Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Peña, Fidel A Guerrero"'
Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly bounding box annotations for training. Given the importance of privacy in people counting, these models rely more
Externí odkaz:
http://arxiv.org/abs/2311.11974
Autor:
Aminbeidokhti, Masih, Peña, Fidel A. Guerrero, Medeiros, Heitor Rapela, Dubail, Thomas, Granger, Eric, Pedersoli, Marco
Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the training
Externí odkaz:
http://arxiv.org/abs/2310.06670
Autor:
Medeiros, Heitor Rapela, Pena, Fidel A. Guerrero, Aminbeidokhti, Masih, Dubail, Thomas, Granger, Eric, Pedersoli, Marco
Publikováno v:
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2024
A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the same distribution as the target domain. Given a cross-modal applicati
Externí odkaz:
http://arxiv.org/abs/2310.04662
Autor:
Peña, Fidel A. Guerrero, Medeiros, Heitor Rapela, Dubail, Thomas, Aminbeidokhti, Masih, Granger, Eric, Pedersoli, Marco
The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity. However, finding the
Externí odkaz:
http://arxiv.org/abs/2212.12042
Autor:
Dubail, Thomas, Peña, Fidel Alejandro Guerrero, Medeiros, Heitor Rapela, Aminbeidokhti, Masih, Granger, Eric, Pedersoli, Marco
In intelligent building management, knowing the number of people and their location in a room are important for better control of its illumination, ventilation, and heating with reduced costs and improved comfort. This is typically achieved by detect
Externí odkaz:
http://arxiv.org/abs/2209.11335
Autor:
Fernandez, Pedro D. Marrero, Ren, Tsang Ing, Jyh, Tsang Ing, Peña, Fidel A. Guerrero, Cunha, Alexandre
We propose a deep metric learning model to create embedded sub-spaces with a well defined structure. A new loss function that imposes Gaussian structures on the output space is introduced to create these sub-spaces thus shaping the distribution of th
Externí odkaz:
http://arxiv.org/abs/2001.06612
Autor:
Peña, Fidel A. Guerrero, Fernandez, Pedro D. Marrero, Tarr, Paul T., Ren, Tsang Ing, Meyerowitz, Elliot M., Cunha, Alexandre
We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. We improve the separation of touching and immediate cells, obtaining sharp segmentation boundaries with high adequ
Externí odkaz:
http://arxiv.org/abs/1910.09783
Autor:
Peña, Fidel Alejandro Guerrero, Fernández, Pedro Diamel Marrero, Ren, Tsang Ing, Vasconcelos, Germano Crispim, Cunha, Alexandre
Multi-Focus Image Fusion seeks to improve the quality of an acquired burst of images with different focus planes. For solving the task, an activity level measurement and a fusion rule are typically established to select and fuse the most relevant inf
Externí odkaz:
http://arxiv.org/abs/1908.10945
We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space representation for expression recognition. We devise this architecture based
Externí odkaz:
http://arxiv.org/abs/1902.03284
Autor:
Peña, Fidel A. Guerrero, Fernández, Pedro D. Marrero, Ren, Tsang Ing, Leandro, Jorge J. G., Nishihara, Ricardo
We propose a new incremental aggregation algorithm for multi-image deblurring with automatic image selection. The primary motivation is that current bursts deblurring methods do not handle well situations in which misalignment or out-of-context frame
Externí odkaz:
http://arxiv.org/abs/1810.12121