Oh! I just meant it in the technical sense :). I was reading a blog and while reading it, I pondered over various things. The first thing that I thought of was “Why just Audio-Visual?”. Surely, the kind of meta-data talked about in the post is relevant only to audio, images and videos. But is that the limit? Is it not relevant to text - the form in which we have most of our data? I, for one can list things like when, where, by whom and in which meaning that can be associated to text(knol). The knol can be take from internet, from a book, or from notes. Surely that can help us find a lot about its content. Given the time-period when a person came to know about the knol, We can know about the complexity of the content(is it something deep or just introductory). Many of us have heard of semantic <insert keyword here> so does using that information to index also help? I think it does. In fact, We had done something very similar in last year’s Imagine cup with recog.

Recog uses the meta data, not only from text but also from audios and images too, to index them. It uses semantic indexing along with use of other meta-data to present the content to user. This meta data and the way to organize knowledge surely does spice up the things and opens up many possibilities for future.

Sounds interesting? It is and surely we are going to see some great innovations in this field soon (i hope :) )

Tags: future research, technology, textual-audio-visual

This entry was posted on Sunday, December 23rd, 2007 at 8:56 pm and is filed under research, technology. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.