Automatic Concept Discovery from Parallel Text and Visual Corpora
2015 IEEE International Conference on Computer Vision (ICCV)(2015)
摘要
Humans connect language and vision to perceive the world. How to build a similar connection for computers? One possible way is via visual concepts, which are text terms that relate to visually discriminative entities. We propose an automatic visual concept discovery algorithm using parallel text and visual corpora; it filters text terms based on the visual discriminative power of the associated images, and groups them into concepts using visual and semantic similarities. We illustrate the applications of the discovered concepts using bidirectional image and sentence retrieval task and image tagging task, and show that the discovered concepts not only outperform several large sets of manually selected concepts significantly, but also achieves the state-of-the-art performance in the retrieval task.
更多查看译文
关键词
parallel text corpora,parallel visual corpora,visually discriminative entities,automatic visual concept discovery algorithm,text term filtering,visual similarities,semantic similarities,bidirectional image,sentence retrieval task,image tagging task
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络