Filters








7,411 Hits in 14.9 sec

D9.4 - Report on Dissemination Activities and Update of the Dissemination Plan v1

Ignacio Lacalle, Benjamin Molina, Carlos E. Palau, Joao Costa, Olivier Le Brun
2021 Zenodo  
In this document, a comprehensive description of the PIXEL's role in every industrial niche, scientific forum and public exposure in order to maximize both innovation and impact.  ...  This deliverable reflects and formalizes the events, scientific actions and industrial dissemination planned.  ...  Additionally, continuously posting short and dynamic videos, in order to let the global audience know PIXEL in a light and entertaining way.  ... 
doi:10.5281/zenodo.5553133 fatcat:c2yhdrxzfbbmzgjt53atqv2wum

A predictive processing model of episodic memory and time perception [article]

Zafeirios Fountas, Anastasia Sylaidi, Kyriacos Nikiforou, Anil Seth, Murray Shanahan, Warrick Roseboom
2020 bioRxiv   pre-print
Our approach provides an end-to-end model of duration perception from natural stimulus processing to estimation and from current experience to recalling the past, providing a new understanding of this  ...  Model-based estimates matched human reports, replicating key qualitative biases including differences by cognitive load, scene type, and judgement (prospective or retrospective).  ...  The authors would like to thank Karl Friston for insightful comments on the theoretical model presented here and Chris Bird for comments on a previous version of the manuscript.  ... 
doi:10.1101/2020.02.17.953133 fatcat:2c4bxom725f7xbveirg4fzzl54

Advances and Challenges in Deep Lip Reading [article]

Marzieh Oghbaie, Arian Sabaghi, Kooshan Hashemifard, Mohammad Akbari
2021 arXiv   pre-print
Finally, we introduce some typical VSR application concerns and impediments to real-world scenarios as well as future research directions.  ...  Advancements in these directions will expedite the transformation of silent speech interface from theory to practice. We also discuss the main modules of a VSR pipeline and the influential datasets.  ...  Watch, Listen, Attend and Spell (WLAS) [33] and Multi-view Watch, Attend and Spell (MV-WAS) [36] also adopt MT strategy in their spatial feature extractors.  ... 
arXiv:2110.07879v1 fatcat:eimcuzdz5va3vdlgw2g7y25tki

stagNet: An Attentive Semantic RNN for Group Activity and Individual Action Recognition

Mengshi Qi, Yunhong Wang, Jie Qin, Annan Li, Jiebo Luo, Luc Van Gool
2019 IEEE transactions on circuits and systems for video technology (Print)  
In a complex dynamic scene, a crucial yet challenging issue is how to better model the spatio-temporal contextual information and inter-person relationship.  ...  attention mechanism and semantic graph modeling.  ...  The method in the paper proposed an end-to-end deep reinforcement approach which introduces an agent to classify videos only by watching a small portion of frames, based on "fast forward" and "adaptive  ... 
doi:10.1109/tcsvt.2019.2894161 fatcat:wcjvyo3wgfbsfcew4x62sw6cfi

ActivityNet Challenge 2017 Summary [article]

Bernard Ghanem, Juan Carlos Niebles, Cees Snoek, Fabian Caba Heilbron, Humam Alwassel, Ranjay Khrisna, Victor Escorcia, Kenji Hata, Shyamal Buch
2017 arXiv   pre-print
The ActivityNet Large Scale Activity Recognition Challenge 2017 Summary: results and challenge participants papers.  ...  We would like to thank the authors of the Kinetics dataset for their kind support; and Joao Carreira and Brian Zhang for helpful discussions.  ...  The entire model is trained end-to-end with jointly optimized localization and classification losses.  ... 
arXiv:1710.08011v1 fatcat:bc5qhp2cungrdj4j3lebxeoane

Building machines that learn and think like people

Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman
2016 Behavioral and Brain Sciences  
Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans  ...  in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and (3) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge  ...  Acknowledgments We are grateful to Peter Battaglia, Matt Botvinick, Y-Lan Boureau, Anatole Gershman, George Kachergis, George Konidaris, Tejas Kulkarni, Tammy Kwan, Michael Littman, Steven Pinker, and  ... 
doi:10.1017/s0140525x16001837 pmid:27881212 fatcat:3fjriprksbhaxpqdcydrhmcjqm

D2.2 Implementations of methods adapted to enhanced human inputs

Doukhan, Francis, Harrando, Huet, Kaseva, Kurimo, Laaksonen, Lindh-Knuutila, Lisena, Pehlivan Tort, Reboud, Rouhe (+2 others)
2020 Zenodo  
Special attention has been on methods that combine different modalities and bring human knowledge as input to the learning system.  ...  Based on the methods' primary input domain, they have been grouped as visual (facial person recognition, facial gender classification and video description), auditory (speech and gender segmentation, speech  ...  This work was partially funded by ANR (the French National Research Agency) via the ANTRACT project and the European H2020 research and innovation programme via the project MeMAD (GA780069).  ... 
doi:10.5281/zenodo.4964298 fatcat:6bbqa7q3xrctnm6nrf5fxh7f3q

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation.  ...  Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn.  ...  The authors propose policy-space response oracle (PSRO), and its approximation, deep cognitive hierarchies (DCH), to compute best responses to a mixture of policies using deep RL, and to compute new meta-strategy  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

Building Machines That Learn and Think Like People [article]

Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman
2016 arXiv   pre-print
Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some  ...  in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge  ...  Acknowledgments We are grateful to Peter Battaglia, Matt Botvinick, Y-Lan Boureau, Shimon Edelman, Nando de Freitas, Anatole Gershman, George Kachergis, Leslie Kaelbling, Andrej Karpathy, George Konidaris  ... 
arXiv:1604.00289v3 fatcat:ph2rrwk2znb4dpb5nvcg54x2xi

What Makes People Watch Online Videos

Christoph Lagger, Mathias Lux, Oge Marques
2017 Computers in Entertainment  
Our findings can be used to enhance current video retrieval systems, search interfaces, and algorithms, in order to improve the overall user satisfaction and experience.  ...  when they retrieved and watched videos; and an online quantitative survey with more than 200 participants answering comparable questions.  ...  ACKNOWLEDGMENTS The authors would like to thank all participants from the qualitative interviews and the quantitative survey for taking the time to answer our questions.  ... 
doi:10.1145/3034706 fatcat:2zhzscvosbbbvk4zlv2zy6ulke

Computer and Information Science, Vol. 1, No. 2, May 2008, all in one file

Editor CIS
2008 Computer and Information Science  
The authors and evaluators found the slot-approach to be fairly intuitive for the task for expression editing.  ...  as VASDE) for manually disabled programmers for whom the use of a keyboard and/or mouse is problematic.  ...  Additionally, it is useful to incorporate user retention and attrition dynamics to the model. (Pradalier and Sekhavat, 2002) .  ... 
doi:10.5539/cis.v1n2p0 fatcat:plvvknmc2jel3m3tzfz7bs2mdu

Intelligent user interfaces in the living room

Konstantinos Chorianopoulos, George Lekakos, Diomidis Spinellis
2003 Proceedings of the 8th international conference on Intelligent user interfaces - IUI '03  
The ITV application was evaluated by consumers and addressed three contemporary UI issues: video skipping, animated character, and dynamic advertisement insertion.  ...  Overall, the methodology employed a holistic design approach for ITV applications, in which the UI model and the business model were systematically mapped to and validated through an ITV music application  ...  scheme Every ITV application can be described along two dimensions:Temporal personalization via dynamic video synthesis: The local storage can be used to produce dynamic flows of television channels.  ... 
doi:10.1145/604079.604083 fatcat:rnov6mkezreulpibbhbzjpkxh4

Transforming the Preparation of Physics GTAs: Curriculum Development [article]

Emily Alicea-Muñoz, Carol Subiño Sullivan, Michael F. Schatz
2021 arXiv   pre-print
and its applications to many potential career paths.  ...  But GTAs are students themselves, and not all of them desire to pursue an academic career.  ...  ACKNOWLEDGMENTS We would like to thank Ed Greco for valuable discussions and feedback about GTAs and teaching labs; Eric Murray, Martin Jarrio, and Nicholas Darnton for information about the specifics  ... 
arXiv:2109.00168v1 fatcat:uy3diub7tbbn3dmxrckxeg2esq

The Uses of Multimedia: Three Digital Literacy Case Studies

John Hartley, Kelly McWilliam, Jean Burgess, John Banks
2008 Media International Australia: Incorporating Culture & Policy  
requires a procedural (not propositional) model of knowledge, a vernacular and informal model of creativity, and a 'navigator' and entrepreneurial model of consumer agency.  ...  We identify some tensions between formal education and informal learning in the uses of popular literacy since the nineteenth century, in order to argue for a 'demand-led' model of education in digital  ...  Procedural knowledge, however, is the acquisition of an open-ended and user-led approach to knowledge.  ... 
doi:10.1177/1329878x0812800108 fatcat:a6rfwfbrbndtbmyb64lx3o6q3e

The Search as Learning Spaceship: Toward a Comprehensive Model of Psychological and Technological Facets of Search as Learning

Johannes von Hoyer, Anett Hoppe, Yvonne Kammerer, Christian Otto, Georg Pardi, Markus Rokicki, Ran Yu, Stefan Dietze, Ralph Ewerth, Peter Holtz
2022 Frontiers in Psychology  
Exploratory search activities which are carried out in order to gain knowledge are conceptualized and denoted as Search as Learning (SAL).  ...  In this paper, we introduce a novel framework model which incorporates the perspective of both psychology and computer science to describe the search as learning process by reviewing recent literature.  ...  ACKNOWLEDGMENTS The authors would like to thank Daniel Hienert and Gábor Kismihók for fruitful discussions in the context of this work and also thanks to Marie Hornberger, who helped with formatting and  ... 
doi:10.3389/fpsyg.2022.827748 pmid:35369228 pmcid:PMC8964633 fatcat:i5korimbqfaidhsnuz3p5xhzcm
« Previous Showing results 1 — 15 out of 7,411 results