If someone told me, a couple of weeks prior, that I would be taking pictures of everything that crossed my path, I would have laughed in their face. But there I was, sitting on the sidewalk, looking to capture the perfect shot that would allow me to learn a little more about the world I am a part of: the expression of the guide dog who is always by my side; the bustle of a busy street full of buildings, cars, and signs; the box of desserts I just bought, wondering whether it looked appetizing enough to bring to a family dinner. I can't see these things, which are so easy to take for granted, with my own eyes. But A.I. has now brought me as close to being able to do so as I'll probably ever be. I was born totally blind, and my visual world has always been determined by what well-meaning people can tell me about my surroundings. To appreciate all the details of a room or to read a menu in a restaurant, I was dependent on someone else.

Fox News Flash top entertainment and celebrity headlines are here. Check out what's clicking today in entertainment. Cloris Leachman, known for her decades-long career in film, television and beyond, has died at the age of 94. She died on Wednesday of natural causes, her rep told Fox News. Leachman was a history-making actress, having racked up more Emmy award wins than any other performer in the business with eight awards for primetime programming and an additional Daytime Emmy for appearing in "ABC Afterschool Specials."

Transfer learning research attempts to make model induction transferable across different domains. This method assumes that specific information regarding to which domain each instance belongs is known. This paper helps to extend the capability of transfer learning for linear regression problems to situations where the domain information is uncertain or unknown; in fact, the framework can be extended to classification problems. For normal datasets, we assume that some latent domain information is available for transfer learning. The instances in each domain can be inferred by different parameters. We obtain this domain information from the distribution of the regression coefficients corresponding to the explanatory variable $x$ as well as the response variable $y$ based on a Dirichlet process, which is more reasonable. As a result, we transfer not only variable $x$ as usual but also variable $y$, which is challenging since the testing data have no response value. Previous work mainly overcomes the problem via pseudo-labelling based on transductive learning, which introduces serious bias. We provide a novel framework for analysing the problem and considering this general situation: the joint distribution of variable $x$ and variable $y$. Furthermore, our method controls the bias well compared with previous work. We perform linear regression on the new feature space that consists of different latent domains and the target domain, which is from the testing data. The experimental results show that the proposed model performs well on real datasets.

In this paper, we present a novel approach for the task of eXplainable Question Answering (XQA), i.e., generating natural language (NL) explanations for the Visual Question Answering (VQA) problem. We generate NL explanations comprising of the evidence to support the answer to a question asked to an image using two sources of information: (a) annotations of entities in an image (e.g., object labels, region descriptions, relation phrases) generated from the scene graph of the image, and (b) the attention map generated by a VQA model when answering the question. We show how combining the visual attention map with the NL representation of relevant scene graph entities, carefully selected using a language model, can give reasonable textual explanations without the need of any additional collected data (explanation captions, etc). We run our algorithms on the Visual Genome (VG) dataset and conduct internal user-studies to demonstrate the efficacy of our approach over a strong baseline. We have also released a live web demo showcasing our VQA and textual explanation generation using scene graphs and visual attention.

We've been following Dex-Net's progress towards universal grasping for several years now, and today in a paper in Science Robotics, UC Berkeley is presenting Dex-Net 4.0. The new and exciting bit about this latest version of Dex-Net is that it's able to successfully grasp 95 percent of unseen objects at a rate of 300 per hour, thanks to some added ambidexterity that lets the robot dynamically choose between two different kinds of grippers. For some context, humans are able to pick objects like these nearly twice as fast, between 400 and 600 picks per hour. And my guess would be that human success rates are as close to 100 percent as you can reasonably expect, perhaps achieving 100 percent if you allow for multiple tries to pick the same object. We set a very, very high bar for the machines.

Google's next iPhone killer, the Pixel XL has been revealed in a new leaked image. According to Android Police, the picture shows a second generation Pixel XL, the larger of the two Pixel devices, with a 6inch screen. It is believed the handset will be made by LG, and will feature a radical'squeezable' frame. According to Android Police, the picture shows a second generation Pixel XL, the larger of the two Pixel devices, with a 6inch screen. The site says it is'exceptionally confident' the image is real.

Two Ohio inmates used discarded computers to access their prison's network to create passes to get into restricted areas and plan a tax fraud scheme. A state watchdog released a report on Tuesday stating a lack of supervision at the Marion Correctional Institution allowed the prisoners to hide computers in the ceiling and run wiring to connect them to the network. The two tech-savvy convicts were also able to access the internal records of other inmates as part of their scheme. One of the prisoners planned to steal the identity of a fellow inmate and file tax returns under that inmate's name, officials said. Two Ohio inmates used discarded computers to access their prison's network to create passes to get into restricted areas and plan a tax fraud scheme.

In this paper, we propose a bottom-up approach to generating short descriptive sentences from images, to enhance scene understanding. We demonstrate automatic methods for mapping the visual content in an image to natural spoken or written language. We also introduce a human-in-the-loop evaluation strategy that quantitatively captures the meaningfulness of the generated sentences. We recorded a correctness rate of 60.34% when human users were asked to judge the meaningfulness of the sentences generated from relatively challenging images. Also, our automatic methods compared well with the state-of-the-art techniques for the related computer vision tasks.