toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author (up) M. Bressan; Jordi Vitria edit  openurl
  Title Improving Naive Bayes using Class Conditional ICA Type Miscellaneous
  Year 2002 Publication F. Garijo, J. Riquelme, M. Toro, (Eds.), Advances in Artificial Intelligece–Iberamia, LNAI 2527: 1–10, Springer Verlag Series. Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address  
  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;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ BrV2002d Serial 278  
Permanent link to this record
 

 
Author (up) M. Bressan; Jordi Vitria edit  openurl
  Title Improving Naive Bayes using Class Condicitonal ICA. Type Miscellaneous
  Year 2002 Publication Iberoamerican Conference on Artificial Intelligence IBERAMIA 2002. Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Sevilla, Espanya  
  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;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ BrV2002e Serial 305  
Permanent link to this record
 

 
Author (up) M. Bressan; Jordi Vitria edit  openurl
  Title Independent Modes of Variation in Point Distribution Models Type Miscellaneous
  Year 2001 Publication In C. Arcelli, L.P. Cordella, G. Sanniti di Baja (Eds.): Visual Form 2001 4tth International Workshop on Visual Visual Form 2001 4tth International Workshop on Visual Form, IWVF4, Proceedings, LNCS 2059, Springer Verlag, 123 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Capri, Italia  
  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;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ BVi2001 Serial 80  
Permanent link to this record
 

 
Author (up) M. Gomez; J. Mauri; E. Fernandez-Nofrerias; Oriol Rodriguez-Leor; Carme Julia; Petia Radeva; David Rotger; V. Valle edit  openurl
  Title Nuevos Avances para la correlacion de imagenes angiograficas y de ecograia intracoronaria. Type Miscellaneous
  Year 2002 Publication Congreso de las Enfermedades Cardiovasculares, XXXVIII Congreso de la Sociedad Española de Cardiologia. Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Madrid, Espanya  
  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 @ GMF2002c Serial 309  
Permanent link to this record
 

 
Author (up) M. Gonzalez-Audicana; Xavier Otazu; O. Fors; R Garcia; J. Nuñez edit  openurl
  Title Fusion of different spatial and spectral resolution images: development, apllication and comparison of new methods based on wavelets. Type Miscellaneous
  Year 2002 Publication Proceedings of the 1st. International Symposium Recent Advances in Quantitative Remote Sensing. Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address  
  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 @ GOF2002 Serial 291  
Permanent link to this record
 

 
Author (up) Maciej Wielgosz; Antonio Lopez; Muhamad Naveed Riaz edit   pdf
url  openurl
  Title CARLA-BSP: a simulated dataset with pedestrians Type Miscellaneous
  Year 2023 Publication Arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract We present a sample dataset featuring pedestrians generated using the ARCANE framework, a new framework for generating datasets in CARLA (0.9.13). We provide use cases for pedestrian detection, autoencoding, pose estimation, and pose lifting. We also showcase baseline results.  
  Address  
  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 ADAS Approved no  
  Call Number Admin @ si @ WLN2023 Serial 3866  
Permanent link to this record
 

 
Author (up) Maedeh Aghaei; Mariella Dimiccoli; Petia Radeva edit  openurl
  Title Multi-Face Tracking by Extended Bag-of-Tracklets in Egocentric Videos Type Miscellaneous
  Year 2015 Publication Arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Egocentric images offer a hands-free way to record daily experiences and special events, where social interactions are of special interest. A natural question that arises is how to extract and track the appearance of multiple persons in a social event captured by a wearable camera. In this paper, we propose a novel method to find correspondences of multiple-faces in low temporal resolution egocentric sequences acquired through a wearable camera. This kind of sequences imposes additional challenges to the multitracking problem with respect to conventional videos. Due to the free motion of the camera and to its low temporal resolution (2 fpm), abrupt changes in the field of view, in illumination conditions and in the target location are very frequent. To overcome such a difficulty, we propose to generate, for each detected face, a set of correspondences along the whole sequence that we call tracklet and to take advantage of their redundancy to deal with both false positive face detections and unreliable tracklets. Similar tracklets are grouped into the so called extended bag-of-tracklets (eBoT), which are aimed to correspond to specific persons. Finally, a prototype tracklet is extracted for each eBoT. We validated our method over a dataset of 18.000 images from 38 egocentric sequences with 52 trackable persons and compared to the state-of-the-art methods, demonstrating its effectiveness and robustness.  
  Address  
  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 Admin @ si @ ADR2015b Serial 2713  
Permanent link to this record
 

 
Author (up) Marçal Rusiñol; Josep Llados edit  openurl
  Title Symbol Spotting in Technical Drawings Using Vectorial Signatures Type Miscellaneous
  Year 2005 Publication 6th IAPR International Workshop on Graphics Recognition (GREC 2005), 35–45 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong  
  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 DAG Approved no  
  Call Number DAG @ dag @ RuL2005 Serial 579  
Permanent link to this record
 

