Skip to main content

Home/ CIS Focal Issue/ Group items tagged recognition

Rss Feed Group items tagged

Maria Gurova

Pixar Vets Reinvent Speech Recognition So It Works for Kids | WIRED - 0 views

  • Though characters like Woody and Buzz Lightyear are wonderfully realistic and lovable, the relationship that kids have with them is largely one-sided. Kids can hear these characters talk—not only through movies, but games, toys, and other movie merchandise—but they can’t engage them.
  • It was this idea that inspired Jacob to team up with his former Pixar colleague, Martin Reddy, and launch a new company, ToyTalk. The San Francisco-based outfit develops mobile games that let kids have conversations with animated characters—dialogues that can last for hours
  • Known as PullString, it’s equal parts speech recognition engine and script writing tool, and it’s quite a departure from other speech rec tools developed by the likes of Microsoft, Google, and Apple. It’s tailored specifically to kids, whose sentence structure, pitch, and vocal tone have posed challenges for traditional tools.
  • ...7 more annotations...
  • Kids don’t want to ask a monkey character in a game what the weather will be on Tuesday. They want to sing him a song or ask him about life in the zoo.
  • But as he points out, the way today’s children use technology will likely dictate the tech landscape for decades to come. If you can get kids hooked on speech technology young, they’ll stay with it forever.
  • “The way kids talk and communicate is very different from how adults do, both in terms of how they use language and the fundamental frequencies that come out of their throats,
  • While ToyTalk uses existing third party technology for its raw speech recognition, it works with those partners to develop better recognition models using ToyTalk’s own data. Now, ToyTalk has a trove of some 20 million children’s utterances, which Jacob believes is the largest database of kids conversation in the world
  • “Virtual assistants are awesome when they can answer every question. In our case, it’s the opposite,” Jacob says. “I have to know a lot of things that I’m not able to answer, and redirect the conversation to something that is within character.”
  • And Jacob says some toy companies are already testing PullString to power apps based on existing characters.
  • this technology could give kids a whole new way to play that falls somewhere in between the playground and the imaginary friend. “I think at some deep level if we succeed, we’ll inspire the imagination of kids to talk about things they might not otherwise talk about,”
  •  
    the voice rec technology developed by ex-Pixar guy that is targeted to kids. It considers all nuances of kids speech behavior and analyses millions of kids conversations to make interaction with favorite characters within all possible media truly engaging
Maria Gurova

Frustrated? Confused? Learning software could watch your face for signals and match con... - 0 views

  • they were able to show that automated facial expression recognition could be nearly as accurate as human recognition in analyzing a wider range of student movements and gestures.
  • emotionally-aware software isn’t without ethical and privacy questions, but it opens the door to technology that’s even more engaging and that fits more seamlessly into our lives.
  • Those
  • ...2 more annotations...
  • types of technologies could be used to generate more personalized digital experiences
  • emotion-sensing technology could build on the already booming field of adaptive learning software that assesses students’ mastery and delivers content appropriate to their skill level.
  •  
    New face expression technology that is used for learning within computing classes, but can also be used in media and entertainment 
Maria Gurova

Using ToyTalk Technology, New Hello Barbie Will Have Real Conversations With Kids | Fas... - 1 views

  •  
    I've posted earlier about this ToyTalk company, they are founded by the guy who worked at Pixar for 20 years. The company develops the speech recognition technology, signed their first deal with a big toy company - Mattel. They are going to develop Barbie doll that will be able to sustain meaningful conversations with kids
Vladimir Antonov

Disney's New Technology Turns Facial Expressions Into Animation In Real Time - DesignTA... - 1 views

  • new facial recognition software that can capture a person’s expressions and convert them into animation in real-time
  • which records facial features and movements, like wrinkles on an actor’s face, which previously was difficult to include in an animated character.
  • software will be useful for their animation process as it can be used by anyone at any time
  •  
    The studio has come up with a new facial recognition software that can capture a person's expressions and convert them into animation in real-time. In a research paper released by Disney, the team describes the "Real-Time High-Fidelity Facial Performance Capture", which records facial features and movements, like wrinkles on an actor's face, which previously was difficult to include in an animated character. 
Ilya Vorobiev

