UAB Digital Repository of Documents 83 records found  previous11 - 20nextend  jump to record: Search took 0.01 seconds. 
11.
16 p, 3.8 MB Distributed learning and inference with compressed images / Katakol, Sudeep (Birla Institute of Technology and Science. Department of Mathematics) ; Elbarashy, Basem (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Herranz, Luis (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Weijer, Joost van de (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e. [...]
2021 - 10.1109/TIP.2021.3058545
IEEE transactions on image processing, Vol. 30 (Dec. 2021) , p. 3069-3083  
12.
11 p, 2.3 MB Intention recognition of pedestrians and cyclists by 2D pose estimation / Fang, Zhijie (Centre de Visió per Computador (Bellaterra, Catalunya)) ; López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Anticipating the intentions of vulnerable road users (VRUs) such as pedestrians and cyclists is critical for performing safe and comfortable driving maneuvers. This is the case for human driving and, thus, should be taken into account by systems providing any level of driving assistance, from advanced driver assistant systems (ADAS) to fully autonomous vehicles (AVs). [...]
2020 - 10.1109/TITS.2019.2946642
IEEE Transactions on Intelligent Transportation Systems, Vol. 21, issue 11 (Nov. 2020) , p. 4773-4783  
13.
9 p, 611.7 KB Rotate your networks : better weight consolidation and less catastrophic forgetting / Liu, Xialei (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Masana, Marc (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Herranz, Luis (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Weijer, Joost van de (Centre de Visió per Computador (Bellaterra, Catalunya)) ; López Peña, Antonio M. (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Bagdanov, Andrew (Media Integration and Communication Center (Firenze))
In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. [...]
Institute of Electrical and Electronics Engineers (IEEE), cop.2018 - 10.1109/ICPR.2018.8545895
2018 24th International Conference on Pattern Recognition (ICPR), 2018, p. 2262-2268  
14.
17 p, 2.6 MB On offline evaluation of vision-based driving models / Codevilla Moraes, Felipe (Centre de Visió per Computador (Bellaterra, Catalunya)) ; López Peña, Antonio M. (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Koltun, Vladlen (Intel Corporation) ; Dosovitskiy, Alexey (Intel Labs)
Autonomous driving models should ideally be evaluated by deploying them on a fleet of physical vehicles in the real world. Unfortunately, this approach is not practical for the vast majority of researchers. [...]
Cham, Switzerland: Springer, 2018 (Lecture Notes in Computer Science book series (LNCS) ; 11219) - 10.1007/978-3-030-01267-0_15
Computer Vision - ECCV 2018, 2018, p. 246-262  
15.
16 p, 5.6 MB Co-Training for On-Board Deep Object Detection / Villalonga, Gabriel (Centre de Visió per Computador (Bellaterra, Catalunya)) ; López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features and shallow machine learning and, despite its unprecedented performance gains, the problem remains open within the deep learning paradigm due to its data-hungry nature. [...]
2020 - 10.1109/ACCESS.2020.3032024
IEEE Access, Vol. 8 (October 2020) p. 194441-194456  
16.
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  
17.
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  
18.
7 p, 9.7 MB Is the pedestrian going to cross? : answering by 2D pose estimation / Fang, Zhijie (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ; López Peña, Antonio M. (Centre de Visió per Computador (Bellaterra, Catalunya))
Our recent work suggests that, thanks to nowadays powerful CNNs, image-based 2D pose estimation is a promising cue for determining pedestrian intentions such as crossing the road in the path of the ego-vehicle, stopping before entering the road, and starting to walk or bending towards the road. [...]
Institute of Electrical and Electronics Engineers (IEEE), cop.2018 - 10.1109/IVS.2018.8500413
2018 IEEE Intelligent Vehicles Symposium (IV), 2018, p. 1271-1276  
19.
18 p, 4.7 MB Metric learning for novelty and anomaly detection / Masana, Marc (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Ruiz López, Idoia (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Serrat Gual, Joan (Centre de Visió per Computador (Bellaterra, Catalunya)) ; Weijer, Joost van de (Centre de Visió per Computador (Bellaterra, Catalunya)) ; López Peña, Antonio M. (Centre de Visió per Computador (Bellaterra, Catalunya))
When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. [...]
2019
British Machine Vision Conference. Northumbria University (Newcastle), 3-6 Sep. 2018  
20.
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  

UAB Digital Repository of Documents : 83 records found   previous11 - 20nextend  jump to record:
See also: similar author names
23 Lopez, A.
3 Lopez, A.D.
1 Lopez, A.M.
1 Lopez, A.O.
1 Lopez, Aitziber
3 Lopez, Alan D
1 Lopez, Alan D.
1 Lopez, Ana M.
1 Lopez, Anaïs
1 Lopez, Andreu
1 Lopez, Angel
1 Lopez, Anthony
8 Lopez, Antonio
23 López, A.
1 López, A. L.
1 López, A.C.
1 López, A.M.
2 López, Adrià
1 López, Adrián
1 López, Aitziber,
3 López, Alba María
1 López, Alejandro
6 López, Alex
5 López, Alexandre
3 López, Alicia
2 López, Amador
1 López, Amanda Rodríguez
2 López, Amparo
1 López, Ana Felisa
1 López, Ana Luisa
1 López, Ana María
1 López, André
1 López, Andrés
1 López, Andrés P.
4 López, Anna
2 López, Antoni
1 López, Antonia
8 López, Antonio
1 López, Ascensión
1 López, Aurora
6 López, Àlex
6 López, Álex
1 López, Ángel L.
1 López, Ángel Luis
1 López, Ángel Luis,
Interested in being notified about new results for this query?
Set up a personal email alert or subscribe to the RSS feed.