Post «Facebook machine learning aims to modify faces, hands, and… outfits» in blog Прогноз погоды

People

John Smith

John Smith, 48

Joined: 28 January 2014

Interests: No data

Jonnathan Coleman

Jonnathan Coleman, 32

Joined: 18 June 2014

About myself: You may say I'm a dreamer

Interests: Snowboarding, Cycling, Beer

Andrey II

Andrey II, 41

Joined: 08 January 2014

Interests: No data

David

David

Joined: 05 August 2014

Interests: No data

David Markham

David Markham, 65

Joined: 13 November 2014

Interests: No data

Michelle Li

Michelle Li, 41

Joined: 13 August 2014

Interests: No data

Max Almenas

Max Almenas, 53

Joined: 10 August 2014

Interests: No data

29Jan

29Jan, 31

Joined: 29 January 2014

Interests: No data

s82 s82

s82 s82, 26

Joined: 16 April 2014

Interests: No data

Wicca

Wicca, 36

Joined: 18 June 2014

Interests: No data

Phebe Paul

Phebe Paul, 26

Joined: 08 September 2014

Interests: No data

Артем Ступаков

Артем Ступаков, 93

Joined: 29 January 2014

About myself: Радуюсь жизни!

Interests: No data

sergei jkovlev

sergei jkovlev, 59

Joined: 03 November 2019

Interests: музыка, кино, автомобили

Алексей Гено

Алексей Гено, 8

Joined: 25 June 2015

About myself: Хай

Interests: Интерес1daasdfasf, http://apple.com

technetonlines

technetonlines

Joined: 24 January 2019

Interests: No data



Facebook machine learning aims to modify faces, hands, and… outfits

23:53 | 11 November expand

Facebook machine learning aims to modify faces, hands, and… outfits

The latest research out of Facebook sets machine learning models to tasks that, to us, seem rather ordinary — but for a computer are still monstrously difficult.

These projects aim to anonymize faces, improvise hand movements, and — perhaps hardest of all — give credible fashion advice.

The research here was presented recently at the International Conference on Computer Vision, among a few dozen other papers from the company, which has invested heavily in AI research, computer vision in particular.

Modifying faces in motion is something we’ve all come to associate with “deepfakes” and other nefarious applications. But the Facebook team felt there was actually a potentially humanitarian application of the technology.

Deepfakes use a carefully cultivated understanding of the face’s features and landmarks to map one person’s expressions and movements onto a completely different face. The Facebook team used the same features and landmarks, but instead uses them to tweak the face just enough that it’s no longer recognizable to facial recognition engines.

This could allow someone who, for whatever reason, wants to appear on video but not be recognized publicly to do so without something as clunky as a mask or completely fabricated face. Instead, they’d look a bit like themselves, but with slightly wider-set eyes, a thinner mouth, higher forehead, and so on.

Facebook machine learning aims to modify faces, hands, and… outfits

The system they created appears to work well, but would of course require some optimization before it can be deployed as a product. But one can imagine how useful such a thing might be, either for those at risk of retribution from political oppressors or more garden variety privacy preferences.

In virtual spaces it can be difficult to recognize someone at all — partly because of the lack of nonverbal cues we perceive constantly in real life. This next piece of research attempts to capture, catalogue, and reproduce these movements, or at least the ones we make with our hands.

It’s a little funny to think about, but really there’s not a lot of data on how exactly people move their hands when they talk. So the researchers recorded 50 full hours of pairs of people having ordinary conversations — or as ordinary as they could while suited up in high-end motion capture gear.

Facebook machine learning aims to modify faces, hands, and… outfits

These (relatively) natural conversations, and the body and hand motions that went with them, were then ingested by the machine learning model; it learned to associate, for example, that when people said “back then” they’d point behind them, or when they said “all over the place,” they’d make a sweeping gesture.

What might this be used for? More natural-seeming conversations in virtual environments, perhaps, but maybe also by animators who’d like to base the motions of their characters in real life without doing motion capture of their own. It turns out that the database Facebook put together is really like nothing else out there in scale or detail, which is valuable in and of itself.

Similarly unique, but arguably more frivolous, is this system meant to help you improve your outfit. If we’re going to have smart mirrors, they ought to be able to make suggestions, right?

Fashion++ is a system that, having ingested a large library of images labeled with both the pieces worn (e.g. hat, scarf, skirt) and overall fashionability (obviously a subjective measure), can then look at a given outfit and suggest changes. Nothing major — it isn’t that sophisticated — but rather small things like removing a layer or tucking in a shirt.

Facebook machine learning aims to modify faces, hands, and… outfits

It’s far from a digital fashion assistant, but the paper documents early success in making suggestions for outfits that real people found credible and perhaps even a good idea. That’s pretty impressive given how complex this problem proves to be when you really consider it, and how ill-defined “fashionable” really is.

Facebook’s ICCV research shows that the company and its researchers are looking fairly broadly at the question of what computer vision can accomplish. It’s always nice to detect faces in a photo faster or more accurately, or infer location from the objects in a room, but clearly there are many more obscure or surprising aspects of digital life that could be improved with a little visual intelligence. You can check out the rest of the papers here.

Facebook machine learning aims to modify faces, hands, and… outfits Facebook machine learning aims to modify faces, hands, and… outfits Facebook machine learning aims to modify faces, hands, and… outfits Facebook machine learning aims to modify faces, hands, and… outfits Facebook machine learning aims to modify faces, hands, and… outfits Facebook machine learning aims to modify faces, hands, and… outfits
Facebook machine learning aims to modify faces, hands, and… outfits

 


Read more→

Posted on 11.11.2019 23:53

Comments

To show the previous comments (%s from %s)
Show new comments

Last comments

Walmart retreats from its UK Asda business to hone its focus on competing with Amazon
Peter Short
Good luck
Peter Short

Evolve Foundation launches a $100 million fund to find startups working to relieve human suffering
Peter Short
Money will give hope
Peter Short

Boeing will build DARPA’s XS-1 experimental spaceplane
Peter Short
Great
Peter Short

Is a “robot tax” really an “innovation penalty”?
Peter Short
It need to be taxed also any organic substance ie food than is used as a calorie transfer needs tax…
Peter Short

Twitter Is Testing A Dedicated GIF Button On Mobile
Peter Short
Sounds great Facebook got a button a few years ago
Then it disappeared Twitter needs a bottom maybe…
Peter Short

Apple’s Next iPhone Rumored To Debut On September 9th
Peter Short
Looks like a nice cycle of a round year;)
Peter Short

AncestryDNA And Google’s Calico Team Up To Study Genetic Longevity
Peter Short
I'm still fascinated by DNA though I favour pure chemistry what could be
Offered is for future gen…
Peter Short

U.K. Push For Better Broadband For Startups
Verg Matthews
There has to an email option icon to send to the clowns in MTNL ... the govt of India's service pro…
Verg Matthews

CrunchWeek: Apple Makes Music, Oculus Aims For Mainstream, Twitter CEO Shakeup
Peter Short
Noted Google maybe grooming Twitter as a partner in Social Media but with whistle blowing coming to…
Peter Short

CrunchWeek: Apple Makes Music, Oculus Aims For Mainstream, Twitter CEO Shakeup
Peter Short
Noted Google maybe grooming Twitter as a partner in Social Media but with whistle blowing coming to…
Peter Short


Site search