Learning Multimodal Affinities for Textual Editing in Images
This addresses the challenge of editing text in document images for users dealing with abundant document data, though it is incremental as it builds on existing multimodal representation techniques.
The paper tackles the problem of automatically clustering textual entities in document images by learning multimodal affinities based on visual style, text content, and geometric context, using an unsupervised deep optimization scheme to enable various editing operations.
Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent. Unlike natural images that capture physical objects, document-images contain a significant amount of text with critical semantics and complicated layouts. In this work, we devise a generic unsupervised technique to learn multimodal affinities between textual entities in a document-image, considering their visual style, the content of their underlying text and their geometric context within the image. We then use these learned affinities to automatically cluster the textual entities in the image into different semantic groups. The core of our approach is a deep optimization scheme dedicated for an image provided by the user that detects and leverages reliable pairwise connections in the multimodal representation of the textual elements in order to properly learn the affinities. We show that our technique can operate on highly varying images spanning a wide range of documents and demonstrate its applicability for various editing operations manipulating the content, appearance and geometry of the image.