Document (#38875)

Author
Donahue, J.
Hendricks, L.A.
Guadarrama, S.
Rohrbach, M.
Venugopalan, S.
Saenko, K.
Darrell, T.
Title
Long-term recurrent convolutional networks for visual recognition and description
Source
http://arxiv.org/pdf/1411.4389v1.pdf
Year
2014
Abstract
Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep" in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.
Content
Vgl. auch: https://news.ycombinator.com/item?id=8621658.
Theme
Automatisches Indexieren
Form
Bilder

Similar documents (content)

  1. Mao, J.; Xu, W.; Yang, Y.; Wang, J.; Yuille, A.L.: Explain images with multimodal recurrent neural networks (2014) 0.54
    0.5406491 = sum of:
      0.5406491 = product of:
        1.3516228 = sum of:
          0.032049805 = weight(abstract_txt:state in 3022) [ClassicSimilarity], result of:
            0.032049805 = score(doc=3022,freq=2.0), product of:
              0.059898462 = queryWeight, product of:
                1.001025 = boost
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.012355663 = queryNorm
              0.5350689 = fieldWeight in 3022, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.03837399 = weight(abstract_txt:networks in 3022) [ClassicSimilarity], result of:
            0.03837399 = score(doc=3022,freq=2.0), product of:
              0.06753933 = queryWeight, product of:
                1.0629563 = boost
                5.142511 = idf(docFreq=686, maxDocs=43254)
                0.012355663 = queryNorm
              0.5681726 = fieldWeight in 3022, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.142511 = idf(docFreq=686, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.0437944 = weight(abstract_txt:image in 3022) [ClassicSimilarity], result of:
            0.0437944 = score(doc=3022,freq=2.0), product of:
              0.07375834 = queryWeight, product of:
                1.1108173 = boost
                5.374059 = idf(docFreq=544, maxDocs=43254)
                0.012355663 = queryNorm
              0.59375525 = fieldWeight in 3022, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.374059 = idf(docFreq=544, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.010011838 = weight(abstract_txt:which in 3022) [ClassicSimilarity], result of:
            0.010011838 = score(doc=3022,freq=1.0), product of:
              0.04377518 = queryWeight, product of:
                1.2102247 = boost
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.012355663 = queryNorm
              0.22871038 = fieldWeight in 3022, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.060172006 = weight(abstract_txt:directly in 3022) [ClassicSimilarity], result of:
            0.060172006 = score(doc=3022,freq=2.0), product of:
              0.091158055 = queryWeight, product of:
                1.234908 = boost
                5.9744015 = idf(docFreq=298, maxDocs=43254)
                0.012355663 = queryNorm
              0.66008437 = fieldWeight in 3022, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.9744015 = idf(docFreq=298, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.04210529 = weight(abstract_txt:tasks in 3022) [ClassicSimilarity], result of:
            0.04210529 = score(doc=3022,freq=1.0), product of:
              0.103624776 = queryWeight, product of:
                1.6125549 = boost
                5.2009544 = idf(docFreq=647, maxDocs=43254)
                0.012355663 = queryNorm
              0.40632457 = fieldWeight in 3022, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.2009544 = idf(docFreq=647, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.12680082 = weight(abstract_txt:deep in 3022) [ClassicSimilarity], result of:
            0.12680082 = score(doc=3022,freq=2.0), product of:
              0.17151833 = queryWeight, product of:
                2.0746171 = boost
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.012355663 = queryNorm
              0.7392844 = fieldWeight in 3022, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.48758298 = weight(abstract_txt:recurrent in 3022) [ClassicSimilarity], result of:
            0.48758298 = score(doc=3022,freq=2.0), product of:
              0.49912703 = queryWeight, product of:
                4.56891 = boost
                8.841632 = idf(docFreq=16, maxDocs=43254)
                0.012355663 = queryNorm
              0.97687155 = fieldWeight in 3022, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                8.841632 = idf(docFreq=16, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.3982465 = weight(abstract_txt:convolutional in 3022) [ClassicSimilarity], result of:
            0.3982465 = score(doc=3022,freq=1.0), product of:
              0.5494861 = queryWeight, product of:
                4.793861 = boost
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.012355663 = queryNorm
              0.7247617 = fieldWeight in 3022, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
          0.11248514 = weight(abstract_txt:models in 3022) [ClassicSimilarity], result of:
            0.11248514 = score(doc=3022,freq=1.0), product of:
              0.307652 = queryWeight, product of:
                5.320449 = boost
                4.679995 = idf(docFreq=1090, maxDocs=43254)
                0.012355663 = queryNorm
              0.3656246 = fieldWeight in 3022, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.679995 = idf(docFreq=1090, maxDocs=43254)
                0.078125 = fieldNorm(doc=3022)
        0.4 = coord(10/25)
    
  2. Karpathy, A.; Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions (2015) 0.26
    0.25718853 = sum of:
      0.25718853 = product of:
        1.0716189 = sum of:
          0.022662636 = weight(abstract_txt:state in 3333) [ClassicSimilarity], result of:
            0.022662636 = score(doc=3333,freq=1.0), product of:
              0.059898462 = queryWeight, product of:
                1.001025 = boost
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.012355663 = queryNorm
              0.37835088 = fieldWeight in 3333, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.078125 = fieldNorm(doc=3333)
          0.03837399 = weight(abstract_txt:networks in 3333) [ClassicSimilarity], result of:
            0.03837399 = score(doc=3333,freq=2.0), product of:
              0.06753933 = queryWeight, product of:
                1.0629563 = boost
                5.142511 = idf(docFreq=686, maxDocs=43254)
                0.012355663 = queryNorm
              0.5681726 = fieldWeight in 3333, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.142511 = idf(docFreq=686, maxDocs=43254)
                0.078125 = fieldNorm(doc=3333)
          0.05363697 = weight(abstract_txt:image in 3333) [ClassicSimilarity], result of:
            0.05363697 = score(doc=3333,freq=3.0), product of:
              0.07375834 = queryWeight, product of:
                1.1108173 = boost
                5.374059 = idf(docFreq=544, maxDocs=43254)
                0.012355663 = queryNorm
              0.7271987 = fieldWeight in 3333, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                5.374059 = idf(docFreq=544, maxDocs=43254)
                0.078125 = fieldNorm(doc=3333)
          0.07111587 = weight(abstract_txt:visual in 3333) [ClassicSimilarity], result of:
            0.07111587 = score(doc=3333,freq=1.0), product of:
              0.16175699 = queryWeight, product of:
                2.3263958 = boost
                5.627473 = idf(docFreq=422, maxDocs=43254)
                0.012355663 = queryNorm
              0.4396463 = fieldWeight in 3333, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.627473 = idf(docFreq=422, maxDocs=43254)
                0.078125 = fieldNorm(doc=3333)
          0.48758298 = weight(abstract_txt:recurrent in 3333) [ClassicSimilarity], result of:
            0.48758298 = score(doc=3333,freq=2.0), product of:
              0.49912703 = queryWeight, product of:
                4.56891 = boost
                8.841632 = idf(docFreq=16, maxDocs=43254)
                0.012355663 = queryNorm
              0.97687155 = fieldWeight in 3333, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                8.841632 = idf(docFreq=16, maxDocs=43254)
                0.078125 = fieldNorm(doc=3333)
          0.3982465 = weight(abstract_txt:convolutional in 3333) [ClassicSimilarity], result of:
            0.3982465 = score(doc=3333,freq=1.0), product of:
              0.5494861 = queryWeight, product of:
                4.793861 = boost
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.012355663 = queryNorm
              0.7247617 = fieldWeight in 3333, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.078125 = fieldNorm(doc=3333)
        0.24 = coord(6/25)
    
