Goto

Collaborating Authors

 Media


Facial recognition software can now reportedly recognize bears

#artificialintelligence

Using artificial intelligence, the project has been able to recognize 132 of the animals individually and it's a much more effective -- and safe -- way to …


MEG: Multi-Evidence GNN for Multimodal Semantic Forensics

arXiv.org Artificial Intelligence

Fake news often involves semantic manipulations across modalities such as image, text, location etc and requires the development of multimodal semantic forensics for its detection. Recent research has centered the problem around images, calling it image repurposing -- where a digitally unmanipulated image is semantically misrepresented by means of its accompanying multimodal metadata such as captions, location, etc. The image and metadata together comprise a multimedia package. The problem setup requires algorithms to perform multimodal semantic forensics to authenticate a query multimedia package using a reference dataset of potentially related packages as evidences. Existing methods are limited to using a single evidence (retrieved package), which ignores potential performance improvement from the use of multiple evidences. In this work, we introduce a novel graph neural network based model for multimodal semantic forensics, which effectively utilizes multiple retrieved packages as evidences and is scalable with the number of evidences. We compare the scalability and performance of our model against existing methods. Experimental results show that the proposed model outperforms existing state-of-the-art algorithms with an error reduction of up to 25%.


6 AI Tools That Add Color to Old Black and White Photos

#artificialintelligence

For years, production companies have used costly techniques to colorize old black and white movies. But now artificial intelligence is placing that capability in the hands of everyday users, allowing you to add color to old family photos, historical images, or black and white video frames in seconds. It works like this: A developer feeds a large number of color images into a neural network, which is AI-speak for software modeled after brain functions. Over time, the software learns to recognize different objects and determine their likely colors. These algorithms are incorporated into online services as well as software that you can download and run on a computer.


Music from the heart, with an AI assist

#artificialintelligence

His favorite rappers felt like personal mentors, and he decided to imitate them and try rapping himself. He recorded songs using the microphone on his MP3 player; he says they were a crucial way for him to vent. "From when I was 13 until today, being able to write about my life and how I'm feeling, it's the most therapeutic thing for me," he says. Around the same time he discovered hip-hop, MJ became fascinated by technology. His family couldn't afford a computer, but someone at his local church built a computer for them, complete with a see-through CPU tower.


Moneybrain to supply Kim Joo-ha AI anchor solution to MBN

#artificialintelligence

With Moneybrain's solution, MBN is able to report videos of breaking news vividly and quickly with an AI anchor. In addition, AI models will be put into MBN's various programs, allowing the company to start producing broadcasts in the same time slot. The Moneybrain solution introduced by MBN is a real-time video synthesis technology based on deep learning and provides AI model videos that express the same person as the actual person. By simply entering an article script, it converts into voice and video and it provides various costume choices, making it easier for users to produce AI models. As a result, existing broadcasting officials have been able to save a lot of resources such as time, personnel, and cost for filming.


Multi-Plane Program Induction with 3D Box Priors

arXiv.org Machine Learning

We consider two important aspects in understanding and editing images: modeling regular, program-like texture or patterns in 2D planes, and 3D posing of these planes in the scene. Unlike prior work on image-based program synthesis, which assumes the image contains a single visible 2D plane, we present Box Program Induction (BPI), which infers a program-like scene representation that simultaneously models repeated structure on multiple 2D planes, the 3D position and orientation of the planes, and camera parameters, all from a single image. Our model assumes a box prior, i.e., that the image captures either an inner view or an outer view of a box in 3D. It uses neural networks to infer visual cues such as vanishing points or wireframe lines to guide a search-based algorithm to find the program that best explains the image. Such a holistic, structured scene representation enables 3D-aware interactive image editing operations such as inpainting missing pixels, changing camera parameters, and extrapolate the image contents.




Do you think artificial intelligence (AI) would predict movie ratings in future? Read on.

#artificialintelligence

Believe it or not, researchers have demonstrated that artificial intelligence (AI) tools can rate a movie's content in a matter of seconds, based on the …


Historically Black colleges get $3 million to develop sensors for nuclear plants

#artificialintelligence

Students in the program will have the opportunity to study machine learning research for materials sciences, and they will be given the chance to do …