Search (13 results, page 1 of 1)

  • × theme_ss:"Automatisches Indexieren"
  • × type_ss:"el"
  1. Mao, J.; Xu, W.; Yang, Y.; Wang, J.; Yuille, A.L.: Explain images with multimodal recurrent neural networks (2014) 0.03
    0.025052762 = product of:
      0.050105523 = sum of:
        0.050105523 = product of:
          0.07515828 = sum of:
            0.042919125 = weight(_text_:j in 1557) [ClassicSimilarity], result of:
              0.042919125 = score(doc=1557,freq=4.0), product of:
                0.14407694 = queryWeight, product of:
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.04534291 = queryNorm
                0.2978903 = fieldWeight in 1557, product of:
                  2.0 = tf(freq=4.0), with freq of:
                    4.0 = termFreq=4.0
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.046875 = fieldNorm(doc=1557)
            0.032239158 = weight(_text_:m in 1557) [ClassicSimilarity], result of:
              0.032239158 = score(doc=1557,freq=6.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.28572327 = fieldWeight in 1557, product of:
                  2.4494898 = tf(freq=6.0), with freq of:
                    6.0 = termFreq=6.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.046875 = fieldNorm(doc=1557)
          0.6666667 = coord(2/3)
      0.5 = coord(1/2)
    
    Abstract
    In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel sentence descriptions to explain the content of images. It directly models the probability distribution of generating a word given previous words and the image. Image descriptions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on three benchmark datasets (IAPR TC-12 [8], Flickr 8K [28], and Flickr 30K [13]). Our model outperforms the state-of-the-art generative method. In addition, the m-RNN model can be applied to retrieval tasks for retrieving images or sentences, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval.
  2. Donahue, J.; Hendricks, L.A.; Guadarrama, S.; Rohrbach, M.; Venugopalan, S.; Saenko, K.; Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description (2014) 0.01
    0.013600469 = product of:
      0.027200937 = sum of:
        0.027200937 = product of:
          0.040801406 = sum of:
            0.025290335 = weight(_text_:j in 1873) [ClassicSimilarity], result of:
              0.025290335 = score(doc=1873,freq=2.0), product of:
                0.14407694 = queryWeight, product of:
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.04534291 = queryNorm
                0.17553353 = fieldWeight in 1873, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=1873)
            0.015511071 = weight(_text_:m in 1873) [ClassicSimilarity], result of:
              0.015511071 = score(doc=1873,freq=2.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.13746867 = fieldWeight in 1873, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=1873)
          0.6666667 = coord(2/3)
      0.5 = coord(1/2)
    
