Search (2 results, page 1 of 1)

0.015815454 = product of:
  0.04744636 = sum of:
    0.04744636 = weight(_text_:search in 3086) [ClassicSimilarity], result of:
      0.04744636 = score(doc=3086,freq=4.0), product of:
        0.1747324 = queryWeight, product of:
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.05027291 = queryNorm
        0.27153727 = fieldWeight in 3086, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3086)
  0.33333334 = coord(1/3)

Abstract

Improvements in network bandwidth along with dramatic drops in digital storage and processing costs have resulted in the explosive growth of multimedia (combinations of text, image, audio, and video) resources on the Internet and in digital repositories. A suite of computer technologies delivering speech, image, and natural language understanding can automatically derive descriptive metadata for such resources. Difficulties for end users ensue, however, with the tremendous volume and varying quality of automated metadata for multimedia information systems. This lecture surveys automatic metadata creation methods for dealing with multimedia information resources, using broadcast news, documentaries, and oral histories as examples. Strategies for improving the utility of such metadata are discussed, including computationally intensive approaches, leveraging multimodal redundancy, folding in context, and leaving precision-recall tradeoffs under user control. Interfaces building from automatically generated metadata are presented, illustrating the use of video surrogates in multimedia information systems. Traditional information retrieval evaluation is discussed through the annual National Institute of Standards and Technology TRECVID forum, with experiments on exploratory search extending the discussion beyond fact-finding to broader, longer term search activities of learning, analysis, synthesis, and discovery.

0.013419857 = product of:
  0.04025957 = sum of:
    0.04025957 = weight(_text_:search in 458) [ClassicSimilarity], result of:
      0.04025957 = score(doc=458,freq=2.0), product of:
        0.1747324 = queryWeight, product of:
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.05027291 = queryNorm
        0.230407 = fieldWeight in 458, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.475677 = idf(docFreq=3718, maxDocs=44218)
          0.046875 = fieldNorm(doc=458)
  0.33333334 = coord(1/3)

Abstract

Metadata describing multimedia can address a wide variety of purposes, from the purely physical characteristics of an item, to the circumstances surrounding its production, to attributes that cannot necessarily be determined by examining the item itself directly. These latter attributes, often dealing with "meaning" or interpretation of an item's content, are frequently deemed too difficult to determine and subject to individual and cultural variability. At the same time, however, research has shown that these abstract, interpretive attributes, which carry meaning, are frequently the ones for which people search. To describe an item fully, therefore, means to describe it at both the "syntactic" and the "semantic" levels. This article discusses the development of the semantic description schemes within the MPEG-7 standard from both a historical and an intellectual perspective, as well as the difficulties inherent in creating a descriptive schema that can fully capture the complexity of "narrative worlds."