toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author Angel Sappa; Patricia Suarez; Henry Velesaca; Dario Carpio edit   pdf
url  openurl
  Title Domain Adaptation in Image Dehazing: Exploring the Usage of Images from Virtual Scenarios Type Conference Article
  Year 2022 Publication 16th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing Abbreviated Journal  
  Volume Issue Pages 85-92  
  Keywords Domain adaptation; Synthetic hazed dataset; Dehazing  
  Abstract This work presents a novel domain adaptation strategy for deep learning-based approaches to solve the image dehazing
problem. Firstly, a large set of synthetic images is generated by using a realistic 3D graphic simulator; these synthetic
images contain different densities of haze, which are used for training the model that is later adapted to any real scenario.
The adaptation process requires just a few images to fine-tune the model parameters. The proposed strategy allows
overcoming the limitation of training a given model with few images. In other words, the proposed strategy implements
the adaptation of a haze removal model trained with synthetic images to real scenarios. It should be noticed that it is quite
difficult, if not impossible, to have large sets of pairs of real-world images (with and without haze) to train in a supervised
way dehazing algorithms. Experimental results are provided showing the validity of the proposed domain adaptation
strategy.
 
  Address (up) Lisboa; Portugal; July 2022  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CGVCVIP  
  Notes MSIAU; no proj Approved no  
  Call Number Admin @ si @ SSV2022 Serial 3804  
Permanent link to this record
 

 
Author Miguel Oliveira; Victor Santos; Angel Sappa; P. Dias edit   pdf
doi  openurl
  Title Scene Representations for Autonomous Driving: an approach based on polygonal primitives Type Conference Article
  Year 2015 Publication 2nd Iberian Robotics Conference ROBOT2015 Abbreviated Journal  
  Volume 417 Issue Pages 503-515  
  Keywords Scene reconstruction; Point cloud; Autonomous vehicles  
  Abstract In this paper, we present a novel methodology to compute a 3D scene
representation. The algorithm uses macro scale polygonal primitives to model the scene. This means that the representation of the scene is given as a list of large scale polygons that describe the geometric structure of the environment. Results show that the approach is capable of producing accurate descriptions of the scene. In addition, the algorithm is very efficient when compared to other techniques.
 
  Address (up) Lisboa; Portugal; November 2015  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ROBOT  
  Notes ADAS; 600.076; 600.086 Approved no  
  Call Number Admin @ si @ OSS2015a Serial 2662  
Permanent link to this record
 

 
Author J.Poujol; Cristhian A. Aguilera-Carrasco; E.Danos; Boris X. Vintimilla; Ricardo Toledo; Angel Sappa edit   pdf
url  doi
isbn  openurl
  Title Visible-Thermal Fusion based Monocular Visual Odometry Type Conference Article
  Year 2015 Publication 2nd Iberian Robotics Conference ROBOT2015 Abbreviated Journal  
  Volume 417 Issue Pages 517-528  
  Keywords Monocular Visual Odometry; LWIR-RGB cross-spectral Imaging; Image Fusion.  
  Abstract The manuscript evaluates the performance of a monocular visual odometry approach when images from different spectra are considered, both independently and fused. The objective behind this evaluation is to analyze if classical approaches can be improved when the given images, which are from different spectra, are fused and represented in new domains. The images in these new domains should have some of the following properties: i) more robust to noisy data; ii) less sensitive to changes (e.g., lighting); iii) more rich in descriptive information, among other. In particular in the current work two different image fusion strategies are considered. Firstly, images from the visible and thermal spectrum are fused using a Discrete Wavelet Transform (DWT) approach. Secondly, a monochrome threshold strategy is considered. The obtained
representations are evaluated under a visual odometry framework, highlighting
their advantages and disadvantages, using different urban and semi-urban scenarios. Comparisons with both monocular-visible spectrum and monocular-infrared spectrum, are also provided showing the validity of the proposed approach.
 
  Address (up) Lisboa; Portugal; November 2015  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2194-5357 ISBN 978-3-319-27145-3 Medium  
  Area Expedition Conference ROBOT  
  Notes ADAS; 600.076; 600.086 Approved no  
  Call Number Admin @ si @ PAD2015 Serial 2663  
Permanent link to this record
 

