Summarizing video content is an important task in many applications. This task can be defined as the computation of the ordered list of actions present in a video. Such a list could be extracted using action detection algorithms. However, it is not necessary to determine the temporal boundaries of actions to know their existence. Moreover, localizing precise boundaries usually requires dense video analysis to be effective. In this work, we propose to directly compute this ordered list by sparsely browsing the video and selecting one frame per action instance, task known as action spotting in literature. To do this, we propose ActionSpotter, a spotting algorithm that takes advantage of Deep Reinforcement Learning to efficiently spot actions while adapting its video browsing speed, without additional supervision. Experiments performed on datasets THUMOS14 and ActivityNet show that our framework outperforms state of the art detection methods. In particular, the spotting mean Average Precision on THUMOS14 is significantly improved from 59.7% to 65.6% while skipping 23% of video.

ABSTRACT Mirror Ritual is an interactive installation that challenges the existing paradigms in our understanding of human emotion and machine perception. In contrast to prescriptive interfaces, the work's real-time affective interface engages the audience in the iterative conceptualisation of their emotional state through the use of affectively-charged machine generated poetry. The audience are encouraged to make sense of the mirror's poetry by framing it with respect to their recent life experiences, effectively'putting into words' their felt emotion. This process of affect labelling and contextualisation works to not only regulate emotion, but helps to construct the rich personal narratives that constitute human identity. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.

PyTorch continues to enjoy an impressive level of general interest, judging by online searches and, more importantly, continues to increase its rate of adoption. PyTorch is thought of as powerful and flexible, a pair of characteristics which are welcome by researchers. However, PyTorch has, in the past, been susceptible to criticism by practitioners for its lack of a simplified higher-level API, such as TensorFlow's Keras. This situation has recently changed. Concisely defined via the project's developers: Above requires no user intervention (except single call to torchlayers.build)

Amazon Web Services Inc. announced today that it's adding support for PyTorch models with its Amazon Elastic Inference service, which it said will help developers reduce the costs of deep learning inference by as much as 75% in some cases. Amazon Elastic Inference is a service launched in late 2018 that enables customers to attach graphics processing unit-powered inference acceleration to a standard Amazon EC2 instance. Inference refers to the process of making predictions using a trained deep learning model. PyTorch is an open-source machine learning library that was first developed by Facebook Inc. It's used primarily for applications such as computer vision and natural language processing.

Insilico Medicine is pleased to announce that it has entered into a research collaboration with Boehringer Ingelheim to utilize Insilico's generative machine learning technology and proprietary Pandomics Discovery Platform with the aim of identifying potential therapeutic targets implicated in a variety of diseases. "Insilico Medicine is very impressed with the Research Beyond Borders group at Boehringer Ingelheim capabilities in the search of potential drug targets. In this collaboration, Insilico will provide additional AI capabilities to discover novel targets for a variety of diseases to benefit the patients worldwide. We are very happy to partner with such an advanced group," said Alex Zhavoronkov, PhD, founder, and CEO of Insilico Medicine. "We believe that Insilico's exclusive Pandomics platform will provide huge boost to our ability to explore and identify drug targets. We look forward to using AI to significantly improve the drug discovery process and contribute to human health," said from Dr. Weiyi Zhang, Head of External Innovation Hub, Boehringer Ingelheim Greater China.

"Everyone has innate creative capabilities, she said, "and this is a tool that helps push those boundaries even further." Hector Postigo, an associate professor at the Klein College of Media and Communication at Temple University, began experimenting with GPT-2 shortly after it was released. His first idea was to train the program to automatically write a simple policy statement about ethics policies for A.I. systems. After "fine-tuning" GPT-2 with a large collection of human-written articles, position papers, and laws collected in 2019 on A.I., big data and algorithms, he seeded the program with a single sentence: "Algorithmic decision-making can pose dangers to human rights." The program created a short essay that began, "Decision systems that assume predictability about human behavior can be prone to error.

In this regular column, we'll bring you all the latest industry news centered around our main topics of focus: big data, data science, machine learning, AI, and deep learning. Our industry is constantly accelerating with new products and services being announced everyday. Fortunately, we're in close touch with vendors from this vast ecosystem, so we're in a unique position to inform you about all that's new and exciting. Our massive industry database is growing all the time so stay tuned for the latest news items describing technology that may make you and your organization more competitive. Mist Systems, a Juniper Networks company and a pioneer in secure AI-driven networks, announced the launch of Mist Premium Analytics, a new service that offers enterprises a comprehensive network visibility and business insights platform to support the increasing demands of digital transformation projects.

We present the Dayton Annotated LiDAR Earth Scan (DALES) data set, a new large-scale aerial LiDAR data set with over a half-billion hand-labeled points spanning 10 square kilometers of area and eight object categories. Large annotated point cloud data sets have become the standard for evaluating deep learning methods. However, most of the existing data sets focus on data collected from a mobile or terrestrial scanner with few focusing on aerial data. Point cloud data collected from an Aerial Laser Scanner (ALS) presents a new set of challenges and applications in areas such as 3D urban modeling and large-scale surveillance. DALES is the most extensive publicly available ALS data set with over 400 times the number of points and six times the resolution of other currently available annotated aerial point cloud data sets. This data set gives a critical number of expert verified hand-labeled points for the evaluation of new 3D deep learning algorithms, helping to expand the focus of current algorithms to aerial data. We describe the nature of our data, annotation workflow, and provide a benchmark of current state-of-the-art algorithm performance on the DALES data set.

The big problem for neural network models which are trained to count instances is that whenever test range goes high training range generalization error increases i.e. they are not good generalizers outside training range. Consider the case of automating cell counting process where more dense images with higher cell counts are commonly encountered as compared to images used in training data. By making better predictions for higher ranges of cell count we are aiming to create better generalization systems for cell counting. With architecture proposal of neural arithmetic logic units (NALU) for arithmetic operations, task of counting has become feasible for higher numeric ranges which were not included in training data with better accuracy. As a part of our study we used these units and different other activation functions for learning cell counting task with two different architectures namely Fully Convolutional Regression Network and U-Net. These numerically biased units are added in the form of residual concatenated layers to original architectures and a comparative experimental study is done with these newly proposed changes . This comparative study is described in terms of optimizing regression loss problem from these models trained with extensive data augmentation techniques. We were able to achieve better results in our experiments of cell counting tasks with introduction of these numerically biased units to already existing architectures in the form of residual layer concatenation connections. Our results confirm that above stated numerically biased units does help models to learn numeric quantities for better generalization results.

Recently, NLP has seen a surge in the usage of large pre-trained models. Users download weights of models pre-trained on large datasets, then fine-tune the weights on a task of their choice. This raises the question of whether downloading untrusted pre-trained weights can pose a security threat. In this paper, we show that it is possible to construct ``weight poisoning'' attacks where pre-trained weights are injected with vulnerabilities that expose ``backdoors'' after fine-tuning, enabling the attacker to manipulate the model prediction simply by injecting an arbitrary keyword. We show that by applying a regularization method, which we call RIPPLe, and an initialization procedure, which we call Embedding Surgery, such attacks are possible even with limited knowledge of the dataset and fine-tuning procedure. Our experiments on sentiment classification, toxicity detection, and spam detection show that this attack is widely applicable and poses a serious threat. Finally, we outline practical defenses against such attacks. Code to reproduce our experiments is available at https://github.com/neulab/RIPPLe.