Maria del Camp Davesa. (2011). Human action categorization in image sequences (Vol. 169). Master's thesis, , .
|
Albert Gordo. (2009). A Cyclic Page Layout Descriptor for Document Classification & Retrieval (Vol. 128). Master's thesis, , Bellaterra, Barcelona.
|
David Augusto Rojas. (2009). Colouring Local Feature Detection for Matching (Vol. 133). Master's thesis, , Bellaterra, Barcelona.
|
Olivier Penacchio. (2009). Relative Density of L, M, S photoreceptors in the Human Retina (Vol. 135). Master's thesis, , Bellaterra, Barcelona.
|
Xavier Boix. (2009). Learning Conditional Random Fields for Stereo (Vol. 136). Master's thesis, , Bellaterra, Barcelona.
|
Shida Beigpour. (2009). Physics-based Reflectance Estimation Applied to Recoloring (Vol. 137). Master's thesis, , Bellaterra, Barcelona.
|
Jose Carlos Rubio. (2009). Graph matching based on graphical models with application to vehicle tracking and classification at night (Vol. 144). Master's thesis, , Bellaterra, Barcelona.
|
Ivet Rafegas. (2013). Exploring Low-Level Vision Models. Case Study: Saliency Prediction (Vol. 175). Master's thesis, , .
|
Ricard Balague. (2014). Exploring the combination of color cues for intrinsic image decomposition (Vol. 178). Master's thesis, , .
Abstract: Intrinsic image decomposition is a challenging problem that consists in separating an image into its physical characteristics: reflectance and shading. This problem can be solved in different ways, but most methods have combined information from several visual cues. In this work we describe an extension of an existing method proposed by Serra et al. which considers two color descriptors and combines them by means of a Markov Random Field. We analyze in depth the weak points of the method and we explore more possibilities to use in both descriptors. The proposed extension depends on the combination of the cues considered to overcome some of the limitations of the original method. Our approach is tested on the MIT dataset and Beigpour et al. dataset, which contain images of real objects acquired under controlled conditions and synthetic images respectively, with their corresponding ground truth.
|
Javier Vazquez. (2007). Content-based Colour Space.
|
Maria Vanrell. (1997). Exploring the space of behaviour of a texture perception algorithm.
|
A. Martinez, & Robert Benavente. (1998). The AR face database.
|
Robert Benavente. (1999). Dealing with colour variability: application to a colour naming task.
|
Jordi Vitria, Petia Radeva, X. Binefa, A. Pujol, Ernest Valveny, Robert Benavente, et al. (1999). Real time recognition of pharmaceutical products by subspace methods.
|
Robert Benavente, & Maria Vanrell. (2001). A colour naming experiment.
|
Anna Salvatella, & Maria Vanrell. (2002). Towards a texture representation database.
|
Bojana Gajic, & Ramon Baldrich. (2018). Cross-domain fashion image retrieval. In CVPR 2018 Workshop on Women in Computer Vision (WiCV 2018, 4th Edition) (pp. 19500–19502).
Abstract: Cross domain image retrieval is a challenging task that implies matching images from one domain to their pairs from another domain. In this paper we focus on fashion image retrieval, which involves matching an image of a fashion item taken by users, to the images of the same item taken in controlled condition, usually by professional photographer. When facing this problem, we have different products
in train and test time, and we use triplet loss to train the network. We stress the importance of proper training of simple architecture, as well as adapting general models to the specific task.
|
Bojana Gajic, Ariel Amato, Ramon Baldrich, Joost Van de Weijer, & Carlo Gatta. (2022). Area Under the ROC Curve Maximization for Metric Learning. In CVPR 2022 Workshop on Efficien Deep Learning for Computer Vision (ECV 2022, 5th Edition).
Abstract: Most popular metric learning losses have no direct relation with the evaluation metrics that are subsequently applied to evaluate their performance. We hypothesize that training a metric learning model by maximizing the area under the ROC curve (which is a typical performance measure of recognition systems) can induce an implicit ranking suitable for retrieval problems. This hypothesis is supported by previous work that proved that a curve dominates in ROC space if and only if it dominates in Precision-Recall space. To test this hypothesis, we design and maximize an approximated, derivable relaxation of the area under the ROC curve. The proposed AUC loss achieves state-of-the-art results on two large scale retrieval benchmark datasets (Stanford Online Products and DeepFashion In-Shop). Moreover, the AUC loss achieves comparable performance to more complex, domain specific, state-of-the-art methods for vehicle re-identification.
Keywords: Training; Computer vision; Conferences; Area measurement; Benchmark testing; Pattern recognition
|