Microsoft Hyperlapse: time lapse your videos - 1 views

    • Ilya Vorobiev
       
      Every vacation or important event we produce a lot of videos and photos that are hardly consumable in the future. This is big a challenge for image and video recognition technologies. Hyperlapse is a great example in this field that helps to convert minutes or hours of videos into short simple and nice clip. Video - https://www.youtube.com/watch?v=wZcBLc4ifuQ
  • Microsoft Hyperlapse is a new technology that creates smooth and stabilized time lapses from first-person videos.
  • you can time lapse those experiences, distilling them into easily consumable, enjoyable experiences.
Anton Vorykhalov

Smart Billboards Identify Vehicles to Target Ads | Digital Trends - 0 views

  • Smart billboards will identify car models and target ads to drivers
  • Some day in the not-too-distant future ads you see on billboards will be there simply because of the make, model, and year of the vehicle you’re driving. Smart data storage company Cloudian and Japanese advertising company Dentsu are launching just such a program in Japan this fall, as reported by CNN Money.
  • Cloudian and Dentsu tested smart billboard vehicle recognition earlier this year with impressive results. Combining big data and deep learning, the test identified vehicles in traffic correctly 94 percent of the time.
  • ...1 more annotation...
  • Once the system has identified a vehicle, it displays a targeted ad on the LED billboard for as long as five seconds. The choice of ads to be displayed to specific vehicles is determined by the advertisers. For example, people driving a five-year old vehicle might see an ad for a newer model of the same car. Truck drivers might be shown ads for upcoming trucker-friendly stops.
Anton Vorykhalov

Goxip is a 'shoppable Instagram' for fashion followers in Asia | TechCrunch - 1 views

  • Gimenez’s take is “shoppable Instagram:” an app that uses image recognition and a large collection of retailers — 400-500 merchants selling over two million items from upwards of 15,000 brands — to create a more engaging and ultimately more fruitful social commerce experience.
  • Social commerce, the idea of buying products listed on social media sites, is huge in Asia.
  • “When you see anything online or on Instagram, the frustration is that you can’t shop even when people are using it as merchants,
Anna Dubinina

Bentley подбирает авто по выражению лиц покупателей - 0 views

  •  
    Bentley Inspirator анализирует эмоции покупателя, которые он испытывает во время специального фильма, а также с помощью камеры следит за мимическими изменениями лица человека. Затем, исходя из результатов, программа предлагает цвет, конфигурацию автомобиля, подходящие именно для данного покупателя.
Vladimir Antonov

Soon, Gmail's AI Could Reply to Your Email for You | WIRED - 0 views

  • what’s called “deep learning”—a form of artificial intelligence that’s rapidly reinventing a wide range of online services—the company is beefing up its Inbox by Gmail app so that it can analyze the contents of an email and then suggest a few (very brief) responses
  • The idea is that you can rapidly respond to someone while on the go—without having to manually tap a fresh message into your smartphone keyboard.
  • system learns to generate appropriate replies by analyzing scads of email conversations from across Google’s Gmail service
  • ...3 more annotations...
  • neural network—a vast network of machines that approximates the web of neurons in the human brain—and this neural network analyzes the information in order to “learn” a particular task.
  • Google’s Smart Reply system doesn’t always get things right. But that’s part of the reason the company provides three potential replies to each email—not just one.
  • The system uses what’s called a “long short-term-memory,” or LSTM, neural network. Essentially, this is a neural net that exhibits something akin to human memory. It can “remember” the beginning of an email as it’s parsing the end—and that helps it, on some level, understand this natural language
  •  
    This technology could be developed further to other areas, to tailored made games for kids for example, that are adopt to each individual gaming style so kids find that games are actually made specially for them what makes their experience really personal and unique.
al_semenchenko

Knightscope releases fleet of autonomous crime fighting security robots - Interesting E... - 2 views

  • The 5 feet, 300 pound scooting robot is stacked with quite the resume of capabilities and because it delivers real-time data to a secure monitored location, it will minimize threats for human security officers that take on these dangerous jobs.
  • this venture gets some backing as security companies are looking for more innovative solutions to counter their turnover rates, some as high as 400%, Knightscope reports.
  • hese autonomous patrol units are doing the jobs that may be too dangerous for people and doing them better, backed with day and night 360-degree video capture, infrared and thermal scanning, proximity sensors, radar for real-time 3D mapping, and optical character recognition, allowing the K5 to never forget a face. Knightscope confirmed though that K5s are NOT intended to replace law enforcement, instead “to help and assist officers, improve response times and keep them out of harm’s way if possible.”
  •  
    Robots assisting police officers in monitoring dangerous areas. Also available for home security.
1 - 10 of 10
Showing 20 items per page