| Sundaram, H., Xie, L., and Chang, S.F. A Utility Framework for the Automatic Generation of Audio-Visual Skims. ACM Multimedia 2002. |
....elements. This definition is easily extended in a hierarchical fashion (e.g. a dialog sequence is an entity, whose constituents are shots that share a topological property adjacent shots differ, while every second shot is alike. Such definition is similar to the one that we introduced in [3]. Complex entities can be defined by more sophisticated properties. For example, syntactic entities like recurrent anchor shots in news, pitching shots in baseball, and structured dialog sequences in films can be defined by syntactic relations among elements in the data. Semantic entities like ....
....attributes in multiple dimensions. In addition to SNR, other dimensions include temporal smoothness, audio visual rhythm, comprehensibility (see Section 3.2) coherence, etc. The last three have been included in the utility model used in our prior work of optimal audio visual skim generation [3]. 2.4.2 Relations among Adaptation, Resource, and Figure 2 shows the relationships among the adaptation space, the resource space, and the utility space. Given a content entity, e, the adaptation space represents the conceptual space of all possible adaptation operations. adaptation original ....
[Article contains additional citation context not shown here]
H. Sundaram, L. Xie,, and S.-F. Chang, "A Utility Framework for the Automatic Generation of AudioVisual Skims," ACM Multimedia, Juan-les-Pins, France, Dec. 2002.
No context found.
Sundaram, H., Xie, L., and Chang, S.F. A Utility Framework for the Automatic Generation of Audio-Visual Skims. ACM Multimedia 2002.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC