Đang chuẩn bị liên kết để tải về tài liệu:
Handbook of Multimedia for Digital Entertainment and Arts- P3

Handbook of Multimedia for Digital Entertainment and Arts- P3: The advances in computer entertainment, multi-player and online games, technology-enabled art, culture and performance have created a new form of entertainment and art, which attracts and absorbs their participants. The fantastic success of this new field has influenced the development of the new digital entertainment industry and related products and services, which has impacted every aspect of our lives. | 46 N. Kamimaeda et al. Original Metadata Associated Concept Dictionary New Metadata Genre Title Keyword. detailed Genre Personality Impression Lifestyle. Origine Attribute Origine Value Destination Attribute Destination Value Cast A Personality Intelligent Cast B Imoression Kind Cast C Detailed Genre Love Storv Cast D Kevword Summer Cast E Character Tender Heart Title Star Treasure Kevword Soace Title EB Lifestyle Earlv Adaoter Genre Golf Kevword PGA Kevword Earth Kevword Planets Keyword Johnnvs Detailed Genre teen heartthrob Fig. 15 Automatic Metadata Expansion title keywords and so on. Content profiles CP are created from these data and they consist of some vectors like CP i ContentId Attribute Id Value Id . ContentId is a primary key to distinguish between content. Attribute is a class unit such as cast genre and so on. Value is an instance of the class. For example comedy sports or drama is a value of an attribute of the genre. We can also find that A B C D or E is a value of an attribute of cast Figure 15 . AME creates new content metadata which are ContentId Destination Attribute Destination Value from the original content metadata which are ContentId Origin Attribute Origin Value . Consider the following example with content named 001. It has cast of Mr. A which becomes vector 001 Cast Mr. A . The content gets new metadata 001 Personality Intelligent since the ACD declares that the customers think Mr. A is an intelligent person. Therefore our system can use not only original content metadata but also these expanded metadata for recommendation purposes. These processes are performed in our system as a part of content metadata creation in the mining engine. If the ACD has knowledge based on the lifestyle for example a person who likes the title EB is Early Adapter or Follower likes Cast A it is very efficient to apply this method to cross-category recommendation. Lifestyle is very suitable as common metadata. Moreover if the content metadata is expanded using