 
Author Carlos David Martinez Hinarejos; Josep Llados; Alicia Fornes; Francisco Casacuberta; Lluis de Las Heras; Joan Mas; Moises Pastor; Oriol Ramos Terrades; Joan Andreu Sanchez; Enrique Vidal; Fernando Vilariño edit   pdf
openurl 
  Title Context, multimodality, and user collaboration in handwritten text processing: the CoMUN-HaT project Type Conference Article
  Year 2016 Publication 3rd IberSPEECH Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Processing of handwritten documents is a task that is of wide interest for many
purposes, such as those related to preserve cultural heritage. Handwritten text recognition techniques have been successfully applied during the last decade to obtain transcriptions of handwritten documents, and keyword spotting techniques have been applied for searching specific terms in image collections of handwritten documents. However, results on transcription and indexing are far from perfect. In this framework, the use of new data sources arises as a new paradigm that will allow for a better transcription and indexing of handwritten documents. Three main different data sources could be considered: context of the document (style, writer, historical time, topics,. . . ), multimodal data (representations of the document in a different modality, such as the speech signal of the dictation of the text), and user feedback (corrections, amendments,. . . ). The CoMUN-HaT project aims at the integration of these different data sources into the transcription and indexing task for handwritten documents: the use of context derived from the analysis of the documents, how multimodality can aid the recognition process to obtain more accurate transcriptions (including transcription in a modern version of the language), and integration into a userin-the-loop assisted text transcription framework. This will be reflected in the construction of a transcription and indexing platform that can be used by both professional and nonprofessional users, contributing to crowd-sourcing activities to preserve cultural heritage and to obtain an accessible version of the involved corpus.
 
  Address (up) Lisboa; Portugal; November 2016  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference IberSPEECH  
  Notes DAG; MV; 600.097;SIAI Approved no  
  Call Number Admin @ si @MLF2016 Serial 2813  
Permanent link to this record
 

 
Author Javier Rodenas; Bhalaji Nagarajan; Marc Bolaños; Petia Radeva edit  url
openurl 
  Title Learning Multi-Subset of Classes for Fine-Grained Food Recognition Type Conference Article
  Year 2022 Publication 7th International Workshop on Multimedia Assisted Dietary Management Abbreviated Journal  
  Volume Issue Pages 17–26  
  Keywords  
  Abstract Food image recognition is a complex computer vision task, because of the large number of fine-grained food classes. Fine-grained recognition tasks focus on learning subtle discriminative details to distinguish similar classes. In this paper, we introduce a new method to improve the classification of classes that are more difficult to discriminate based on Multi-Subsets learning. Using a pre-trained network, we organize classes in multiple subsets using a clustering technique. Later, we embed these subsets in a multi-head model structure. This structure has three distinguishable parts. First, we use several shared blocks to learn the generalized representation of the data. Second, we use multiple specialized blocks focusing on specific subsets that are difficult to distinguish. Lastly, we use a fully connected layer to weight the different subsets in an end-to-end manner by combining the neuron outputs. We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets. Our method was successful in learning the confused classes better and we outperformed the state-of-the-art on the three datasets.  
  Address (up) Lisboa; Portugal; October 2022  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference MADiMa  
  Notes MILAB Approved no  
  Call Number Admin @ si @ RNB2022 Serial 3797  
Permanent link to this record
 

 
Author Silvio Giancola; Anthony Cioppa; Adrien Deliege; Floriane Magera; Vladimir Somers; Le Kang; Xin Zhou; Olivier Barnich; Christophe De Vleeschouwer; Alexandre Alahi; Bernard Ghanem; Marc Van Droogenbroeck; Abdulrahman Darwish; Adrien Maglo; Albert Clapes; Andreas Luyts; Andrei Boiarov; Artur Xarles; Astrid Orcesi; Avijit Shah; Baoyu Fan; Bharath Comandur; Chen Chen; Chen Zhang; Chen Zhao; Chengzhi Lin; Cheuk-Yiu Chan; Chun Chuen Hui; Dengjie Li; Fan Yang; Fan Liang; Fang Da; Feng Yan; Fufu Yu; Guanshuo Wang; H. Anthony Chan; He Zhu; Hongwei Kan; Jiaming Chu; Jianming Hu; Jianyang Gu; Jin Chen; Joao V. B. Soares; Jonas Theiner; Jorge De Corte; Jose Henrique Brito; Jun Zhang; Junjie Li; Junwei Liang; Leqi Shen; Lin Ma; Lingchi Chen; Miguel Santos Marques; Mike Azatov; Nikita Kasatkin; Ning Wang; Qiong Jia; Quoc Cuong Pham; Ralph Ewerth; Ran Song; Rengang Li; Rikke Gade; Ruben Debien; Runze Zhang; Sangrok Lee; Sergio Escalera; Shan Jiang; Shigeyuki Odashima; Shimin Chen; Shoichi Masui; Shouhong Ding; Sin-wai Chan; Siyu Chen; Tallal El-Shabrawy; Tao He; Thomas B. Moeslund; Wan-Chi Siu; Wei Zhang; Wei Li; Xiangwei Wang; Xiao Tan; Xiaochuan Li; Xiaolin Wei; Xiaoqing Ye; Xing Liu; Xinying Wang; Yandong Guo; Yaqian Zhao; Yi Yu; Yingying Li; Yue He; Yujie Zhong; Zhenhua Guo; Zhiheng Li edit  url
doi  openurl
  Title SoccerNet 2022 Challenges Results Type Conference Article
  Year 2022 Publication 5th International ACM Workshop on Multimedia Content Analysis in Sports Abbreviated Journal  
  Volume Issue Pages 75-86  
  Keywords  
  Abstract The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team. In 2022, the challenges were composed of 6 vision-based tasks: (1) action spotting, focusing on retrieving action timestamps in long untrimmed videos, (2) replay grounding, focusing on retrieving the live moment of an action shown in a replay, (3) pitch localization, focusing on detecting line and goal part elements, (4) camera calibration, dedicated to retrieving the intrinsic and extrinsic camera parameters, (5) player re-identification, focusing on retrieving the same players across multiple views, and (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams. Compared to last year's challenges, tasks (1-2) had their evaluation metrics redefined to consider tighter temporal accuracies, and tasks (3-6) were novel, including their underlying data and annotations. More information on the tasks, challenges and leaderboards are available on this https URL. Baselines and development kits are available on this https URL.  
  Address (up) Lisboa; Portugal; October 2022  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ACMW  
  Notes HUPBA; no menciona Approved no  
  Call Number Admin @ si @ GCD2022 Serial 3801  
Permanent link to this record
 

