International Thyrrenian Workshop on Digital Communications, Advanced Methods for Multimedia Signal Processing, September 8-11, 2002, Capri, Italy
In this paper, we present a new approach to combine text and video in the automatic construction of summaries for audio-video sequences. This extends our previous work which was based on video only. Here, we generalize the Maximum Recollection Principle we were employing and we show how this same principle can be used to build summaries from text, based on several strategies. We present some experimental results in the evaluation of these strategies. Finally, we show how this novel principle can be used to combine text and video information for automatic summarization.
Type:
Conference
City:
Capri
Date:
2002-09-08
Department:
Data Science
Eurecom Ref:
1114
