thesis published Viktoriia Sharmanska author 2EA6D09E-F248-11E8-B48F-1D18A9856A870000-0003-0192-9308 Christoph Lampert supervisor ChLa department GradSch department The human ability to recognize objects in complex scenes has driven research in the computer vision field over couple of decades. This thesis focuses on the object recognition task in images. That is, given the image, we want the computer system to be able to predict the class of the object that appears in the image. A recent successful attempt to bridge semantic understanding of the image perceived by humans and by computers uses attribute-based models. Attributes are semantic properties of the objects shared across different categories, which humans and computers can decide on. To explore the attribute-based models we take a statistical machine learning approach, and address two key learning challenges in view of object recognition task: learning augmented attributes as mid-level discriminative feature representation, and learning with attributes as privileged information. Our main contributions are parametric and non-parametric models and algorithms to solve these frameworks. In the parametric approach, we explore an autoencoder model combined with the large margin nearest neighbor principle for mid-level feature learning, and linear support vector machines for learning with privileged information. In the non-parametric approach, we propose a supervised Indian Buffet Process for automatic augmentation of semantic attributes, and explore the Gaussian Processes classification framework for learning with privileged information. A thorough experimental analysis shows the effectiveness of the proposed models in both parametric and non-parametric views. https://research-explorer.ista.ac.at/download/1401/9177/2015_Thesis_Sharmanska.pdf application/pdfno https://research-explorer.ista.ac.at/download/1401/10297/2015_Thesis_Sharmanska_pdfa.pdf application/pdf Institute of Science and Technology Austria2015 eng 2663-337X10.15479/at:ista:1401 144 Sharmanska, Viktoriia. <i>Learning with Attributes for Object Recognition: Parametric and Non-Parametrics Views</i>. Institute of Science and Technology Austria, 2015, doi:<a href="https://doi.org/10.15479/at:ista:1401">10.15479/at:ista:1401</a>. Sharmanska, V. (2015). <i>Learning with attributes for object recognition: Parametric and non-parametrics views</i>. Institute of Science and Technology Austria. <a href="https://doi.org/10.15479/at:ista:1401">https://doi.org/10.15479/at:ista:1401</a> V. Sharmanska, Learning with Attributes for Object Recognition: Parametric and Non-Parametrics Views, Institute of Science and Technology Austria, 2015. Sharmanska V. Learning with attributes for object recognition: Parametric and non-parametrics views. 2015. doi:<a href="https://doi.org/10.15479/at:ista:1401">10.15479/at:ista:1401</a> Sharmanska, Viktoriia. “Learning with Attributes for Object Recognition: Parametric and Non-Parametrics Views.” Institute of Science and Technology Austria, 2015. <a href="https://doi.org/10.15479/at:ista:1401">https://doi.org/10.15479/at:ista:1401</a>. Sharmanska V. 2015. Learning with attributes for object recognition: Parametric and non-parametrics views. Institute of Science and Technology Austria. V. Sharmanska, “Learning with attributes for object recognition: Parametric and non-parametrics views,” Institute of Science and Technology Austria, 2015. 14012018-12-11T11:51:48Z2026-04-09T14:25:49Z