Multimodal Alignment of Scholarly Documents and Their Presentations
Research Area: Digital Libraries Year: 2013
Type of Publication: In Proceedings Keywords: Digital library, fine-grained document alignment slide presentation, slide image classification
Authors:
  • Bamdad Bahrani
  • Min-Yen Kan
 
   
Note:
Short Paper.
Abstract:
We present a multimodal system for aligning scholarly documents to corresponding presentations in a fi ne-grained manner (i.e., per presentation slide and per paper section). Our method improves upon a state-of-the-art baseline that em- ploys only textual similarity. Based on an analysis of base line errors, we propose a three-pronged alignment system that combines textual, image, and ordering information to establish alignment. Our results show a statistically signifi cant improvement of 25%, con firming the importance of visual content in improving alignment accuracy.
Digital version