From flat-earthers to QAnon to Covid quackery, the video giant is awash in misinformation. Can AI keep the lunatic fringe from going viral?
Mark Sargent saw instantly that his situation had changed for the worse. A voluble, white-haired 52-year-old, Sargent is a flat-earth evangelist who lives on Whidbey Island in Washington state and drives a Chrysler with the vanity plate “ITSFLAT.” But he’s well known around the globe, at least among those who don’t believe they are living on one. That’s thanks to YouTube, which was the on-ramp both to his flat-earth ideas and to his subsequent international stardom.
… Crucial to his success, he says, was YouTube’s recommendation system. …For four years, Sargent’s flat-earth videos got a steady stream of traffic from YouTube’s algorithms. Then, in January 2019, the flow of new viewers suddenly slowed to a trickle. Read More
Tag Archives: Image Recognition
Library of Congress Launches New Tool to Search Historical Newspaper Images
The public can now explore more than 1.5 million historical newspaper images online and free of charge. The latest machine learning experience from Library of Congress Labs, Newspaper Navigator allows users to search visual content in American newspapers dating 1789-1963.
… Through the creative ingenuity of Innovator in Residence Benjamin Lee and advances in machine learning, Newspaper Navigator now makes images in the newspapers searchable by enabling users to search by visual similarity. Read More
DeepFaceDrawing: Deep Generation of Face Images from Sketches
Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend to overfit to sketches, thus requiring professional sketches or even edge maps as input. To address this issue, our key idea is to implicitly model the shape space of plausible face images and synthesize a face image in this space to approximate an input sketch. We take a local-to-global approach. We first learn feature embeddings of key face components, and push corresponding parts of input sketches towards underlying component manifolds defined by the feature vectors of face component samples. We also propose another deep neural network to learn the mapping from the embedded component features to realistic images with multi-channel feature maps as intermediate results to improve the information flow. Our method essentially uses input sketches as soft constraints and is thus able to produce high-quality face images even from rough and/or incomplete sketches. Our tool is easy to use even for non-artists, while still supporting fine-grained control of shape details. Both qualitative and quantitative evaluations show the superior generation ability of our system to existing and alternative solutions. The usability and expressiveness of our system are confirmed by a user study. Read More
Full-Body Awareness from Partial Observations
There has been great progress in human 3D mesh recovery and great interest in learning about the world from consumer video data. Unfortunately current methods for 3D human mesh recovery work rather poorly on consumer video data, since on the Internet, unusual camera viewpoints and aggressive truncations are the norm rather than a rarity. We study this problem and make a number of contributions to address it: (i) we propose a simple but highly effective self-training framework that adapts human 3D mesh recovery systems to consumer videos and demonstrate its application to two recent systems; (ii) we introduce evaluation protocols and keypoint annotations for 13K frames across four consumer video datasets for studying this task, including evaluations on out-of-image keypoints; and (iii) we show that our method substantially improves PCK and human-subject judgments compared to baselines, both on test videos from the dataset it was trained on, as well as on three other datasets without further adaptation. Read More
A quantum-inspired framework for video sentiment analysis
Automatically identifying the overall sentiment expressed in a video or text could be useful for a wide range of applications. For instance, it could help companies or political parties to screen large amounts of online content and gain insight on what the public thinks about their products, services, campaigns or initiatives.
Researchers at University of Padua, the Open University and University of Copenhagen have recently introduced a new framework for video sentiment analysis that is based on quantum physics theory. Read More
Machine Learning & Image to Audio Captioning
A brief literature review of how machine learning is used to translate images directly into speech. Read More
How to build an image automatic rotator in 24 hours
The simplicity of Neural Network and Keras’ tools.
Recently, I was challenged to do this task which basically asked to use neural networks to predict the image orientation (upright, upside down, left or right) and with that prediction rotate the image to the correct position (upright), all of this in 24 hours! Read More
YouTube removes record number of videos as human moderators replaced by AI
YouTube’s automated filters were less reliable than human moderators, but the company ‘accepted a lower level of accuracy; to ensure harmful content was removed.
YouTube has removed more videos in the second quarter of 2020 than ever before.
During the coronavirus pandemic, when the video sharing site could not rely on its human moderators as much as previously, YouTube increased its use of automated filters in order to take down videos that could potentially violate its policies. Read More
Facebook and NYU use artificial intelligence to make MRI scans four times faster
AI learns to create MRI scans from a quarter of the data.
If you’ve ever had an MRI scan before, you’ll know how unsettling the experience can be. You’re placed in a claustrophobia-inducing tube and asked to stay completely still for up to an hour while unseen hardware whirs, creaks, and thumps around you like a medical poltergeist. New research, though, suggests AI can help with this predicament by making MRI scans four times faster, getting patients in and out of the tube quicker.
The work is a collaborative project called fastMRI between Facebook’s AI research team (FAIR) and radiologists at NYU Langone Health. Read More
Rick's Cafe AI 