Deep Visual-Semantic Alignments for Generating Image Descriptions. A model that generates free-form natural language descriptions of image regions. Holy crap.
"Masuma Ahuja and Denise Lu for the Washington Post applied a technique called databending to a bunch of photos. The idea is that computer files — even though they represent different things like documents, images, and audio — encode data in one form or another. It's just that sound files encode beats, notes, and rhythms, whereas image files encode hue, saturation, and brightness. So when you treat image files as if they were audio, you get some interesting results. Jamie Boulton has a detailed description on how to do this yourself with Audacity Effects." [via]
Retail Therapy: What Mannequins Say About Us
Like the larger fashion industry, mannequin design echoes seasonal styles that come and go, both in regard to technological improvements and the way we view our bodies. “It’s often the body attitudes and facial expressions that reflect what’s going on socially,” says Hale. Accordingly, the stiff, unnatural bodies of early mannequins were well-matched for the Victorian Era‘s restrictive ideas about women’s rights and fashions, which dictated they wear many layers of heavy fabric over tight-fitting corsets.[more inside]
Educationally bizarre: Current events, medicine, animals, forensics, oddities, teeth, eyes, deformities, funerals, cemeteries, blood, albinism and such ........ It's The Soul is Bone. Not necessarily disturbing, but not necessarily not disturbing. Not necessarily NSFW, but not necessarily not NSFW.
Anne Helen Petersen of " Scandals Of Classic Hollywood" fame talks about Zac Efron, the impossible demands of movie masculinity, and the history of the Teen Idol Industry on BuzzReads
Gigapixel ArtZoom is a multi-billion-pixel panoramic image celebrating the arts in Seattle, featuring artists and performers in the context of their city. Pan and zoom the image to find each artist/group (and enjoy the sights and scenery along the way); when an artist is in your sights, a pop-up ID tag will link to an artist profile page featuring a bio and video showcase.
With the advent of Flickr, Picasa, Instagram, i.e. massive databases of images, researchers have devised tools like simple markers like SIFT, in order to reduce image information to bits. As it turns out, many people think this degraded information can only be used for simple operation on images such as comparison, etc... Hérvé Jégou and other researchers have shown in some vivid manner that one can reconstruct images from these "information degraded" markers. As an extension of the original paper, Hérvé Jégou has produced a wide variety of reconstructions from photos taken while on vacation. The result: stunning dream-like, artistic-like rendering of the original scenes. And while it may raise all kinds of privacy issues, one cannot escape the similarity between these renderings and the scenes reconstructed from MRI readings.
Sales of digital comics have soared in the past three years. Readers love the look of comics on the iPad screen and they also love the convenience of in-app purchasing, which allows consumers to buy and store their comics within a single app. So it’s a big deal when Apple bans a comic—usually because of sexual or mature material or nudity—and it has happened to at least 59 comics this year. - Are comics too hot for Apple? Publishers Weekly looks at Apples role as Gatekeeper in the wake of their rejection of Sex Criminals #3 and retroactive removal of Sex Criminals #1 from the iOS marketplace. Strangely the books remain available via iBooks. This is not the first time Apples policies have been confusing or raised concerns of censorship, such as with the Saga of Saga #12 earlier this year, and before the rise of comixology with the banning/unbanning of Ulysses Seen (previously).
After several years out of the mainstream music scene Lily Allen returned last week covering Keane's "Somewhere only we know" in this year's John Lewis Christmas TV ad. However, today Lily released her latest video which is ... somewhat different in tone and nature. [more inside]
Saga, by Brian K. Vaughan and Fiona Staples , has swept the Eisners, taking home awards for Best Continuing Series, Best New Series and Best Writer. Here's why you should be reading it.
