL achieves 98% coverage rate with 100 agents in the simple-spread benchmark and reproduces the ramp-use behavior originally shown in OpenAI's hide-and-seek project. Our project website is at https://sites.google.com/view/vacl-neurips-2021.

In this paper we use The Quijote simulations in order to extract the cosmological parameters through Bayesian Neural Networks. This kind of models has a remarkable ability of estimating the associated uncertainty, which is one of the ultimate goals in the precision cosmology era. We demonstrate the advantages of BNNs for extracting more complex output distributions and non-Gaussianities information from the simulations.

The malware has been being one of the most damaging threats to computers that span across multiple operating systems and various file formats. To defend against the ever-increasing and ever-evolving threats of malware, tremendous efforts have been made to propose a variety of malware detection methods that attempt to effectively and efficiently detect malware. Recent studies have shown that, on the one hand, existing ML and DL enable the superior detection of newly emerging and previously unseen malware. However, on the other hand, ML and DL models are inherently vulnerable to adversarial attacks in the form of adversarial examples, which are maliciously generated by slightly and carefully perturbing the legitimate inputs to confuse the targeted models. Basically, adversarial attacks are initially extensively studied in the domain of computer vision, and some quickly expanded to other domains, including NLP, speech recognition and even malware detection. In this paper, we focus on malware with the file format of portable executable (PE) in the family of Windows operating systems, namely Windows PE malware, as a representative case to study the adversarial attack methods in such adversarial settings. To be specific, we start by first outlining the general learning framework of Windows PE malware detection based on ML/DL and subsequently highlighting three unique challenges of performing adversarial attacks in the context of PE malware. We then conduct a comprehensive and systematic review to categorize the state-of-the-art adversarial attacks against PE malware detection, as well as corresponding defenses to increase the robustness of PE malware detection. We conclude the paper by first presenting other related attacks against Windows PE malware detection beyond the adversarial attacks and then shedding light on future research directions and opportunities.