Filters








20 Hits in 8.0 sec

Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network [article]

Yu Liu, Jianlong Fu, Tao Mei, Chang Wen Chen
2016 arXiv   pre-print
In this paper, we propose a novel visual storytelling approach with Bidirectional Multi-thread Recurrent Neural Network (BMRNN).  ...  A typical photo story consists of a global timeline with multi-thread local storylines, where each storyline occurs in one different scene.  ...  To this end, we propose a novel neural network called skip Gated Recurrent Unit (sGRU) (Section 2), and a Bidirectional Multi-thread RNN (BMRNN) architecture (Section 3), to solve the pseudo-gap problem  ... 
arXiv:1606.00625v1 fatcat:na5fjeg3uzc3zd4xuudsm4boai

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.  ...  At the end of this paper, we conclude the further development of BMs in a more general view.  ...  Deep learning models, such as convolutional neural networks (CNNs) [2, 3] , recurrent neural networks (RNNs) [4, 5] , generative adversarial networks (GANs) [6, 7] , graph neural networks (GNNs) [8  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  This doctoral thesis covers some of my advances in electron microscopy with deep learning.  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4598227 fatcat:hm2ksetmsvf37adjjefmmbakvq

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  This doctoral thesis covers some of my advances in electron microscopy with deep learning.  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4591029 fatcat:zn2hvfyupvdwlnvsscdgswayci

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  This doctoral thesis covers some of my advances in electron microscopy with deep learning.  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4399748 fatcat:63ggmnviczg6vlnqugbnrexsgy

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  This doctoral thesis covers some of my advances in electron microscopy with deep learning.  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4413249 fatcat:35qbhenysfhvza2roihx52afuy

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  This doctoral thesis covers some of my advances in electron microscopy with deep learning.  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4415407 fatcat:6dejwzzpmfegnfuktrld6zgpiq

Advances in Electron Microscopy with Deep Learning

Jeffrey Ede
2020 Zenodo  
, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional  ...  This doctoral thesis covers some of my advances in electron microscopy with deep learning.  ...  In addition, part of the text in section 1.2 is adapted from our earlier work with permission 201 under a Creative Commons Attribution 4.0 73 license.  ... 
doi:10.5281/zenodo.4429792 fatcat:qs6yuapx4vdbdmwna7ix7nnwty

Knowledge Extracted from Copernicus Satellite Data

Dumitru Octavian, Schwarz Gottfried, Eltoft Torbjørn, Kræmer Thomas, Wagner Penelope, Hughes Nick, Arthus David, Fleming Andrew, Koubarakis Manolis, Datcu Mihai
2019 Zenodo  
The proposed methodology uses new paradigms from Recurrent Neural Networks and Generative Adversarial Networks, supported by Bayesian and Information Bottleneck concepts. References 1.  ...  By applying an already established active learning approach based on a Support Vector Machine with relevance feedback [2], we can limit ourselves to a limited number of typical satellite images to extract  ...  Popularization platform focus on network popularization of investigation knowledge.  ... 
doi:10.5281/zenodo.3941573 fatcat:zzifwgljifck5bpjnboetsftfu

MMEDIA 2012 The Fourth International Conferences on Advances in Multimedia MMEDIA 2012 PROGRAM COMMITTEE MMEDIA Advisory Committee MMEDIA 2012 Technical Program Committee

Chamonix, Mont Blanc, France, David Newell, Dan Dumitru, Burdescu, Philip Davies, Poole College, Jean-Claude Moissinac, Telecom Paristech, France, Patrice Alface (+81 others)
unpublished
conferencing, streaming video and audio.  ...  Large and specialized databases together with these technological achievements have brought true mobile multimedia experiences to mobile customers.  ...  The paper has been elaborated in the framework of the IT4Innovations Centre of Excellence project, reg. no.  ... 
fatcat:krhwyvwrhzdynmouyuzjiq65ki

Book of Abstracts of the Digital Humanities in the Nordic Countries 5th conference. Riga, 20–23 October 2020 [article]

Sanita Reinsone, Anda Baklāne, Jānis Daugavietis
2020 Zenodo  
Book of Abstracts DHN, Rīga 2020 Book of Abstracts of the Digital Humanities in the Nordic Countries 5th conference.  ...  Literature, Folklore and Art (University of Latvia) lulfmi.lv Rīga, 2020 ISBN 978-9984-850-83-2 DOI 10.5281/zenodo.4107117  ...  We also thank the library of the Technische Acknowledgements This work has been supported by the European Union's Horizon 2020 research and innovation programme under grant 770299 (NewsEye).  ... 
doi:10.5281/zenodo.4107117 fatcat:6ongky6p5rab7gvtawnjmp2ofm

Learning-based face reconstruction and editing [article]

Hyeongwoo Kim, Universität Des Saarlandes
2020
It is based on a generative neural network with a novel space-time architecture, which enables photo-realistic re-animation of portrait videos using an input video.  ...  Photo-realistic face editing -an important basis for a wide range of applications in movie and game productions, and applications for mobile devices -is based on computationally expensive algorithms that  ...  of eye blinking using recurrent neural networks [Li et al. 2018 ].  ... 
doi:10.22028/d291-32394 fatcat:w2ynq7nz25hlvl4v6td4ifiiqy

and On-line Learning eLmL 2017 COMMITTEE eLmL Steering Committee

Ahmed Mohamed, Fahmy Yousef, Maiga Chang, Hironori Washizaki, Ivan Ganchev, Ben-David Yifat, Kolikant, Maiga Chang, Hironori Washizaki, Ivan Ganchev, Ben-David Yifat, Kolikant (+55 others)
2017 The Ninth International Conference on Mobile, Hybrid, The ninth edition of the International Conference on Mobile, Hybrid, and On-line Learning   unpublished
The goal of the eLmL 2017 conference was to provide an overview of technologies, approaches, and trends that are happening right now.  ...  We hope that eLmL 2017 was a successful international forum for the exchange of ideas and results between academia and industry and for the promotion of progress in eLearning research.  ...  Special thanks to the research team in educational technology seminar, and school of computer science and information technology at Northeast Normal University.  ... 
fatcat:qex5su5c3fd2vlncczyh4mtav4

Proceedings of the Seminar "Research Trends in Media Informatics"

(:Unkn)Unknown, Universität Ulm, Florian Schaub, Stefan Dietzel, Boto Zsolt Bako, Bastian Könings, Elmar Schoch, Björn Wiedersheim, Michael Weber
2016
The Internet, Web 2.0, Social Networks, Ubiquitous Computing, Computer Graphics, Usability, Social Interactions, HCI, and Privacy are just a few examples.  ...  This seminar aims to provide an overview and a closer look at research directions and current and future challenges that are focus of active research around the world and at our Institute.  ...  Color code symbolizes bidirectional links due to hosts from different nodes. Figure 3 . 3 Figure3. Social network as multi-graph for persons and events in Table I[8] Figure 4 . 4 Figure 4.  ... 
doi:10.18725/oparu-3892 fatcat:jflgj7nspfd3pfwdkagkrbwij4

Learning from Multimodal Web Data

John Miles Hessel
2020
The ultimate aim of this line of work is to build models capable of drawing connections between different modes of data, e.g., images+text.  ...  We find not only that our scoring method aligns with human judgements, but that concreteness is context specific: our method discovers that "London" is a consistent, identifiable visual concept in an image  ...  We also ran experiments encoding text using order-aware recurrent neural networks, but we did not observe significant performance differences.  ... 
doi:10.7298/fzce-qv86 fatcat:limoc6b6xjgm5b2dbzh3f72tuq
« Previous Showing results 1 — 15 out of 20 results