The New York City Municipal Archives Online Gallery offers over 870,000 historical images related to the 'city that never sleeps,' including maps as well as video and audio recordings. A selection of 53 images from the collection can be seen at In Focus. [more inside]
Only for Children: [via: DIY Photography]" The ANAR Foundation is a Spanish organization which helps kids in risk. They Operate a unique phone number - 116 111 - where minors at risk can get aid and consultation. Anar did a campaign advertizing the number, but were facing a problem where they did not want potential aggressors to see that a kid was even looking at the ad. The solution was using Lenticular printing [wiki] on street signs." [more inside]
The George Eastman House is producing a series of nicely produced videos, each about 10 minutes long, demonstrating every major technological development in photographic process with guidance from historians, curators, and artists and illustrated by objects from their collection. There are more to come, but you can start now with The Dageurrotype, The Collodion Process, The Albumen Print, The Woodburytype, The Platium Print, and The Gelatin Silver Print.
OMGif! [Wired] "On Tuesday, Google announced via Google+ that Image Search now has an “Animated” filter. That means that if you’re only searching for animated magic, you need never be bothered with a still image again. Finally that search for Jennifer Lawrence GIFs from the Academy Awards just got a whole lot easier."
We've all seen it. The off-white UAV is seen side on, nose tilted slightly down, a stubby missile caught at the moment of launch beneath it, a blue and grey landscape of treeless mountains behind it. There's no motion blur and none of the markings on the aircraft have been obfuscated. It's a perfect shot. Except for one or two details. [more inside]
Female porn stars, with and without their makeup It's a large bandwidth-intensive imgur gallery. (Via)
The stereotypes about Africa/Africans are too many to list here. They’re mostly negative, myopic depictions that focus on war, famine, abject poverty, disease, and corruption. In other oversimplifications, Africans are written up as model immigrants, overachieving geniuses, or displaced chiefs moonlighting as gas station attendants. Outside of these caricatures, many Africans are going to work and school, voting in their local elections, and spending way too much time on Facebook. And they’re over the ignorance that has collectively miscast them. In response, a swelling movement of young Africans are launching concerted efforts to wrest the image of Africa from entities and interests that don’t promote a balanced understanding of the continent.
A day before her 32nd birthday, Jill Brzezinski-Conley was diagnosed with breast cancer and underwent a double mastectomy. She's now 35, and her cancer has metastasized to terminal, stage-4. Sue Bryce won Australian Portrait Photographer of the Year in both 2011 and 2012, and last year's prize was a one-person trip to Paris. After hearing her story, Bryce took Brzezinski-Conley with her to the City of Light for a photo shoot and brought along a videographer. The resulting short film: "The Light That Shines." (Also on Vimeo.) Photos. (click the open magazine at the top of the page). The video and photos both show a topless Ms. Brzezinski-Conley, and may be nsfw. [more inside]
Has Slate's well known, some would say even cliched, contrarism jumped the shark, now they've gone so far as to defend Rob Liefeld? [more inside]
The New York Times asks seven 'experts': Does makeup ultimately damage a woman’s self-esteem, or elevate it? [more inside]
Gigapixel image of the Khumbu Glacier and Mount Everest Taken by filmmaker David Breashears this is a gigapixel image of Everest (the mainly rock peak to the left of centre) and surrounding area taken in Spring 2012. To get an idea of the scale Everest basecamp can be seen in the bottom-centre area of the image. Best viewed fullscreen.
The permanent collection of the (US) National Veterans Art Museum in Chicago contains more than 2,500 pieces of art by 250 artists, all of which can be seen at NVAM Collection Online. The site includes biographical material on the artists who created the work. Featured Artwork. A small selection. (Via. Images at links in this post may be nsfw, and/or disturbing to some viewers.)
Teenage girls try to navigate the minefields of desirability, attractiveness, and self-objectification in the age of Facebook. [more inside]
Artist Dusty Abell has created a massive poster featuring "at least one, sometimes more, character, entity, starship or structure from every episode of [Star Trek: The Original] series." Via io9, who ask: How many characters can you name? Stumped? Here's a key of all 123! [more inside]
35 years ago today, Voyager 1 transmitted three images which NASA processed into a single frame of Earth and its moon. [more inside]
Shrinp.com is a site that does very little and does it well. Stick anything after the domain name (shrinp.com/shrimp! shrinp.com/puggle! shrinp.com/metafilter!) and you'll get a helpfully labeled image of maybe that thing, or maybe not so much that thing, who can tell? The internet, it's very mysterious. Built by our very own 31d1. Approximately as NSFW as you try to make it.
