A storyboard is a sequence of images to illustrate a story containing multiple sentences, which has been a key process to create different story products. In this paper, we tackle a new multimedia task of automatic storyboard creation to facilitate this process and inspire human artists. Inspired by the fact that our understanding of languages is based on our past experience, we propose a novel inspire-and-create framework with a story-to-image retriever that selects relevant cinematic images for inspiration and a storyboard creator that further refines and renders images to improve the relevancy and visual consistency. The proposed retriever dynamically employs contextual information in the story with hierarchical attentions and applies dense visual-semantic matching to accurately retrieve and ground images. The creator then employs three rendering steps to increase the flexibility of retrieved images, which include erasing irrelevant regions, unifying styles of images and substituting consistent characters. We carry out extensive experiments on both in-domain and out-of-domain visual story datasets. The proposed model achieves better quantitative performance than the state-of-the-art baselines for storyboard creation. Qualitative visualizations and user studies further verify that our approach can create high-quality storyboards even for stories in the wild.

GuessWhat?! is a visual dialogue task between a guesser and an oracle. The guesser aims to locate an object supposed by the oracle oneself in an image by asking a sequence of Yes/No questions. Asking proper questions with the progress of dialogue is vital for achieving successful final guess. As a result, the progress of dialogue should be properly represented and tracked. Previous models for question generation pay less attention on the representation and tracking of dialogue states, and therefore are prone to asking low quality questions such as repeated questions. This paper proposes visual dialogue state tracking (VDST) based method for question generation. A visual dialogue state is defined as the distribution on objects in the image as well as representations of objects. Representations of objects are updated with the change of the distribution on objects. An object-difference based attention is used to decode new question. The distribution on objects is updated by comparing the question-answer pair and objects. Experimental results on GuessWhat?! dataset show that our model significantly outperforms existing methods and achieves new state-of-the-art performance. It is also noticeable that our model reduces the rate of repeated questions from more than 50% to 21.9% compared with previous state-of-the-art methods.

A major wildfire spread through Colorado, and I spent long hours locating shelters, identifying evacuation routes and piecing together satellite imagery. As the Fourmile Canyon Fire devastated areas to the west of Boulder, ultimately destroying 169 homes and causing $217 million in damage, my biggest concerns were ensuring that people could safely evacuate and first responders had the best chance of keeping the fire at bay. I spent it sitting comfortably in my home in Bloomington, Indiana, a thousand miles away from the action. I was a volunteer, trying to help fire victims. I had created a webpage to aggregate data about the fire, including the location of shelters and the latest predictions of fire spread.

Believe it or not, but AI influencers are actually a thing, and during 2018 this new and rather unexplored market experienced impressive growth. Chances are that you've heard about AI influencers before and are curious to learn more. Or perhaps this is the first time you've heard about the phenomenon and you're eager to learn more about AI influencers and digital models. Regardless, you have come to the right place, and on the page below we'll guide you through everything you need to know about AI influencers and the future of influencer marketing. The concept of AI influencers has actually been around since 2016 and in some cases even earlier than that.

Edy Portmann explains why it is important for schools to reinforce the scientist that lies within every child. He talks about intelligent learning systems and how they can be used to build collective intelligence, as well as to encourage students' creativity and help them learn to work together to solve problems. Sabine Gysi: In discussions of the digital transformation in education, skeptics often complain that reality is being pushed aside in favor of the digital. Does it make sense to look at the "real" world and the digital world as opposites? Edy Portmann: I've heard some teachers say that technological tools are "artificial."

The "Global Artificial Intelligence in Supply Chain Market Analysis to 2027" is a specialized and in-depth study of the technology, media and telecommunication industry with a special focus on the global market trend analysis. The report aims to provide an overview of the Artificial Intelligence in Supply Chain market with detailed market segmentation by components, technology, application, and industry vertical, and geography. The global artificial intelligence in supply chain market is expected to witness high growth during the forecast period. The report provides key statistics on the market status of the leading artificial intelligence in supply chain market players and offers key trends and opportunities in the market. The reports cover key developments in the artificial intelligence in supply chain market as organic and inorganic growth strategies.

Powerful new technologies have the potential to radically transform both science and society. In science, as Douglas Robertson describes in Phase Change (2003), a new technology like the microscope, the telescope, and the calculus can profoundly alter the questions we ask, and advance our ability to better understand nature. Society, visibly, can also be transformed by technology, as we've seen with examples ranging from the steam engine and the telegraph to automation and the internet. The catch is, this transformation doesn't occur overnight – far from it. The remarkable and often maddening aspect of innovation (as I've discussed here, here) is the exceptionally long time it takes between the time a technology is originally invented and the time when people figure out how to use it most effectively.

"It cannot make moral decisions easily and can lead to disasters. AI can cause a lot of harm," it continued. Artificial intelligence can only make decisions it has been programmed for and "it is not possible to program for all scenarios, only humans can." Then, the machine switched sides, delivering the opposing team's argument. Artificial intelligence "will be a great advantage as it will free up more time from having to do mundane and repetitive tasks," it said, its voice embodied by a blue waveform on a screen set into a two-meter-tall sleek black monolith-like pillar.

Suffice it to say that they are a form of non-linear regression tool whose underlying design found inspiration in a simplification of the basic architecture of the human brain. Many of the great advances that we have experienced in Machine Learning over the last few years make use of neural networks. The basic algorithm has been around for decades -- but it has come into its own as processing power and data availability have steadily increased. For this project we implemented our neural network in Python using the popular TensorFlow library from Google. The characteristics of our neural network, and in particular its complexity, were chosen to balance precision and generalization.

This publication draws on a wide range of expertise to illuminate the year ahead. Even so, all our contributors have one thing in common: they are human. But advances in technology mean it is now possible to ask an artificial intelligence (AI) for its views on the coming year. We asked an AI called GPT-2, created by Openai, a research outfit. GPT-2 is an "unsupervised language model" trained using 40 gigabytes of text from the internet.