Jointly modeling embedding and translation to bridge video and language
US9807473B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 20, 2015 |
| Grant date | Oct 31, 2017 |
| Priority date | — |
| Expiry date | Nov 20, 2035 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N21/26603
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Video description generation using neural network training based on relevance and coherence is described. In some examples, long short-term memory with visual-semantic embedding (LSTM-E) can maximize the probability of generating the next word given previous words and visual content and can create a visual-semantic embedding space for enforcing the relationship between the semantics of an entire sentence and visual content. LSTM-E can include a 2-D and/or 3-D deep convolutional neural networks for learning powerful video representation, a deep recurrent neural network for generating sentences, and a joint embedding model for exploring the relationships between visual content and sentence semantics.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.