[Nfbk] {Spam?} Re: [Nfbktad] {Disarmed} De cades of computer vision research, one âSwiss Army knifeâ
David Andrews
dandrews at visi.com
Thu Apr 7 02:33:18 UTC 2016
It is not a list, it means the message was
scanned for viruses etc., along the way, and found ok.
Dave
At 08:50 AM 4/6/2016, you wrote:
>
>Good morning,
>
>I keep seeing things with {disarmed}. What is
>this? Is it a list? If so, how does one aubscribe? Thanks.
>----- Original Message -----
>From: <mailto:nfbk at nfbnet.org>Cathy Jackson via Nfbk
>To: <mailto:nfbktad at nfbnet.org>NFB of Kentucky,
>Technology Assistance Division
>Cc: <mailto:cathyj1949 at gmail.com>Cathy Jackson ; <mailto:nfbk at nfbnet.org>NFBK
>Sent: Saturday, April 02, 2016 9:58 AM
>Subject: Re: [Nfbk] [Nfbktad] {Disarmed} Decades
>of computer vision research, one âSwiss Army knifeâ
>
>Ann worked for our national office not NFB of Maryland.
>Cathy
>
>Sent from my iPhone
>
>On Apr 2, 2016, at 9:03 AM, Kevin Pearl via
>Nfbktad <<mailto:nfbktad at nfbnet.org>nfbktad at nfbnet.org> wrote:
>
>>Anne Taylor is a senior project manager at
>>Microsoft and a former NFBK member. She also worked for the NFB in Baltimore.
>>
>>
>>
>>Decades of computer vision research, one
>>âSwiss Army knifeâ - Next at Microsoft
>>
>>
>>
>>When Anne Taylor walks into a room, she wants
>>to know the same things that any person would.
>>
>>Where is there an empty seat? Who is walking up
>>to me, and is that person smiling or frowning? What does that sign say?
>>
>>For Taylor, who is blind, there arenât always
>>easy ways to get this information. Perhaps
>>another person can direct her to her seat,
>>describe her surroundings or make an introduction.
>>
>>There are apps and tools available to help
>>visually impaired people, she said, but they
>>often only serve one limited function and they
>>arenât always easy to use. Itâs also
>>possible to ask other people for help, but most
>>people prefer to navigate the world as independently as possible.
>>
>>Thatâs why, when Taylor arrived at Microsoft
>>about a year ago, she immediately got
>>interested in working with a group of
>>researchers and engineers on a project that she
>>affectionately calls a potential âSwiss Army
>>knifeâ of tools for visually impaired people.
>>
>>âI said, âLetâs do something that really
>>matters to the blind community,ââ said
>>Taylor, a senior project manager who works on
>>ways to make Microsoft products more
>>accessible. âLetâs find a solution for a scenario that really matters.â
>>
>>That project is
>><https://youtu.be/3WP7Id8SxYQ>Seeing AI, a
>>research project that uses computer vision and
>>natural language processing to describe a
>>personâs surroundings, read text, answer
>>questions and even identify emotions on
>>peopleâs faces. Seeing AI, which can be used
>>as a cell phone app or via smart glasses from
>><http://www.pivothead.com/>Pivothead, made its
>>public debut at the companyâs
>><http://build.microsoft.com/>Build conference
>>this week. It does not currently have a release date.
>>
>>Taylor said Seeing AI provides another layer of
>>information for people who also are using
>>mobility aids such as white canes and guide dogs.
>>
>>âThis app will help level the playing field,â Taylor said.
>>
>>At the same conference, Microsoft also unveiled
>><https://www.captionbot.ai/>CaptionBot, a
>>demonstration site that can take any image and
>>provide a detailed description of it.
>>
>>Very deep neural networks, natural language processing and more
>>Seeing AI and CaptionBot represent the latest
>>advances in this type of technology, but they
>>are built on decades of cutting-edge research
>>in fields including computer vision, image
>>recognition, natural language processing and machine learning.
