Things tagged video:
So many good things here. A random sampling:
Keyboards are inefficient for two reasons: they do not exploit the redundancy in normal language; and they waste the fine analogue capabilities of the user’s motor system (fingers and eyes, for example). I describe a system intended to rectify both these inefficiencies. Dasher is a text-entry system in which a language model plays an integral role, and it’s driven by continuous gestures.
More infro and apps to play with it at http://www.inference.org.uk/dasher/
In my opinion, physical keyboards will always win, as they have a 1 to 1 relationship between thinking a letter and accessing that letter (for alphabets with a reasonable number of characters anyway). But this is a stunningly amazing improvement over eye tracked onscreen keyboards, and a fun thing to play with. Check out the scanning box method in the phone version. For someone with severe physical disabilities I think this would be best in class?
Once upon a Line (1947)
“Model husbands” from 1947 show off the pulling power of their miniature trains.
Putting aside current 3D modeling techniques, Red Giant’s Chief Creative Officer Stu Maschwitz looked to the past and built a visual homage to vector arcade games of the 80’s entirely in Adobe After Effects, using math, code, and hundreds of hours of painstaking animation work.
The Mauritania Railway: Backbone of the Sahara is a documentary film directed by MacGregor.
Mona El Dorr is from a village in the south of Lebanon called Majdelzoum. She is known as Oum Ali. For over a decade, she has put her heart, strength and soul into keeping the culinary traditions of her village alive.
Athens Digital Arts Festival (ADAF), the Greek representative in the international digital arts scene, returns for its 14th edition
Masahiro Kikuno is a master craftsman who belongs to an exclusive international group of independent watchmakers. These consummate artists create timepieces that reflect their deepest ideals, with no connection to commercial watch manufacturers.
And the adorable hug from the referee at the end.
Inbar Mosseri and Oran Lang at Google Research:
People are remarkably good at focusing their attention on a particular person in a noisy environment, mentally “muting” all other voices and sounds. Known as the cocktail party effect, this capability comes natural to us humans. However, automatic speech separation — separating an audio signal into its individual speech sources — while a well-studied problem, remains a significant challenge for computers.
In “Looking to Listen at the Cocktail Party”, to appear in SIGGRAPH 2018 this summer, we present a deep learning audio-visual model for isolating a single speech signal from a mixture of sounds such as other voices and background noise. In this work, we are able to computationally produce videos in which speech of specific people is enhanced while all other sounds are suppressed. Our method works on ordinary videos with a single audio track, and all that is required from the user is to select the face of the person in the video they want to hear, or to have such a person be selected algorithmically based on context. We believe this capability can have a wide range of applications, from speech enhancement and recognition in videos, through video conferencing, to improved hearing aids, especially in situations where there are multiple people speaking.
Yeah whatever, a bunch of mumbo jumbo right? Well just watch this:
Frank Bretschneider: One of the key activists of the electronic music underground in former East Germany, Frank Bretschneider has continued to revolutionize electronic music as part of raster-noton for the past 20 years. Today he presents his brand new album!