The "Ok Google" command has expanded since the debut of Android KitKat, allowing devices to respond in various smart ways to those two words. Now, Google Maps on Android has this ability too, whether you're in the middle of a road trip or doing something else. Once it's enabled in settings, you can choose whether it works only while Maps is open or from any screen. Say the magic phrase then follow it up with something like "find a gas station" or "How's traffic ahead?" and it will let you know. Existing Google Maps voice commands like "What's my ETA?" work too, plus new addition like the ability to turn traffic display on or off.
In this paper we describe a qualitative approach for natural language communication about vehicle traffic. It is an intuitive and simple model that can be used as the basis for defining more detailed position descriptions and transitions. It can also function as a framework for relating different aggregation levels. We apply a diagrammatic abstraction of traffic that mirrors the different possible interpretations of it and with this the different mental abstractions that humans might make. The abstractions are kept in parallel and according to the communicative context it will be switched to the corresponding interpretation.
Researchers have found a simple way to prevent ISPs from spying on you through your Internet of Things (IoT) devices. IoT and smart home products are becoming more common in households worldwide. Whether it be Amazon's Alexa voice assistant, Google Home, or smart lighting systems, IoT has become an established industry in itself with countless products now on the market. The majority of connected devices require Internet access to function, and when this avenue is carved into your home, there is also the risk of compromise, spying, and data theft. Shodan is a prime example of IoT security gone wrong.
Discovering motion activities in videos is a key problem in computer vision, with applications in scene analysis, video categorization, and video indexing. In this paper, we propose a method that uses probabilistic topic modeling for discovering patterns of motion that occur in a given activity. Our method also identifies how the discovered patterns of motion relate to one another in space and time. The topic-modeling approach used by our method is the relational topic model. Our experiments show that our method is able to discover relevant spatio-temporal motion patterns in videos.
Google is adding a way to understand data with voice-based navigation that's fueled by artificial intelligence. Today, the company is launching a tool for Google Analytics that will allow marketers to ask questions about data, which could free up analysts to focus more on strategy and less on basic queries. The feature--which begins rolling out Wednesday and will become available for Android and iOS devices in the next few weeks--is meant to cut down the number of steps it takes to perform tasks such as checking online revenue data or website traffic. According to Babak Pahlavan, Google's senior director of measurement and analytics, the feature will allow users to speak to the system in a way that's similar to Google's flagship search product. Natural language processing will guide the voice-based navigation, and the technology uses artificial intelligence so that the more it's used, the smarter it gets, both on a macro level and on a user-by-user basis.