Browsing by Author "Soto, A."
Now showing 1 - 12 of 12
Results Per Page
Sort Options
- ItemAction Recognition in Video Using Sparse Coding and Relative Features(2016) Alfaro, A.; Mery Quiroz, Domingo Arturo; Soto, A.
- ItemAutomatic selection and detection of visual landmarks using multiple segmentations(2006) Langdon, D.; Soto, A.; Mery Quiroz, Domingo Arturo
- ItemComparing neural and attractiveness-based visual features for artwork recommendation(2017) Dominguez, V.; Messina, P.; Parra, D.; Mery Quiroz, Domingo Arturo; Trattner, C.; Soto, A.
- ItemExploring content-based artwork recommendation with metadata and visual features(2017) Messina, P.; Dominguez, V.; Parra Santander, Denis Alejandro; Trattner, C.; Soto, A.
- ItemHuman action recognition from interoral dictionaries of key-sequences(2014) Alfaro, A.; Mery Quiroz, Domingo Arturo; Soto, A.
- ItemPT symmetric fermionic field theories with axions: Renormalization and dynamical mass generation(2022) Mavromatos, N. E.; Sarkar, Sarben; Soto, A.We consider the renormalization properties of non-Hermitian Yukawa theories involving a pseudoscalar (axion) field at or near four dimensions. The non-Hermiticity is PT symmetric where P is a linear operator (such as parity) and T is an antilinear idempotent operator (such as time reversal). The coupling constants of the Yukawa and quartic scalar coupling terms reflect this non-Hermiticity. The path integral representing the field theory is used to discuss the Feynman rules associated with the field theory. The fixed point structure associated with the renormalization group has PT symmetric and Hermitian fixed points. At two loops in the massless theory, we demonstrate the flow from Hermitian to non-Hermitian fixed points. From the one-loop renormalization of a massive Yukawa theory, a self-consistent Nambu-Jona-Lasinio gap equation is established and its real solutions are discussed.
- ItemIndoor scene recognition through object detection(IEEE, 2010) Espinace Ronda, Pablo Andrés; Kollar, T.; Soto, A.; Roy, N.Scene recognition is a highly valuable perceptual ability for an indoor mobile robot, however, current approaches for scene recognition present a significant drop in performance for the case of indoor scenes. We believe that this can be explained by the high appearance variability of indoor environments. This stresses the need to include high-level semantic information in the recognition process. In this work we propose a new approach for indoor scene recognition based on a generative probabilistic hierarchical model that uses common objects as an intermediate semantic representation. Under this model, we use object classifiers to associate low-level visual features to objects, and at the same time, we use contextual relations to associate objects to scenes. As a further contribution, we improve the performance of current state-of-the-art category-level object classifiers by including geometrical information obtained from a 3D range sensor that facilitates the implementation of a focus of attention mechanism within a Monte Carlo sampling scheme. We test our approach using real data, showing significant advantages with respect to previous state-of-the-art methods.
- ItemInduced Maxwell-Chern-Simons effective action in very special relativity(2020) Bufalo, R.; Ghasemkhani, M.; Haghgouyan, Z.; Soto, A.In this paper, we study the one-loop induced photon's effective action in the very special relativity electrodynamics in (2+1) spacetime (VSR-QED3). Due to the presence of new nonlocal couplings resulting from the VSR gauge symmetry, we have additional graphs contributing to the AA and AAA amplitudes. From these contributions, we discuss the VSR generalization of the Abelian Maxwell-Chern-Simons Lagrangian, consisting in the dynamical part and the Chern-Simons-like self-couplings, respectively. We use the VSR-Chern-Simons electrodynamics to discuss some non-Ohmic behavior on topological materials, in particular VSR effects on Hall's conductivity. In the dynamical part of the effective action, we observe the presence of a UV/IR mixing, due to the entanglement of the VSR nonlocal effects to the quantum higher-derivative terms. Furthermore, in the self-coupling aspect, we verify the validity of the Furry's theorem in the VSR-QED3 explicitly.
- ItemJoint dictionary and classifier learning for categorization of images using a max-margin framework(2014) Lobel, H.; Vidal, R.; Mery Quiroz, Domingo Arturo; Soto, A.
- ItemLearning discriminative local binary patterns for face recognition(2011) Maturana, D.; Mery Quiroz, Domingo Arturo; Soto, A.
- ItemRequerimientos térmicos para el desarrollo de Encarsia formosa (Hymenoptera:Aphelinidae) criado en Trialeurodes vaporiarorum (Hemiptera:Aleyrodidae).(2001) Soto, A.; Norero, A.; Apablaza, J.; Estay, P.
- ItemTowards improving Top-N recommendation by generalization of SLIM(2015) Larraín, S.; Parra Santander, Denis Alejandro; Soto, A.