  3. Agarwal, B.; Ramampiaro, H.; Langseth, H.; Ruocco, M.: ¬A deep network model for paraphrase detection in short text messages (2018) 0.25
    0.25331324 = sum of:
      0.25331324 = product of:
        0.79160386 = sum of:
          0.018130109 = weight(abstract_txt:state in 44) [ClassicSimilarity], result of:
            0.018130109 = score(doc=44,freq=1.0), product of:
              0.059898462 = queryWeight, product of:
                1.001025 = boost
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.012355663 = queryNorm
              0.3026807 = fieldWeight in 44, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
          0.012834468 = weight(abstract_txt:they in 44) [ClassicSimilarity], result of:
            0.012834468 = score(doc=44,freq=1.0), product of:
              0.05446252 = queryWeight, product of:
                1.1690459 = boost
                3.7705102 = idf(docFreq=2708, maxDocs=43254)
                0.012355663 = queryNorm
              0.23565689 = fieldWeight in 44, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.7705102 = idf(docFreq=2708, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
          0.011327101 = weight(abstract_txt:which in 44) [ClassicSimilarity], result of:
            0.011327101 = score(doc=44,freq=2.0), product of:
              0.04377518 = queryWeight, product of:
                1.2102247 = boost
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.012355663 = queryNorm
              0.25875625 = fieldWeight in 44, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
          0.035735916 = weight(abstract_txt:term in 44) [ClassicSimilarity], result of:
            0.035735916 = score(doc=44,freq=1.0), product of:
              0.11863933 = queryWeight, product of:
                1.9923536 = boost
                4.819436 = idf(docFreq=948, maxDocs=43254)
                0.012355663 = queryNorm
              0.30121475 = fieldWeight in 44, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.819436 = idf(docFreq=948, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
          0.07172938 = weight(abstract_txt:deep in 44) [ClassicSimilarity], result of:
            0.07172938 = score(doc=44,freq=1.0), product of:
              0.17151833 = queryWeight, product of:
                2.0746171 = boost
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.012355663 = queryNorm
              0.4182024 = fieldWeight in 44, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
          0.047431096 = weight(abstract_txt:long in 44) [ClassicSimilarity], result of:
            0.047431096 = score(doc=44,freq=1.0), product of:
              0.14328504 = queryWeight, product of:
                2.189538 = boost
                5.2964187 = idf(docFreq=588, maxDocs=43254)
                0.012355663 = queryNorm
              0.33102617 = fieldWeight in 44, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.2964187 = idf(docFreq=588, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
          0.2758186 = weight(abstract_txt:recurrent in 44) [ClassicSimilarity], result of:
            0.2758186 = score(doc=44,freq=1.0), product of:
              0.49912703 = queryWeight, product of:
                4.56891 = boost
                8.841632 = idf(docFreq=16, maxDocs=43254)
                0.012355663 = queryNorm
              0.552602 = fieldWeight in 44, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                8.841632 = idf(docFreq=16, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
          0.3185972 = weight(abstract_txt:convolutional in 44) [ClassicSimilarity], result of:
            0.3185972 = score(doc=44,freq=1.0), product of:
              0.5494861 = queryWeight, product of:
                4.793861 = boost
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.012355663 = queryNorm
              0.57980937 = fieldWeight in 44, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.0625 = fieldNorm(doc=44)
        0.32 = coord(8/25)
    
  4. Wang, P.; Li, X.: Assessing the quality of information on Wikipedia : a deep-learning approach (2020) 0.24
    0.2436465 = sum of:
      0.2436465 = product of:
        0.76139534 = sum of:
          0.0080331005 = weight(abstract_txt:have in 506) [ClassicSimilarity], result of:
            0.0080331005 = score(doc=506,freq=1.0), product of:
              0.039850578 = queryWeight, product of:
                3.2252884 = idf(docFreq=4672, maxDocs=43254)
                0.012355663 = queryNorm
              0.20158052 = fieldWeight in 506, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.2252884 = idf(docFreq=4672, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
          0.018130109 = weight(abstract_txt:state in 506) [ClassicSimilarity], result of:
            0.018130109 = score(doc=506,freq=1.0), product of:
              0.059898462 = queryWeight, product of:
                1.001025 = boost
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.012355663 = queryNorm
              0.3026807 = fieldWeight in 506, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.842891 = idf(docFreq=926, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
          0.00800947 = weight(abstract_txt:which in 506) [ClassicSimilarity], result of:
            0.00800947 = score(doc=506,freq=1.0), product of:
              0.04377518 = queryWeight, product of:
                1.2102247 = boost
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.012355663 = queryNorm
              0.1829683 = fieldWeight in 506, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
          0.035735916 = weight(abstract_txt:term in 506) [ClassicSimilarity], result of:
            0.035735916 = score(doc=506,freq=1.0), product of:
              0.11863933 = queryWeight, product of:
                1.9923536 = boost
                4.819436 = idf(docFreq=948, maxDocs=43254)
                0.012355663 = queryNorm
              0.30121475 = fieldWeight in 506, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.819436 = idf(docFreq=948, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
          0.124238916 = weight(abstract_txt:deep in 506) [ClassicSimilarity], result of:
            0.124238916 = score(doc=506,freq=3.0), product of:
              0.17151833 = queryWeight, product of:
                2.0746171 = boost
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.012355663 = queryNorm
              0.7243478 = fieldWeight in 506, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
          0.047431096 = weight(abstract_txt:long in 506) [ClassicSimilarity], result of:
            0.047431096 = score(doc=506,freq=1.0), product of:
              0.14328504 = queryWeight, product of:
                2.189538 = boost
                5.2964187 = idf(docFreq=588, maxDocs=43254)
                0.012355663 = queryNorm
              0.33102617 = fieldWeight in 506, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.2964187 = idf(docFreq=588, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
          0.3185972 = weight(abstract_txt:convolutional in 506) [ClassicSimilarity], result of:
            0.3185972 = score(doc=506,freq=1.0), product of:
              0.5494861 = queryWeight, product of:
                4.793861 = boost
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.012355663 = queryNorm
              0.57980937 = fieldWeight in 506, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
          0.20121954 = weight(abstract_txt:models in 506) [ClassicSimilarity], result of:
            0.20121954 = score(doc=506,freq=5.0), product of:
              0.307652 = queryWeight, product of:
                5.320449 = boost
                4.679995 = idf(docFreq=1090, maxDocs=43254)
                0.012355663 = queryNorm
              0.6540492 = fieldWeight in 506, product of:
                2.236068 = tf(freq=5.0), with freq of:
                  5.0 = termFreq=5.0
                4.679995 = idf(docFreq=1090, maxDocs=43254)
                0.0625 = fieldNorm(doc=506)
        0.32 = coord(8/25)
    
