VideoQ: an automated content based video search system using visual cues
MULTIMEDIA '97 Proceedings of the fifth ACM international conference on Multimedia
Querying Multimedia Presentations Based on Content
IEEE Transactions on Knowledge and Data Engineering
A semantic model for flash retrieval using co-occurrence analysis
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Hi-index | 0.00 |
Flash is undergoing an explosive spread as a new prevailing media format on the Web. Unfortunately, few research efforts have been devoted to content-based Flash retrieval (CBFR) in IR community, which goes against the utilization of the enormous Flash resources. In this paper, Flash animation in 3-layer architecture is presented after it is segmented based on its visual features to a series of scenes on time-line of the production process. A promising approach of Flash animation retrieval is proposed based on the visual features of scenes and some meta-parameters. An experimental prototype system of Flash animation retrieval with roughly 100,000 Flash animations in total is built. The primary experiment demonstrates the flexibility and the effectiveness of our approach of CBFR.