Unified embedding with metric learning for zero-exemplar event detection
US10496885B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 21, 2017 |
| Grant date | Dec 3, 2019 |
| Priority date | — |
| Expiry date | Aug 29, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/44
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method, a computer-readable medium, and an apparatus for zero-exemplar event detection are provided. The apparatus may receive a plurality of text blocks, each of which may describe one of a plurality of pre-defined events. The apparatus may receive a plurality of training videos, each of which may be associated with one of the plurality of text blocks. The apparatus may propagate each text block through a neural network to obtain a textual representation in a joint space of textual and video representations. The apparatus may propagate each training video through the neural network to obtain a visual representation in the joint space. The apparatus may adjust parameters of the neural network to reduce, for each pair of associated text block and training video, the distance in the joint space between the textual representation of the associated text block and the visual representation of the associated training video.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.