  3. Peters, G.: Verschlagwortung und automatische Verfahren in der G+J Dokumentation (2003) 0.01
    0.008430112 = product of:
      0.016860224 = sum of:
        0.016860224 = product of:
          0.05058067 = sum of:
            0.05058067 = weight(_text_:j in 2377) [ClassicSimilarity], result of:
              0.05058067 = score(doc=2377,freq=2.0), product of:
                0.14407694 = queryWeight, product of:
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.04534291 = queryNorm
                0.35106707 = fieldWeight in 2377, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.078125 = fieldNorm(doc=2377)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  4. Junger, U.; Schwens, U.: ¬Die inhaltliche Erschließung des schriftlichen kulturellen Erbes auf dem Weg in die Zukunft : Automatische Vergabe von Schlagwörtern in der Deutschen Nationalbibliothek (2017) 0.01
    0.005119449 = product of:
      0.010238898 = sum of:
        0.010238898 = product of:
          0.030716693 = sum of:
            0.030716693 = weight(_text_:22 in 3780) [ClassicSimilarity], result of:
              0.030716693 = score(doc=3780,freq=2.0), product of:
                0.15878315 = queryWeight, product of:
                  3.5018296 = idf(docFreq=3622, maxDocs=44218)
                  0.04534291 = queryNorm
                0.19345059 = fieldWeight in 3780, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.5018296 = idf(docFreq=3622, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=3780)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
    Date
    19. 8.2017 9:24:22
  5. Mongin, L.; Fu, Y.Y.; Mostafa, J.: Open Archives data Service prototype and automated subject indexing using D-Lib archive content as a testbed (2003) 0.01
    0.0050580674 = product of:
      0.010116135 = sum of:
        0.010116135 = product of:
          0.030348403 = sum of:
            0.030348403 = weight(_text_:j in 1167) [ClassicSimilarity], result of:
              0.030348403 = score(doc=1167,freq=2.0), product of:
                0.14407694 = queryWeight, product of:
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.04534291 = queryNorm
                0.21064025 = fieldWeight in 1167, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.046875 = fieldNorm(doc=1167)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  6. Schöneberg, U.; Gödert, W.: Erschließung mathematischer Publikationen mittels linguistischer Verfahren (2012) 0.01
    0.0050580674 = product of:
      0.010116135 = sum of:
        0.010116135 = product of:
          0.030348403 = sum of:
            0.030348403 = weight(_text_:j in 1055) [ClassicSimilarity], result of:
              0.030348403 = score(doc=1055,freq=2.0), product of:
                0.14407694 = queryWeight, product of:
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.04534291 = queryNorm
                0.21064025 = fieldWeight in 1055, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.046875 = fieldNorm(doc=1055)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
    Source
    http://at.yorku.ca/c/b/f/j/99.htm
  7. Banerjee, K.; Johnson, M.: Improving access to archival collections with automated entity extraction (2015) 0.00
    0.0031022145 = product of:
      0.006204429 = sum of:
        0.006204429 = product of:
          0.018613286 = sum of:
            0.018613286 = weight(_text_:m in 2144) [ClassicSimilarity], result of:
              0.018613286 = score(doc=2144,freq=2.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.1649624 = fieldWeight in 2144, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.046875 = fieldNorm(doc=2144)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  8. Beckmann, R.; Hinrichs, I.; Janßen, M.; Milmeister, G.; Schäuble, P.: ¬Der Digitale Assistent DA-3 : Eine Plattform für die Inhaltserschließung (2019) 0.00
    0.0031022145 = product of:
      0.006204429 = sum of:
        0.006204429 = product of:
          0.018613286 = sum of:
            0.018613286 = weight(_text_:m in 5408) [ClassicSimilarity], result of:
              0.018613286 = score(doc=5408,freq=2.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.1649624 = fieldWeight in 5408, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.046875 = fieldNorm(doc=5408)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  9. Franke-Maier, M.; Beck, C.; Kasprzik, A.; Maas, J.F.; Pielmeier, S.; Wiesenmüller, H: ¬Ein Feuerwerk an Algorithmen und der Startschuss zur Bildung eines Kompetenznetzwerks für maschinelle Erschließung : Bericht zur Fachtagung Netzwerk maschinelle Erschließung an der Deutschen Nationalbibliothek am 10. und 11. Oktober 2019 (2020) 0.00
    0.0031022145 = product of:
      0.006204429 = sum of:
        0.006204429 = product of:
          0.018613286 = sum of:
            0.018613286 = weight(_text_:m in 5851) [ClassicSimilarity], result of:
              0.018613286 = score(doc=5851,freq=2.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.1649624 = fieldWeight in 5851, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.046875 = fieldNorm(doc=5851)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  10. Toepfer, M.; Kempf, A.O.: Automatische Indexierung auf Basis von Titeln und Autoren-Keywords : ein Werkstattbericht (2016) 0.00
    0.0025851787 = product of:
      0.0051703574 = sum of:
        0.0051703574 = product of:
          0.015511071 = sum of:
            0.015511071 = weight(_text_:m in 3209) [ClassicSimilarity], result of:
              0.015511071 = score(doc=3209,freq=2.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.13746867 = fieldWeight in 3209, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=3209)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  11. Toepfer, M.; Seifert, C.: Content-based quality estimation for automatic subject indexing of short texts under precision and recall constraints 0.00
    0.0025851787 = product of:
      0.0051703574 = sum of:
        0.0051703574 = product of:
          0.015511071 = sum of:
            0.015511071 = weight(_text_:m in 4309) [ClassicSimilarity], result of:
              0.015511071 = score(doc=4309,freq=2.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.13746867 = fieldWeight in 4309, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=4309)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  12. Markoff, J.: Researchers announce advance in image-recognition software (2014) 0.00
    0.002107528 = product of:
      0.004215056 = sum of:
        0.004215056 = product of:
          0.012645167 = sum of:
            0.012645167 = weight(_text_:j in 1875) [ClassicSimilarity], result of:
              0.012645167 = score(doc=1875,freq=2.0), product of:
                0.14407694 = queryWeight, product of:
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.04534291 = queryNorm
                0.08776677 = fieldWeight in 1875, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.1774964 = idf(docFreq=5010, maxDocs=44218)
                  0.01953125 = fieldNorm(doc=1875)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)
    
  13. Tavakolizadeh-Ravari, M.: Analysis of the long term dynamics in thesaurus developments and its consequences (2017) 0.00
    0.0020681429 = product of:
      0.0041362857 = sum of:
        0.0041362857 = product of:
          0.012408857 = sum of:
            0.012408857 = weight(_text_:m in 3081) [ClassicSimilarity], result of:
              0.012408857 = score(doc=3081,freq=2.0), product of:
                0.11283351 = queryWeight, product of:
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.04534291 = queryNorm
                0.10997493 = fieldWeight in 3081, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4884486 = idf(docFreq=9980, maxDocs=44218)
                  0.03125 = fieldNorm(doc=3081)
          0.33333334 = coord(1/3)
      0.5 = coord(1/2)