Miscellaneous

The Q:Check Cap Verification system inspects flat and sipper caps on beverage bottles for cap presence and height, intact tamper ring, dust cap presence and fill level. The fully automated visual control of the cap area prevents drink contamination and spillage.

Click to expand...

Talk: Vicente Ordonez-Roman
University of North Carolina at Chapel Hill

Title: Language and Perceptual Categorization in Computer Vision

Abstract:
Recently, there has been great progress in both computer vision and natural language processing in representing and recognizing semantic units like objects, attributes, named entities, or constituents. These advances provide opportunities to create systems able to interpret and describe the visual world using natural language. This is in contrast to traditional computer vision systems, which typically output a set of disconnected labels, object locations, or annotations for every pixel in an image. The rich visually descriptive language produced by people incorporates world knowledge and human intuition that often can not be captured by other types of annotations. In this talk, I will present several approaches that explore the connections between language, perception, and vision at three levels: learning how to name objects, generating referring expressions for objects in natural scenes, and producing general image descriptions. These methods provide a framework to augment computer vision systems with linguistic information and to take advantage of the vast amount of text associated with images on the web. I will also discuss some of the intuitions from linguistics and perception behind these efforts and how they potentially connect to the larger goal of creating visual systems that can better learn from and communicate with people.

Click to expand...

The popular Microsoft Selfie app has been updated with social sharing to Facebook, Twitter, WeChat as well as native apps for iOS users. The app uses computer vision and machine learning to enhance the images you take, removing noise and auto-correcting for poor lighting.

Click to expand...

The paper "Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation" is available here.

Click to expand...

Phone apps make everyone’s lives easier, but for members of the blind community, a new seeing AI app transforms how they live and work every day. Anirudh Koul believes that any disability is merely a gap between what we want to do and what we can do, and it’s technology’s role to fill those gaps. Koul points out that we all experience gaps as we age, and his invention gives all hope for a more empowered future. Growing up in India, Anirudh Kuhl was programming computers at a young age and by high school he was captivated by patterns in data—a key component of artificial intelligence. He moved to the United States to study at Carnegie Mellon and after stints at Yahoo and Microsoft, is now an AI researcher with multiple patents. Driven by his desire to help a dear family member, he took on a hackathon challenge at Microsoft and led development of an app that is now helping hundreds of millions of people with disabilities. It literally puts the gift of sight in their hands. This talk was given at a TEDx event using the TED conference format but independently organized by a local community.

Click to expand...