Track:
Contents
Downloads:
Abstract:
Significant advances have been achieved over the past decade in language processing for information extraction from unstructured multilingual text (see, e.g., trec.nist.gov). However, the advent of increasingly large collections of audio (e.g., iTunes), imagery (e.g., Flickr), and video (e.g., YouTube) together with rapid and widespread growth and innovation in new information services (e.g., blogging, podcasting, media editing) is driving the need not only for multimedia retrieval but also for information extraction from and across media. Scientists and engineers are innovating in new challenges such as multimodal sentiment analysis, multimodal summarization, and collaborative multimedia editing. While largely independent research communities have addressed extracting information from single media (e.g., text, imagery, audio), to date there has been no forum focused exclusively on cross media information extraction