-
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
0.009676432 = product of:
0.067735024 = sum of:
0.067735024 = weight(_text_:interpretation in 1873) [ClassicSimilarity], result of:
0.067735024 = score(doc=1873,freq=2.0), product of:
0.21405315 = queryWeight, product of:
5.7281795 = idf(docFreq=390, maxDocs=44218)
0.037368443 = queryNorm
0.3164402 = fieldWeight in 1873, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
5.7281795 = idf(docFreq=390, maxDocs=44218)
0.0390625 = fieldNorm(doc=1873)
0.14285715 = coord(1/7)
- 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.
-
Schöneberg, U.; Gödert, W.: Erschließung mathematischer Publikationen mittels linguistischer Verfahren (2012)
0.00
0.0041475273 = product of:
0.029032689 = sum of:
0.029032689 = product of:
0.058065377 = sum of:
0.058065377 = weight(_text_:anwendung in 1055) [ClassicSimilarity], result of:
0.058065377 = score(doc=1055,freq=2.0), product of:
0.1809185 = queryWeight, product of:
4.8414783 = idf(docFreq=948, maxDocs=44218)
0.037368443 = queryNorm
0.3209477 = fieldWeight in 1055, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.8414783 = idf(docFreq=948, maxDocs=44218)
0.046875 = fieldNorm(doc=1055)
0.5 = coord(1/2)
0.14285715 = coord(1/7)
- Abstract
- Die Zahl der mathematik-relevanten Publikationn steigt von Jahr zu Jahr an. Referatedienste wie da Zentralblatt MATH und Mathematical Reviews erfassen die bibliographischen Daten, erschließen die Arbeiten inhaltlich und machen sie - heute über Datenbanken, früher in gedruckter Form - für den Nutzer suchbar. Keywords sind ein wesentlicher Bestandteil der inhaltlichen Erschließung der Publikationen. Keywords sind meist keine einzelnen Wörter, sondern Mehrwortphrasen. Das legt die Anwendung linguistischer Methoden und Verfahren nahe. Die an der FH Köln entwickelte Software 'Lingo' wurde für die speziellen Anforderungen mathematischer Texte angepasst und sowohl zum Aufbau eines kontrollierten Vokabulars als auch zur Extraction von Keywords aus mathematischen Publikationen genutzt. Es ist geplant, über eine Verknüpfung von kontrolliertem Vokabular und der Mathematical Subject Classification Methoden für die automatische Klassifikation für den Referatedienst Zentralblatt MATH zu entwickeln und zu erproben.
-
Tavakolizadeh-Ravari, M.: Analysis of the long term dynamics in thesaurus developments and its consequences (2017)
0.00
0.002765018 = product of:
0.019355126 = sum of:
0.019355126 = product of:
0.03871025 = sum of:
0.03871025 = weight(_text_:anwendung in 3081) [ClassicSimilarity], result of:
0.03871025 = score(doc=3081,freq=2.0), product of:
0.1809185 = queryWeight, product of:
4.8414783 = idf(docFreq=948, maxDocs=44218)
0.037368443 = queryNorm
0.21396513 = fieldWeight in 3081, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.8414783 = idf(docFreq=948, maxDocs=44218)
0.03125 = fieldNorm(doc=3081)
0.5 = coord(1/2)
0.14285715 = coord(1/7)
- Theme
- Konzeption und Anwendung des Prinzips Thesaurus
-
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)
0.00
0.0018081815 = product of:
0.01265727 = sum of:
0.01265727 = product of:
0.02531454 = sum of:
0.02531454 = weight(_text_:22 in 3780) [ClassicSimilarity], result of:
0.02531454 = score(doc=3780,freq=2.0), product of:
0.13085791 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.037368443 = 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)
0.5 = coord(1/2)
0.14285715 = coord(1/7)
- Date
- 19. 8.2017 9:24:22