>>
>>In recent years, a spate of breakthroughs has
>>allowed computer vision researchers to do
>>things they might not have thought possible even a few years before.
>>
>>âSome people would describe it as a
>>miracle,â said
>><http://research.microsoft.com/en-us/people/xiaohe/>Xiaodong
>>He, a senior Microsoft researcher who is
>>leading the image captioning effort that is
>>part of
>><https://www.microsoft.com/cognitive-services>Microsoft
>>Cognitive Services. âThe intelligence we can
>>say we have developed today is so much better than six years ago.â
>>
>>The field is moving so fast that itâs
>><http://research.microsoft.com/pubs/264408/ImageCaptionInWild.pdf>substantially
>>better than even six months ago, he said. For
>>example,
>><http://research.microsoft.com/people/ktran/>Kenneth
>>Tran, a senior research engineer on his team
>>who is leading the development effort, recently
>>figured out a way to make the image captioning
>>system more than 20 times faster, allowing
>>people who use tools like Seeing AI to get the
>>information they need much more quickly.
>>
>>A major a-ha moment came a few years ago, when
>>researchers hit on the idea of using deep
>>neural networks, which roughly mimic the
>>biological processes of the human brain, for machine learning.
>>
>>Machine learning is the general term for a
>>process in which systems get better at doing
>>something as they are given more training data
>>about that task. For example, if a computer
>>scientist wants to build an app that helps
>>bicyclists recognize when cars are coming up
>>behind them, it would feed the computer tons of
>>pictures of cars, so the app learned to
>>recognize the difference between a car and, say, a sign or a tree.
>>
>>Computer scientists had used neural networks
>>before, but not in this way, and the new
>>approach resulted in big leaps in computer vision accuracy.
>>
>>Several months ago, Microsoft researchers
>><http://research.microsoft.com/en-us/people/jiansun/>Jian
>>Sun and
>><http://research.microsoft.com/en-us/um/people/kahe/>Kaiming
>>Hemade another big leap when they unveiled a
>>new system that uses very deep neural networks
>> called
>><http://arxiv.org/abs/1512.03385>residual
>>neural networks to correctly identify photos.
>>The
>><http://blogs.microsoft.com/next/2015/12/10/microsoft-researchers-win-imagenet-computer-vision-challenge/>new
>>approach to recognizing images resulted in huge
>>improvements in accuracy. The researchers
>>shocked the academic community and won two
>>major contests, the
>><http://www.image-net.org/>ImageNet and
>><http://mscoco.org/home/>Microsoft Common Objects in Contextchallenges.
>>
>>Tools to recognize and accurately describe images
>>That approach is now being used by Microsoft
>>researchers who are working on ways to not just
>>recognize images but also write captions about
>>them. This research, which combines image
>>recognition with natural language processing,
>>can help people who are visually impaired get
>>an accurate description of an image. It also
>>has applications for people who need
>>information about an image but canât look at
>>it, such as when they are driving.
>>
>>The image captioning work also has received
>><https://blogs.technet.microsoft.com/inside_microsoft_research/2015/06/11/microsoft-researchers-tie-for-best-image-captioning-technology/>accolades
>>for its accuracy as compared to other research
>>projects, and it is the basis for the
>>capabilities in Seeing AI and Caption Bot. Now,
>>the researchers are working on expanding the
>>training set so it can give users a deeper sense of the world around them.
>><https://mscorpmedia.azureedge.net/mscorpmedia/2016/03/FSPB4720.jpg>
>>Margaret Mitchell
>>
>>
>>Margaret Mitchell
>>
>><http://m-mitchell.com/>Margaret Mitchell, a
>>Microsoft researcher who specializes in natural
>>language processing and has been one of the
>>industryâs leading researchers on image
>>captioning, said she and her colleagues also
>>are looking at ways a computer can describe an image in a more human way.
>>
>>For example, while a computer might accurately
>>describe a scene as âa group of people that
>>are sitting next to each other,â a person may
>>say that itâs âa group of people having a
>>good time.â The challenge is to help the
>>technology understand what a person would think
>>was <http://arxiv.org/abs/1512.06974>most
>>important, and worth saying, about the picture.
