首页>
外国专利>
Named entity recognition visual context and caption data
Named entity recognition visual context and caption data
展开▼
机译:命名实体识别视觉上下文和标题数据
展开▼
页面导航
摘要
著录项
相似文献
摘要
A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use a visual attention based mechanism to generate a visual context representation from an image and caption. The system can use the visual context representation to identify one or more terms of the caption as a named entity.
展开▼