  5. Zou, J.; Thoma, G.; Antani, S.: Unified deep neural network for segmentation and labeling of multipanel biomedical figures (2020) 0.17
    0.16903888 = sum of:
      0.16903888 = product of:
        0.6037103 = sum of:
          0.021707607 = weight(abstract_txt:networks in 1012) [ClassicSimilarity], result of:
            0.021707607 = score(doc=1012,freq=1.0), product of:
              0.06753933 = queryWeight, product of:
                1.0629563 = boost
                5.142511 = idf(docFreq=686, maxDocs=43254)
                0.012355663 = queryNorm
              0.32140693 = fieldWeight in 1012, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.142511 = idf(docFreq=686, maxDocs=43254)
                0.0625 = fieldNorm(doc=1012)
          0.024773857 = weight(abstract_txt:image in 1012) [ClassicSimilarity], result of:
            0.024773857 = score(doc=1012,freq=1.0), product of:
              0.07375834 = queryWeight, product of:
                1.1108173 = boost
                5.374059 = idf(docFreq=544, maxDocs=43254)
                0.012355663 = queryNorm
              0.3358787 = fieldWeight in 1012, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.374059 = idf(docFreq=544, maxDocs=43254)
                0.0625 = fieldNorm(doc=1012)
          0.00800947 = weight(abstract_txt:which in 1012) [ClassicSimilarity], result of:
            0.00800947 = score(doc=1012,freq=1.0), product of:
              0.04377518 = queryWeight, product of:
                1.2102247 = boost
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.012355663 = queryNorm
              0.1829683 = fieldWeight in 1012, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                2.9274929 = idf(docFreq=6293, maxDocs=43254)
                0.0625 = fieldNorm(doc=1012)
          0.07843437 = weight(abstract_txt:recognition in 1012) [ClassicSimilarity], result of:
            0.07843437 = score(doc=1012,freq=2.0), product of:
              0.14449076 = queryWeight, product of:
                1.9041569 = boost
                6.1414557 = idf(docFreq=252, maxDocs=43254)
                0.012355663 = queryNorm
              0.5428331 = fieldWeight in 1012, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.1414557 = idf(docFreq=252, maxDocs=43254)
                0.0625 = fieldNorm(doc=1012)
          0.07172938 = weight(abstract_txt:deep in 1012) [ClassicSimilarity], result of:
            0.07172938 = score(doc=1012,freq=1.0), product of:
              0.17151833 = queryWeight, product of:
                2.0746171 = boost
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.012355663 = queryNorm
              0.4182024 = fieldWeight in 1012, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.6912384 = idf(docFreq=145, maxDocs=43254)
                0.0625 = fieldNorm(doc=1012)
          0.08045842 = weight(abstract_txt:visual in 1012) [ClassicSimilarity], result of:
            0.08045842 = score(doc=1012,freq=2.0), product of:
              0.16175699 = queryWeight, product of:
                2.3263958 = boost
                5.627473 = idf(docFreq=422, maxDocs=43254)
                0.012355663 = queryNorm
              0.49740303 = fieldWeight in 1012, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.627473 = idf(docFreq=422, maxDocs=43254)
                0.0625 = fieldNorm(doc=1012)
          0.3185972 = weight(abstract_txt:convolutional in 1012) [ClassicSimilarity], result of:
            0.3185972 = score(doc=1012,freq=1.0), product of:
              0.5494861 = queryWeight, product of:
                4.793861 = boost
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.012355663 = queryNorm
              0.57980937 = fieldWeight in 1012, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.27695 = idf(docFreq=10, maxDocs=43254)
                0.0625 = fieldNorm(doc=1012)
        0.28 = coord(7/25)