The highest possible resolution images — about 100,000 dots per inch — have been achieved, and in full-colour, with a printing method that uses tiny pillars a few tens of nanometres tall. The method, described today in Nature Nanotechnology, could be used to print tiny watermarks or secret messages for security purposes, and to make high-density data-storage discs. [more inside]
The First Photo on the Web: A story of crossdressing, particle physics, humorous science-based novelty songs, and terrible photoshop.
FaceTracker is an example of a complex technique that builds on top of a series of computer vision, image processing, and machine learning functions in order to achieve its result. Here's an interview with Kyle McDonald, artist and researcher in New York with a background in computer science and philosophy. He released FaceOSC, a tool for prototyping face-based interaction. Kyle has a growing body of work that uses face tracking in an artistic context, notably Face Substitution.
Model Behavior: A Laurie Penny essay on gender presentation, anorexia, neoliberalism, capitalism, queerness, gender, drag, media, America's Next Top Model, and a few other things.
Gestus is a moving image processing framework that uses computer vision techniques to explore the artistic possibilities of the vector as a symbolic form.
The most Epic Photo Ever Taken? Quora users start adding their faourite pictures. History, awesome, pain, anger, death, it's al here. And at least one surfer.
This week Image Comics celebrated 20 years of producing independent comics with the Image Comics Expo, taking a look back at the past whilst announcing a raft of new titles for the future, including some Grant Morrison projects and the long awaited return of Kieron Gillen and James McKelvie's Phonogram. One strange Image comic that embraces both the past and the future is Prophet - which picks up at issue #21 of an forgotten Liefeld story and turns it into "future space Conan".
The main thing about impersonation, Tom thought, was to maintain the mood and temperament of the person one was impersonating, and to assume the facial expressions that went with them.
Catalog features models with sculpted bodies. A growing confectionary of kit for processing human bodies ( [YouTube]: Estimating body shape under clothing, Parametric Reshaping of Human Bodies in Images, Data-Driven Enhancement of Facial Attractiveness), prefigures a Barbie apocalypse of supernormal stimuli and body image disorders.
Princeton's 5th annual Art of Science Competition "The Art of Science exhibition explores the interplay between science and art. These practices both involve the pursuit of those moments of discovery when what you perceive suddenly becomes more than the sum of its parts. Each piece in this exhibition is, in its own way, a record of such a moment."
"Tanks Are Mighty Fine Things!" And Other Tales Of Truthiness... At the end of World War II, Chrysler sent small hardbound books to shareholders chronicling ways the company had contributed to the war effort. Two have now been placed online at the Chrysler Imperial Club's website: "Tanks are Mighty Fine Things" and "A War Job 'Thought Impossible' (The story of the Chrysler-Sperry Gyro-Compass)" (Via) [more inside]
Man is least himself when he talks in his own person. Give him a mask, and he will tell you the truth
Style Like U features an exhaustive video archive of people talking about their clothes and history and what personal style means to them and the power of self transformation. [more inside]
Storseisundet Bridge, along Atlantic Road, the Atlanterhavsveien in Norway, is a mind-bending (at certain angles) cantilever structure guaranteed to thrill you.
My Life with Science, Art and Food: "Using scientific laboratory photo equipment, I journey over the surfaces of both organic and processed foods: my own favorites and America’s over-indulgences. The closer the lens got, the more I saw food and consumers of food (all of us!) as part of a larger eco-system than mere sustenance." [more inside]
Russian divers working for the Orda Cave Awareness Project have revealed stunning images of the world's longest underwater cave.
The Tatara Project: Learn how to make your own Japanese tanto knives from homemade steel; just follow these explicit directions and 125 photos.