时间：2025-04-04 05:23:04 来源：网络整理编辑：百科
Facebook's search tool is about to get way more visual. Director of Applied Machine Learning Joaquin
Facebook's search tool is about to get way more visual.
Director of Applied Machine Learning Joaquin Candela published a blog post today (accompanying his presentation at the Machine Learning @Scale event in New York City) to share updates about Facebook's AI-based image-recognition tool. The improvements can home in on photos to the "pixel level" and will let users search images based on their content -- whether or not they've been manually tagged.
"Until recently, online search has always been a text-driven technology, even when searching through images," he writes. "Whether an image was discoverable was dependent on whether it was sufficiently tagged or had the right caption -- until now."
SEE ALSO:How Facebook is trying to dominate mobile without owning your smartphoneAdvancements in Facebook's computer vision tech and the introduction of new tools will let users make much more targeted image searches. For instance, when you search your old photos, you'll be able to look for images where you're wearing a black shirt or red dress, or where the people in the image are dancing.
Facebook's computer-vision tools were originally envisioned to help the visually impaired navigate the service, discerning what's in a photo just by scanning it. But today's news shows general Facebook users have a lot to benefit from the feature as well.
Crediting "a lot" of teams for the advancements, Candela wrote that Facebook's general-purpose AI platform, FBLearner Flow, is now running 1.2 million AI experiments a month -- six times more than it was just a year ago.
Built on top of that is Lumos, Facebook's specialized platform for image and video understanding. Using Lumos, the network' search tool can identify features in images and video automatically. For users, that capability will help pinpoint searches to the exact pic they're looking for -- and for Facebook, the automation will make it easier to identify inappropriate content and spam.
These systems are also being employed to improve the platform's automatic alt text (AAT) for photos, which makes the visual aspects of the platform more accessible to the visually impaired. With the new tools, a set of 12 new actions, like "people dancing," have been added to the automatic image description.
TopicsArtificial IntelligenceFacebook
Metallica to seek and destroy your eardrums with new album this fall2025-04-04 05:15
'Mr. Robot' Season 2 finale review2025-04-04 05:00
Customer confounded by a messed up coffee and Baileys order2025-04-04 04:55
Petition to get Steve Irwin on Aussie currency is really, really popular2025-04-04 04:21
Dog elected for third term as mayor of Minnesota town2025-04-04 04:15
This dongle lets you easily transfer your GoPro footage to your phone2025-04-04 04:06
I tried to ignore Trump for a whole month. Here's what I learned.2025-04-04 03:56
Study finds Trump 4 times more likely than Clinton to 'mock or criticize' on Twitter2025-04-04 03:55
Teacher absolutely nails it with new homework policy2025-04-04 03:08
Geode lips as an Instagram beauty trend are too dazzling to behold2025-04-04 02:58
Dressage horse dancing to 'Smooth' by Santana wins gold for chillest horse2025-04-04 05:21
2016 Emmy Winners: Full List2025-04-04 04:39
Trump says Miss Universe winner Alicia Machado gained 'a massive amount of weight'2025-04-04 04:14
2016 Emmys: All the best red carpet looks2025-04-04 03:57
Pole vaulter claims his penis is not to blame2025-04-04 03:56
5 creative ways to trick people into eating healthy2025-04-04 03:30
Dog who came back to the same spot for a year awaiting owners is killed by a vehicle there2025-04-04 03:28
Tom Hiddleston stares into the abyss while wearing a fancy suit and petting a dog2025-04-04 03:10
Nate Parker is finally thinking about the woman who accused him of rape2025-04-04 03:01
Mysterious 'Destiny' ARG solved, and it's part of a giant raid puzzle2025-04-04 02:42
