Fox News Flash top entertainment and celebrity headlines are here. Check out what's clicking today in entertainment. Drew Barrymore is among the legion of fans who have been wrapped up in Netflix's latest hit, "Bridgerton." The "50 First Dates" and "Ever After" star invited Phoebe Dynevor and Regé-Jean Page on to her talk show to discuss the period drama. During their appearance on Friday, Barrymore revealed that the show's steamier scenes inspired the 45-year-old to try her hand once again at dating apps.

Scalable sensor simulation is an important yet challenging open problem for safety-critical domains such as self-driving. Current work in image simulation either fail to be photorealistic or do not model the 3D environment and the dynamic objects within, losing high-level control and physical realism. In this paper, we present GeoSim, a geometry-aware image composition process that synthesizes novel urban driving scenes by augmenting existing images with dynamic objects extracted from other scenes and rendered at novel poses. Towards this goal, we first build a diverse bank of 3D objects with both realistic geometry and appearance from sensor data. During simulation, we perform a novel geometry-aware simulation-by-composition procedure which 1) proposes plausible and realistic object placements into a given scene, 2) renders novel views of dynamic objects from the asset bank, and 3) composes and blends the rendered image segments. The resulting synthetic images are photorealistic, traffic-aware, and geometrically consistent, allowing image simulation to scale to complex use cases. We demonstrate two such important applications: long-range realistic video simulation across multiple camera sensors, and synthetic data generation for data augmentation on downstream segmentation tasks.

Despite the recent attention to DeepFakes and other forms of image manipulations, one of the most prevalent ways to mislead audiences is the use of unaltered images in a new but false context. To address these challenges and support fact-checkers, we propose a new method that automatically detects out-of-context image and text pairs. Our core idea is a self-supervised training strategy where we only need images with matching (and non-matching) captions from different sources. At train time, our method learns to selectively align individual objects in an image with textual claims, without explicit supervision. At test time, we check for a given text pair if both texts correspond to same object(s) in the image but semantically convey different descriptions, which allows us to make fairly accurate out-of-context predictions. Our method achieves 82% out-of-context detection accuracy. To facilitate training our method, we created a large-scale dataset of 203,570 images which we match with 456,305 textual captions from a variety of news websites, blogs, and social media posts; i.e., for each image, we obtained several captions.

Samsung has unveiled its latest range of flagship smartphones, with three models ranging in price from £769 ($799) to £1,149 ($1,199). The S21 range from the South Korean tech giant features an entry-level model, the mid-range Plus, and the Ultra – which is the first S Series phone to be compatible with the Samsung's S-Pen stylus. The stand-out feature on all three devices is the upgraded rear camera system, which was heavily leaked ahead of today's announcement and features night and portrait mode as well as its 100x'space zoom'. Pre-orders of the handsets open today, and the phones will be available as of January 29. The Ultra also comes with S-pen compatibility, the first Galaxy device to do so.

Horror films were wildly popular on streaming platforms over the past year, and 2020 saw the horror genre take home its largest share of the box office in modern history.1 In a year where the world was stricken by real horrors, why were many people escaping to worlds full of fictional horrors? As odd as it may sound, the fact that people were more anxious in 2020 may be one reason why horror films were so popular. A look at typical horror fans may provide some clues about the nature of this peculiar phenomenon. For example, horror fans often mention their own anxiety and how horror helps them deal with it.

British illustrator and visual-effects director Gavin Rothery makes his feature debut with this artificial intelligence thriller: a tale of love, death and robotics that has some nicely creepy moments. Set in 2038, it centres on lonely computer scientist George Almore (Divergent's Theo James), who is holed up in a remote research facility in Japan secretly working on an android version of his wife Jules (Stacy Martin); she has died in a car crash. His prototype, J3 (also played by Martin), is his closest yet to the real thing: a highly advanced humanoid with spookily pale skin who looks like she might be the ghost of his dead wife. Poor old J1 and J2, his earlier, clunkier prototypes: they look on bitterly as the newer, sleeker model gets all George's attention. The movie opens with sweeping helicopter shots over a snowy forest.

Withtheadventofsocialmedia,therehasbeenanextremely rapid increase in the content shared online. Consequently, the propagation of fake news and hostile messages on social media platforms has also skyrocketed. In this paper, we address the problem of detecting hostile and fake content in the Devanagari (Hindi) script as a multi-class, multi-label problem. Using NLP techniques, we build a model that makes use of an abusive language detector coupled with features extracted via Hindi BERT and Hindi FastText models and metadata. Our model achieves a 0.97 F1 score on coarse grain evaluation on Hostility detection task. Additionally, we built models to identify fake news related to Covid-19 in English tweets. We leverage entity information extracted from the tweets along with textual representations learned from word embeddings and achieve a 0.93 F1 score on the English fake news detection task.

As Wednesday draws to a close, so does a grand social experiment: the first-ever online-only CES. In the end, the experience was invariably different. We particularly missed being able to wander The Sands and have learn about smaller, up-and-coming startups. And if seeing is believing, the oddest entries at the show remained locked behind our computer screen, with no chance of getting hands-on time. And yet, we were kept busy this week. Most of the usual tech giants had news to share, and many of those were able to show us their wares in person, ahead of the three-day gadget extravaganza.

Say the word Apple today and we think of Steve Jobs' multi-billion-dollar technology company that spawned the iPhone and the Mac computer. But a decade before the California-based firm was even founded, Apple Electronics, a subsidiary of the Beatles' record label Apple, was working on several pioneering inventions – some of which were precursors of commonly available products today. Apple Electronics was led by Alexis Mardas, a young electronics engineer and inventor originally from Athens in Greece, known to the Beatles as Magic Alex. He died on this day in 2017, aged 74, and was one of the most colourful and mysterious characters in the Beatles' story. Dressed in a white lab coat in his London workshop, Mardas created prototypes of inventions that were set to be marketed and sold. These included the'composing typewriter' – powered by an early example of sound recognition – and a phone with advanced memory capacity.

In highway scenarios, an alert human driver will typically anticipate early cut-in/cut-out maneuvers of surrounding vehicles using visual cues mainly. Autonomous vehicles must anticipate these situations at an early stage too, to increase their safety and efficiency. In this work, lane-change recognition and prediction tasks are posed as video action recognition problems. Up to four different two-stream-based approaches, that have been successfully applied to address human action recognition, are adapted here by stacking visual cues from forward-looking video cameras to recognize and anticipate lane-changes of target vehicles. We study the influence of context and observation horizons on performance, and different prediction horizons are analyzed. The different models are trained and evaluated using the PREVENTION dataset. The obtained results clearly demonstrate the potential of these methodologies to serve as robust predictors of future lane-changes of surrounding vehicles proving an accuracy higher than 90% in time horizons of between 1-2 seconds.