For more than a decade, computer graphics (CG) researchers and visual effects experts have been fascinated with bringing photorealistic digital actors to the screen. Crossing the well-known "uncanny valley" in CG humans has been one of the most difficult and crucial challenges, due to hypersensitivity to synthetic humans lacking even the slightest and most subtle features of genuine human faces. Given sufficient resources and time, photorealistic renderings of digital characters have been achieved in recent years. Some of the most memorable cases are seen in blockbuster movies, such as The Curious Case of Benjamin Button, Furious 7, and Rogue One: A Star Wars Story, in which large teams of highly skilled digital artists use cutting-edge digitization technologies. Despite the progress of 3D-scanning solutions, facial animation systems, and advanced rendering techniques, weeks of manual work are still needed to produce even just a few seconds of animation.

Recent offline performance capture techniques approach the hard monocular reconstruction problem by fitting a blendshape or a multilinear face model to the input video sequence. Even geometric fine-scale surface detail is extracted via inverse shading-based surface refinement. Shi et al.16 achieve impressive results based on global energy optimization of a set of selected keyframes. Our model-based bundling formulation to recover actor identities is similar to their approach; however, we use robust and dense global photometric alignment, which we enforce with an efficient data-parallel optimization strategy on the Graphics Processing Unit (GPU).

Can you tell who is real and who is not? Artificial Intelligence is now able to create lifelike human faces from scratch. Researchers at NVIDIA have been working on creating realistic looking human faces from only a few source photos for years. For many people it's difficult to tell the difference between one of the faces generated below and an actual human face, can you spot which is which? The source image - the top row - are the only legitimate photographs of real people, the rest have been computer generated.

In this paper, we introduce a new task - interactive image editing via conversational language, where users can guide an agent to edit images via multi-turn dialogue in natural language. In each dialogue turn, the agent takes a source image and a natural language description from the user as the input, and generates a target image following the textual description. Two new datasets are created for this task,Zap-Seq and DeepFashion-Seq, collected via crowdsourcing. For this task, we propose a new Sequential Attention Genrative Adversarial Network (SeqAttnGAN) framework, which applies a neural state tracker to encode both source image and textual descriptions, and generates high quality images in each dialogue turn. To achieve better region specific text-to-image generation, we also introducean attention mechanism into the model. Experiments on the two datasets, including quantitative evaluation and user study, show that our model outperforms state-of-the-art ap-proaches in both image quality and text-to-image consistency.

Research on time-series similarity measures has emphasized the need for elastic methods which align the indices of pairs of time series and a plethora of non-parametric have been proposed for the task. On the other hand, deep learning approaches are dominant in closely related domains, such as learning image and text sentence similarity. In this paper, we propose \textit{NeuralWarp}, a novel measure that models the alignment of time-series indices in a deep representation space, by modeling a warping function as an upper level neural network between deeply-encoded time series values. Experimental results demonstrate that \textit{NeuralWarp} outperforms both non-parametric and un-warped deep models on a range of diverse real-life datasets.

On the surface, The Godfather, The Sixth Sense and Little Miss Sunshine appear to have little in common. But even though these films belong to different genres and have very different plots, technically they have the same "emotional arc" - a journey of highs and lows. Using artificial intelligence, we analysed more than 6,000 scripts from the past 80 years and discovered all films fall within six emotional arcs. These include the emotional rise of "rags to riches" films such as The Shawshank Redemption and the rise and fall of "man in a hole" films such as Who Framed Roger Rabbit. But which of these are the most successful, critically and commercially? Tragedies, which depict a continuing emotional fall, appear to receive the highest number of Oscar nominations per film.

There has been growing interest in using neural networks and deep learning techniques to create dialogue systems. Conversational recommendation is an interesting setting for the scientific exploration of dialogue with natural language as the associated discourse involves goal-driven dialogue that often transforms naturally into more free-form chat. This paper provides two contributions. First, until now there has been no publicly available large-scale dataset consisting of real-world dialogues centered around recommendations. To address this issue and to facilitate our exploration here, we have collected ReDial, a dataset consisting of over 10,000 conversations centered around the theme of providing movie recommendations. We make this data available to the community for further research. Second, we use this dataset to explore multiple facets of conversational recommendations. In particular we explore new neural architectures, mechanisms, and methods suitable for composing conversational recommendation systems. Our dataset allows us to systematically probe model sub-components addressing different parts of the overall problem domain ranging from: sentiment analysis and cold-start recommendation generation to detailed aspects of how natural language is used in this setting in the real world. We combine such sub-components into a full-blown dialogue system and examine its behavior.

Members of the House Judiciary Committee peppered the head of Google about potential bias against conservatives and Russian influence and misinformation; Gillian Turner reports. Google has been forced to shut down and "effectively end" its controversial China search engine project, code-named Project Dragonfly, after members of the company's privacy team raised complaints, according to a new report. The tech giant led by CEO Sundar Pichai was forced to close a data analysis system it was using for the controversial project, according to The Intercept, citing two sources familiar with the matter. The news outlet originally broke the news that Google had been considering launching the app-based search engine. Google has not yet responded to a request for comment from Fox News.

If you're still searching for an ideal gift for the smart home fanatic in your life, consider the Ring Video Doorbell 2. Right now, the Ring sequel is $170 at Best BuyRemove non-product link and many other retailers, but Best Buy sweetens the deal by adding a third-generation Amazon Echo Dot for free. Best Buy had a better early Black Friday deal when this bundle was $140. Still, $170 is a great price and well below the non-holiday pricing of $250. We reviewed the Ring Video Doorbell 2 in August 2017. We found the install process a little frustrating, but overall it's a solid improvement of the original.

Catchy Christmas songs can now be created by a special songwriting AI, taught by studying existing festive tunes. The system came up with catchy jingles with names like'Syllabub Chocolatebell', 'Peaches Twinkleleaves' and'Cocoa Jollyfluff'. Researchers from Made by AI trained a neural network by inputting one hundred Christmas tunes in the form of Musical Instrument Digital Interface (MIDI) files. It then picked out recurring themes, motifs, instruments and rhythms to generate its own hits. Scientists have trained an AI system to write its own catchy Christmas songs by teaching it existing festive tunes.