 
Author (up) Marcin Przewiezlikowski; Mateusz Pyla; Bartosz Zielinski; Bartłomiej Twardowski; Jacek Tabor; Marek Smieja edit   pdf
url  openurl
  Title Augmentation-aware Self-supervised Learning with Guided Projector Type Miscellaneous
  Year 2023 Publication arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Self-supervised learning (SSL) is a powerful technique for learning robust representations from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with supervised approaches. However, this invariance may be harmful to solving some downstream tasks which depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. In order for the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks.  
  Address  
  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 LAMP Approved no  
  Call Number Admin @ si @ PPZ2023 Serial 3971  
Permanent link to this record
 

 
Author (up) Marco Cotogni; Fei Yang; Claudio Cusano; Andrew Bagdanov; Joost Van de Weijer edit   pdf
url  openurl
  Title Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation Type Miscellaneous
  Year 2023 Publication ARXIV Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of previously learned tasks. This is often achieved via exemplar replay which can help recalibrate previous task classifiers to the feature drift which occurs when learning new tasks. Exemplar replay, however, comes at the cost of retaining samples from previous tasks which for many applications may not be possible. To address the problem of continual ViT training, we first propose gated class-attention to minimize the drift in the final ViT transformer block. This mask-based gating is applied to class-attention mechanism of the last transformer block and strongly regulates the weights crucial for previous tasks. Importantly, gated class-attention does not require the task-ID during inference, which distinguishes it from other parameter isolation methods. Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks. The combination of gated class-attention and cascaded feature drift compensation allows for plasticity towards new tasks while limiting forgetting of previous ones. Extensive experiments performed on CIFAR-100, Tiny-ImageNet and ImageNet100 demonstrate that our exemplar-free method obtains competitive results when compared to rehearsal based ViT methods.  
  Address  
  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 LAMP Approved no  
  Call Number Admin @ si @ CYC2023 Serial 3981  
Permanent link to this record
 

 
Author (up) Marco Cotogni; Fei Yang; Claudio Cusano; Andrew Bagdanov; Joost Van de Weijer edit   pdf
openurl 
  Title Gated Class-Attention with Cascaded Feature Drift Compensation for Exemplar-free Continual Learning of Vision Transformers Type Miscellaneous
  Year 2022 Publication Arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov, Joost van de Weijer  
  Abstract We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of previously learned tasks. This is often achieved via exemplar replay which can help recalibrate previous task classifiers to the feature drift which occurs when learning new tasks. Exemplar replay, however, comes at the cost of retaining samples from previous tasks which for many applications may not be possible. To address the problem of continual ViT training, we first propose gated class-attention to minimize the drift in the final ViT transformer block. This mask-based gating is applied to class-attention mechanism of the last transformer block and strongly regulates the weights crucial for previous tasks. Importantly, gated class-attention does not require the task-ID during inference, which distinguishes it from other parameter isolation methods. Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks. The combination of gated class-attention and cascaded feature drift compensation allows for plasticity towards new tasks while limiting forgetting of previous ones. Extensive experiments performed on CIFAR-100, Tiny-ImageNet and ImageNet100 demonstrate that our exemplar-free method obtains competitive results when compared to rehearsal based ViT methods.  
  Address  
  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 LAMP; no proj Approved no  
  Call Number Admin @ si @ CYC2022 Serial 3827  
Permanent link to this record
 

 
Author (up) Marco Pedersoli edit  openurl
  Title A Multiresolution Cascade for Human Detection Type Miscellaneous
  Year 2008 Publication CVC Technical Report #126 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Barcelona, Spain  
  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 ISE Approved no  
  Call Number Admin @ si @ Ped2008 Serial 1148  
Permanent link to this record
 

 
Author (up) Maria Vanrell; Felipe Lumbreras; A. Pujol; Ramon Baldrich; Josep Llados; Juan J. Villanueva edit  openurl
  Title Colour Normalisation Based on Background Information. Type Miscellaneous
  Year 2001 Publication Proceeding ICIP 2001, IEEE International Conference on Image Processing Abbreviated Journal ICIP 2001  
  Volume Issue 1 Pages 874–877  
  Keywords  
  Abstract  
  Address Grecia.  
  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 ADAS;DAG;CIC Approved no  
  Call Number ADAS @ adas @ VLP2001 Serial 167  
Permanent link to this record
 

 
Author (up) Maria Vanrell; Jordi Vitria edit  openurl
  Title Mathematical Morphology, Granulometries and Texture Perception. Type Miscellaneous
  Year 1993 Publication SPIE International Symposium on Optical Instrumentation and Applied Science (Conference on image Algebra and Morphological image Processing IV). Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address San Diego; CA; USA  
  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;CIC;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ VaV1993 Serial 178  
Permanent link to this record
 

 
Author (up) Maria Vanrell; Jordi Vitria; Xavier Roca edit  openurl
  Title A General Morphological Framework for Perceptual Texture Discrimination based on Granulometries. Type Miscellaneous
  Year 1993 Publication Technical Workshop on Mathematical Morphology and its Applications to Signal Processing. Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Barcelona  
  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;ISE;CIC;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ VVR1993 Serial 154  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: