Video adaptation based on affective content with MPEG-21 DIA framework

We present a video adaptation system which takes account of users' preference on video affective content (AC) and limited network resource. AC directly causes user's attention, evaluation and memory, which also provides feasible entry for video highlight. According to user's preference, the proposed adaptation insures the video parcels with AC are allocated as much as possible network resource. The system is implemented with MPEG-21 digital item adaptation (DIA) framework which provides a generic video adaptation solution for all video formats and various usage environments by manipulating on XML files. XML file based adaptation avoids complex video computation. 30 students from various departments were invited to test the system and their responses were positive.