Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Andrew D. Bagdanov

Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents


Apr 21, 2021
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov


  Access Paper or Ask Questions

Robust pedestrian detection in thermal imagery using synthesized images


Feb 03, 2021
My Kieu, Lorenzo Berlincioni, Leonardo Galteri, Marco Bertini, Andrew D. Bagdanov, Alberto Del Bimbo

* Accepted at ICPR2020 

  Access Paper or Ask Questions

Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games


Dec 07, 2020
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov

* Presented at the AAAI-21 Workshop on Reinforcement Learning in Games 

  Access Paper or Ask Questions

Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments


Dec 04, 2020
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov

* Presented at the AAAI-21 Workshop on Reinforcement Learning in Games 

  Access Paper or Ask Questions

DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games


Dec 03, 2020
Alessandro Sestini, Alexander Kuhnle, Andrew D. Bagdanov

* Presented at AIIDE-19 Workshop on Experimental Artificial Intelligence in Games 

  Access Paper or Ask Questions

Class-incremental learning: survey and performance evaluation


Oct 28, 2020
Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, Joost van de Weijer


  Access Paper or Ask Questions

RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning


Jul 13, 2020
Riccardo Del Chiaro, Bartłomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer

* 8 pages, 5 figures, to be published in LifelongML workshop at ICML2020 

  Access Paper or Ask Questions

Generative Feature Replay For Class-Incremental Learning


Apr 20, 2020
Xialei Liu, Chenshen Wu, Mikel Menta, Luis Herranz, Bogdan Raducanu, Andrew D. Bagdanov, Shangling Jui, Joost van de Weijer

* Accepted at CVPR2020: Workshop on Continual Learning in Computer Vision 

  Access Paper or Ask Questions

Visual Question Answering for Cultural Heritage


Mar 22, 2020
Pietro Bongini, Federico Becattini, Andrew D. Bagdanov, Alberto Del Bimbo

* accepted at FlorenceHeritech 2020 

  Access Paper or Ask Questions

Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank


Feb 17, 2019
Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov

* Accepted at TPAMI. (Keywords: Learning from rankings, image quality assessment, crowd counting, active learning). arXiv admin note: text overlap with arXiv:1803.03095 

  Access Paper or Ask Questions

Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images


Sep 04, 2018
Dena Bazazian, Dimosthenis Karatzas, Andrew D. Bagdanov

* 4 pages, 3 figures, The Third International Workshop on Egocentric Perception, Interaction and Computing (EPIC) at ECCV2018 

  Access Paper or Ask Questions

Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting


Jul 12, 2018
Xialei Liu, Marc Masana, Luis Herranz, Joost Van de Weijer, Antonio M. Lopez, Andrew D. Bagdanov

* Accepted at ICPR'18. First two authors contributed equally 

  Access Paper or Ask Questions

Scale Coding Bag of Deep Features for Human Attribute and Action Recognition


Mar 26, 2018
Fahad Shahbaz Khan, Joost van de Weijer, Rao Muhammad Anwer, Andrew D. Bagdanov, Michael Felsberg, Jorma Laaksonen

* To appear in Machine Vision and Applications 

  Access Paper or Ask Questions

Review on Computer Vision Techniques in Emergency Situation


Mar 09, 2018
Laura Lopez-Fuentes, Joost van de Weijer, Manuel Gonzalez-Hidalgo, Harald Skinnemoen, Andrew D. Bagdanov

* Multimedia Tools and Applications, 2017, p. 1-39 
* 25 pages 

  Access Paper or Ask Questions

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank


Mar 08, 2018
Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov

* Accepted by CVPR18 

  Access Paper or Ask Questions

Domain-adaptive deep network compression


Sep 06, 2017
Marc Masana, Joost van de Weijer, Luis Herranz, Andrew D. Bagdanov, Jose M Alvarez

* Accepted at ICCV 2017 

  Access Paper or Ask Questions

RankIQA: Learning from Rankings for No-reference Image Quality Assessment


Jul 26, 2017
Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov

* Accepted by ICCV 2017 

  Access Paper or Ask Questions

Visual attention models for scene text recognition


Jun 05, 2017
Suman K. Ghosh, Ernest Valveny, Andrew D. Bagdanov


  Access Paper or Ask Questions

Improving Text Proposals for Scene Images with Fully Convolutional Networks


Feb 16, 2017
Dena Bazazian, Raul Gomez, Anguelos Nicolaou, Lluis Gomez, Dimosthenis Karatzas, Andrew D. Bagdanov

* 6 pages, 8 figures, International Conference on Pattern Recognition (ICPR) - DLPR (Deep Learning for Pattern Recognition) workshop 

  Access Paper or Ask Questions

Bandwidth limited object recognition in high resolution imagery


Jan 16, 2017
Laura Lopez-Fuentes, Andrew D. Bagdanov, Joost van de Weijer, Harald Skinnemoen

* Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on. IEEE, 2017. p. 1197-1205 
* 9 pages, 9 figures, accepted in WACV 

  Access Paper or Ask Questions

On-the-fly Network Pruning for Object Detection


May 11, 2016
Marc Masana, Joost van de Weijer, Andrew D. Bagdanov

* Accepted at ICLR 2016 workshop track as a poster presentation 

  Access Paper or Ask Questions

Sparse Radial Sampling LBP for Writer Identification


Apr 23, 2015
Anguelos Nicolaou, Andrew D. Bagdanov, Marcus Liwicki, Dimosthenis Karatzas

* Submitted to the 13th International Conference on Document Analysis and Recognition (ICDAR 2015) 

  Access Paper or Ask Questions