Automatic Concept Discovery from Parallel Text and Visual Corpora
This work addresses the challenge of bridging language and vision for AI systems, with applications in retrieval and tagging, though it appears incremental as it builds on existing methods for concept discovery.
The paper tackled the problem of connecting language and vision for computers by automatically discovering visual concepts from parallel text and visual corpora, resulting in state-of-the-art performance in bidirectional image and sentence retrieval and significant improvements over manually selected concepts.
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.