 
Author V. Valev; Petia Radeva edit  openurl
  Title ECG Recognition by Non-Reducible Descriptors. Type Miscellaneous
  Year 1995 Publication Portuguese Conference on Pattern Recognition. Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Lisbon, Portugal  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes MILAB Approved no  
  Call Number BCNPCL @ bcnpcl @ VaR1995a Serial 139  
Permanent link to this record
 

 
Author Zhong Jin; Franck Davoine; Zhen Lou edit  openurl
  Title An Effective EM Algorithm for PCA Mixture Model Type Miscellaneous
  Year 2004 Publication Structural and Statistical Pattern Recognition, Lecture Notes in Computer Science, 3138:626–634 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Lisbon, Portugal  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number Admin @ si @ JDL2004 Serial 482  
Permanent link to this record
 

 
Author Olivier Penacchio; Xavier Otazu; A. wilkins; J. Harris edit  url
openurl 
  Title Uncomfortable images prevent lateral interactions in the cortex from providing a sparse code Type Conference Article
  Year 2015 Publication European Conference on Visual Perception ECVP2015 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Liverpool; uk; August 2015  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ECVP  
  Notes NEUROBIT; Approved no  
  Call Number Admin @ si @ POW2015 Serial 2633  
Permanent link to this record
 

 
Author Arash Akbarinia; C. Alejandro Parraga edit   pdf
url  openurl
  Title Biologically Plausible Colour Naming Model Type Conference Article
  Year 2015 Publication European Conference on Visual Perception ECVP2015 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Poster  
  Address (up) Liverpool; UK; August 2015  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ECVP  
  Notes NEUROBIT; 600.068 Approved no  
  Call Number Admin @ si @ AkP2015 Serial 2660  
Permanent link to this record
 

 
Author Jordi Vitria; Petia Radeva; X. Binefa edit  openurl
  Title EigenHistograms: using low dimensional models of color distribution for real time object recognition Type Journal Article
  Year 1999 Publication Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Ljubliana, Slovenia, Springer-Verlag  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes OR;MILAB;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ VRB1999a Serial 29  
Permanent link to this record
 

 
Author Juan Andrade; F. Thomas edit  openurl
  Title Wire-Based Tracking using Mutual Information Type Miscellaneous
  Year 2006 Publication 10th International Symposium on Advances in Robot Kinematics, 3–14 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Ljubljana (Slovenia)  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number Admin @ si @ AnT2006 Serial 665  
Permanent link to this record
 

 
Author A. Martinez; Jordi Vitria edit  openurl
  Title Using Low-Dimensional Spaces for Face Recognition. Type Miscellaneous
  Year 1997 Publication Jornades d'Intel.ligència Artificial: Noves Tendències (JIA'97) Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Lleida  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DOC;OR;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ MaV1997a Serial 52  
Permanent link to this record
 

 
Author J.R. Serra; A. Martinez; Jordi Vitria; J.B. Subirana edit  openurl
  Title Iconic Representation to Image Retrieval. Type Miscellaneous
  Year 1997 Publication Jornades d'Intel.ligència Artificial: Noves Tendències (JIA'97) Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Lleida  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DOC;OR;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ SMV1997 Serial 55  
Permanent link to this record
 

 
Author O. Fors; Xavier Otazu; J. Nuñez edit  openurl
  Title Fusion Mediante Wavelets de Imagenes Spot-pan y del Satelite Tailandes TMSAT. Type Miscellaneous
  Year 2001 Publication Teledeteccion, Medio Ambiente y Cambio Global, IX Congreso Nacional de Teledeteccion, 546–550. Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address (up) Lleida  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes CIC Approved no  
  Call Number CAT @ cat @ FON2001 Serial 94  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: