Yiqing LiangWayne WolfBede LiuJeffrey Huang
We integrated a practical digital video database system based on language and image analysis with components from digital video processing, still image search, information retrieval, closed captioning processing. The attempt is to utilize the multiple modalities of information in video and implement data fusion among the multiple modalities; image information, speech/dialog information, closed captioning information, sound track information such as music, gunfire, explosion, caption information, motion information, temporal information. Effort is made to allow access video contents at different levels including video program level, scene level, shot level, and object level. Approaches of browsing, subject-based classification, and random retrieving are available to gain access to the contents.
C. Y. Roger ChenDikran S. MeliksetianLarry J. LiuMartin C. Chang
Olivier CroquetteJean‐Philippe VandeborreMohamed DaoudiChristophe Chaillou