Rochester Joint Chapter of the IEEE Computer and Computational Intelligence SocietiesRochester, New York |
Date: Friday, September 8, 2017 |
AbstractDeep learning has enabled incredible advances in computer vision, natural language processing, and general pattern understanding. Success in this space spans many domains including object detection, speech recognition, natural language processing, and action/scene interpretation. For targeted tasks, results are on par with and often surpass the abilities of humans. Recent discoveries have enabled researchers to bridge the gap between visual and written stimulus. For example, the automatic captioning of still imagery, summarization of video, and generation of images from keywords were all difficult tasks two years ago, but with the help of deep learning, are all active research today. Despite great progress, the generic connection of various written and visual modalities remains challenging. This talk will review recent advances in the vision and language domains and introduce a novel vector connection space such that words, sentences, and paragraphs can efficiently and accurately connect with still and motion visual stimuli. Similar deep learning techniques are being applied to everyday devices such as smartphones and wearables and will make our lives more efficient and feature rich. Speaker's Biography
|
Rochester Chapter Home | Rochester Section Home | Privacy & Security | Terms & Conditions | Nondiscrimination Policy | |
© Copyright 2016 IEEE – All Rights Reserved. Use of this Web site signifies your agreement to the terms and conditions. |
|
If you would like to contact the
Rochester Joint Chapter of the IEEE Computer and Computational Intelligence Societies Webmaster,
use the email link on the
Officer's page for the Joint Computer Chapter
Webmaster.
(Modified: 24-August-2017 JC) |