>>
>>âThereâs a separation between whatâs in
>>an image and what we say about the image,â
>>said Mitchell, who also is one of the leads on the Seeing AI project.
>>
>>Other Microsoft researchers are developing ways
>>that the latest image recognition tools can
>>provide more thorough explanations of pictures.
>>For example, instead of just describing an
>>image as âa man and a woman sitting next to
>>each other,â it would be more helpful for the
>>technology to say, âBarack Obama and Hillary
>>Clinton are posing for a picture.â
>>
>>Thatâs where
>><http://research.microsoft.com/en-us/people/leizhang/>Lei Zhang comes in.
>>
>>When you search the Internet for an image
>>today, chances are high that the search engine
>>is relying on text associated with that image
>>to return a picture of Kim Kardashian or Taylor Swift.
>>
>>Zhang, a senior researcher at Microsoft, is
>>working with researchers including Yandong Guo
>>on a system that uses machine learning to
>>identify celebrities, politicians and public
>>figures based on the elements of the image
>>rather than the text associated with it.
>>
>>Zhangâs research will be included in the
>>latest vision tools that are part of
>><https://www.microsoft.com/cognitive-services>Microsoft
>>Cognitive Services. Thatâs a set of tools
>>that is based on Microsoftâs cutting-edge
>>machine learning research, and which developers
>>can use to build apps and services that do
>>things like recognize faces, identify emotions
>>and distinguish various voices. Those tools
>>also have provided the technical basis for
>>Microsoft showcase apps and demonstration
>>websites such as
>><http://how-old.net/>how-old.net, which guesses
>>a personâs age, and
>><http://news.microsoft.com/features/fetch-new-microsoft-garage-app-uses-artificial-intelligence-to-name-that-breed/>Fetch,
>>which can identify a dogâs breed.
>>
>>Microsoft Cognitive Services is an example of
>>what is becoming a more common phenomenon the
>>lightning-fast transfer of the latest research
>>advances into products that people can actually
>>use. The engineers who work on Microsoft
>>Cognitive Services say their job is a bit like
>>solving a puzzle, and the pieces are the latest research.
>>
>>âAll these pieces come together and we need
>>to figure out, how do we present those to an
>>end user?â said Chris Buehler, a software
>>engineering manager who works on Microsoft Cognitive Services.
>>
>> From research project to helpful product
>>Seeing AI, the research project that could
>>eventually help visually impaired people, is
>>another example of how fast research can become
>>a really helpful tool. It was conceived at last
>>yearâs
>><http://blogs.microsoft.com/firehose/2015/07/27/oneweek-hackathon-2015-heard-around-the-world/>//oneweek
>>Hackathon, an event in which Microsoft
>>employees from across the company work together
>>to try to make a crazy idea become a reality.
>>
>>The group that built Seeing AI included
>>researchers and engineers from all over the
>>world who were attracted to the project because
>>of the technological challenges and, in many
>>cases, also because they had a personal reason
>>for wanting to help visually impaired people operate more independently.
>>
>>âWe basically had this super team of
>>different people from different backgrounds,
>>working to come up with what was needed,â
>>said Anirudh Koul, who has been a lead on the
>>Seeing AI project since its inception and
>>became interested in it because his grandfather is losing his ability to see.
>>
>>For Taylor, who joined Microsoft to represent
>>the needs of blind people, it was a great
>>experience that also resulted in a potential
>>product that could make a real difference in peopleâs lives.
>>
>>âWe were able to come up with this one Swiss
>>Army knife that is so valuable,â she said.
>>
>>This article is online at:
David Andrews and long white cane Harry.
E-Mail: dandrews at visi.com or david.andrews at nfbnet.org
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://nfbnet.org/pipermail/nfbk_nfbnet.org/attachments/20160406/ae6e06b1/attachment.html>
More information about the NFBK
mailing list