Title:
ZERO SHOT MACHINE VISION SYSTEM VIA JOINT SPARSE REPRESENTATIONS
Document Type and Number:
WIPO Patent Application WO/2019/018022
Kind Code:
A3
Abstract:
Described is a system that can recognize novel objects that the system has never before seen. The system uses a training image set to learn a model that maps visual features from known images to semantic attributes. The learned model is used to map visual features of an unseen input image to semantic attributes. The unseen input image is classified as belonging to an image class with a class label. A device is controlled based on the class label.
Inventors:
KOLOURI SOHEIL (US)
RAO SHANKAR (US)
KIM KYUNGNAM (US)
RAO SHANKAR (US)
KIM KYUNGNAM (US)
Application Number:
PCT/US2018/026951
Publication Date:
April 18, 2019
Filing Date:
April 10, 2018
Export Citation:
Assignee:
HRL LAB LLC (US)
International Classes:
G06K9/00; B60R21/0134; G06K9/72; G06N3/08
Foreign References:
| US20170006261A1 | 2017-01-05 | |||
| US20110191374A1 | 2011-08-04 | |||
| US20030202683A1 | 2003-10-30 | |||
| US20160239711A1 | 2016-08-18 |
Other References:
ZIMING ZHANG ET AL.: "Zero-Shot Learning via Joint Latent Similarity Embedding", THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), pages 6034 - 6042, XP033021802, ISSN: 10.1109/CVPR.2016.649
Attorney, Agent or Firm:
TOPE-MCKAY, Cary, R. (US)
Download PDF: