Depósito Digital de Documentos de la UAB Encontrados 283 registros  anterior11 - 20siguientefinal  ir al registro: La búsqueda tardó 0.01 segundos. 
11.
10 p, 1.5 MB Active learning for deep detection neural networks / Aghdam, Hamed H. (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Gonzalez Garcia, Abel (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Weijer, Joost van de (Centre de Visió per Computador (Bellaterra, Catalunya)) ; López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
The cost of drawing object bounding boxes (i. e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. [...]
Institute of Electrical and Electronics Engineers (IEEE), cop.2019 - 10.1109/ICCV.2019.00377
2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, p. 3671-3679  
12.
7 p, 661.6 KB Training a binary weight object detector by knowledge transfer for autonomous driving / Xu, Jiaolong (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Nie, Yiming (Unmanned Systems Research Center (Beining, Xina)) ; Wang, Peng (Unmanned Systems Research Center (Beining, Xina)) ; López Peña, Antonio M. (Centre de Visió per Computador (Bellaterra, Catalunya))
Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have achieved state-of-the-art accuracy. [...]
Institute of Electrical and Electronics Engineers (IEEE), cop. 2019 - 10.1109/ICRA.2019.8793743
2019 International Conference on Robotics and Automation (ICRA), 2019, p. 2379-2384  
13.
11 p, 1.5 MB Exploring the limitations of behavior cloning for autonomous driving / Codevilla Moraes, Felipe (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Santana, Eder (Toyota Research Institute) ; López Peña, Antonio M. (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Gaidon, Adrien (Toyota Research Institute)
Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. [...]
Institute of Electrical and Electronics Engineers (IEEE), cop.2019 - 10.1109/ICCV.2019.00942
2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, p. 9328-9337  
14.
9 p, 5.3 MB End-to-end driving via conditional imitation learning / Codevilla Moraes, Felipe (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Miiller, Matthias (King Abdullah University of Science and Technology) ; López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; Koltun, Vladlen (Intel Labs) ; Dosovitskiy, Alexey (Intel Labs)
Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. [...]
Institute of Electrical and Electronics Engineers (IEEE), cop.2018 - 10.1109/ICRA.2018.8460487
2018 IEEE International Conference on Robotics and Automation (ICRA), 2018, p. 4693-4700  
15.
21 p, 354.7 KB Teaching law to laymen : The case of the subject "Law & Culture" in Humanities Studies : Strategies Towards Collaborative Learning / Padrós, Carlos (Universitat Autònoma de Barcelona. Departament de Dret Públic i de Ciències Historicojurídiques)
One of the major challenges for the teaching process is to give a course of a given discipline away from the boundaries of your own Faculty. This is the case with teaching Law to Laymen. In 2000 UAB created new studies in Humanities, gathering knowledge of several disciplines (art, litereature, economics, antropology and law) with the goal of educating cultural managers. [...]
2013
Proceedings of the IV UNIVEST International Conference, 2013  
16.
10 p, 409.6 KB On embedding properties of some extrapolation spaces / Martín i Pedret, Joaquim (Universitat de Barcelona. Departament de Matemàtica Aplicada i Anàlisi) ; Carro, María J. (Universitat de Barcelona. Departament de Matemàtica Aplicada i Anàlisi)
Given a sublinear operator T satisfying that ‖Tf‖Lp(ν) ≤ Cp−1‖f‖Lp(μ), for every 1 < p ≤ p0, with C independent of f and p, it has been recently proved that T : LlogL → M(φ), where M(φ) is the maximal Lorentz space with φ(t) = t(1 + log + t)−1. [...]
New York : De Gruyter, 2002 (De Gruyter Proceedings in Mathematics) - 10.1515/9783110198058.241
Function spaces, interpolation theory and related topics: Proceedings of the International Conference in honour of Jaak Peetre on his 65th birthday, 2002, p. 241-248  
17.
11 p, 1.8 MB Assess citizen science based land cover maps with remote sensing products : the Ground Truth 2.0 data quality tool / Maso, Joan (Centre de Recerca Ecològica i d'Aplicacions Forestals) ; Julià, Núria (Centre de Recerca Ecològica i d'Aplicacions Forestals) ; Zabala Torres, Alaitz (Universitat Autònoma de Barcelona. Departament de Geografia) ; Prat Carrió, Ester (Centre de Recerca Ecològica i d'Aplicacions Forestals) ; Van der Kwast, Johannes (IHE Delft Institute for Water Education, Department of Water Resources and Ecosystems) ; Domingo-Marimon, Cristina (Centre de Recerca Ecològica i d'Aplicacions Forestals)
One of the main concerns in adopting citizen science is data quality. Derived products inherit intrinsic limitations of the capture methodology as well as the uncertainties in observations. OpenStreetMap tools are designed to minimize uncertainties in positional accuracy by ensuring a good co-registration of the observations with imagery or direct use of GPS. [...]
2020 - 10.1117/12.2570814
Eighth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2020), Vol. 11524 (2020) , p. 586-595  
18.
20 p, 337.6 KB How easy are audio descriptions? Take 2 / Matamala, Anna (Universitat Autònoma de Barcelona) ; Arias-Badia, Blanca (Universitat Pompeu Fabra)
Easy-to-understand language has traditionally been used for written content, but there has been a recent interest in applying this concept to audiovisual content and access services. In this regard, the EASIT project addressed whether the hybridisation of easy-to-understand language with audio description could produce a new access service, following the path initiated by Pilar Orero and Rocío Bernabé-Caro. [...]
2022
Languages & the Media 2022. 14th International Conference and Exhibition on Language Transfer in Audiovisual Media. Berlín, Alemanya, 14è : 2022  
19.
36 p, 2.8 MB Media Accessibility. Current Solutions and Future Challenges / Orero, Pilar (Universitat Autònoma de Barcelona)
2022 (GreenSCENT)
MediaFutures International Conference. Bergen, : 2022  
20.
23 p, 7.0 MB Towards a Circular Economy in Audiovisual Translation : Green Media for All / Orero, Pilar (Universitat Autònoma de Barcelona)
2022 (GreenSCENT)
International Conference "Il traduttore visibile". Parma, : 2022  

Depósito Digital de Documentos de la UAB : Encontrados 283 registros   anterior11 - 20siguientefinal  ir al registro:
¿Le interesa recibir alertas sobre nuevos resultados de esta búsqueda?
Defina una alerta personal vía correo electrónico o subscríbase al canal RSS.