Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Daniel Olmeda"'
Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained and frozen
Externí odkaz:
http://arxiv.org/abs/2407.16526
Visual relocalization is a key technique to autonomous driving, robotics, and virtual/augmented reality. After decades of explorations, absolute pose regression (APR), scene coordinate regression (SCR), and hierarchical methods (HMs) have become the
Externí odkaz:
http://arxiv.org/abs/2404.09271
Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent works atte
Externí odkaz:
http://arxiv.org/abs/2403.09307
Out-of-Distribution (OOD) detection is a crucial problem for the safe deployment of machine learning models identifying samples that fall outside of the training distribution, i.e. in-distribution data (ID). Most OOD works focus on the classification
Externí odkaz:
http://arxiv.org/abs/2310.01942
In Class-Incremental Learning (CIL) an image classification system is exposed to new classes in each learning session and must be updated incrementally. Methods approaching this problem have updated both the classification head and the feature extrac
Externí odkaz:
http://arxiv.org/abs/2303.13199
Autor:
Ricardo Vazquez, Hortensia Amaris, Monica Alonso, Gregorio Lopez, Jose Ignacio Moreno, Daniel Olmeda, Javier Coca
Publikováno v:
Energies, Vol 10, Iss 2, p 190 (2017)
This paper presents the implementation of an adaptive load forecasting methodology in two different power networks from a smart grid demonstration project deployed in the region of Madrid, Spain. The paper contains an exhaustive comparative study of
Externí odkaz:
https://doaj.org/article/c4224315435c4254b331c69223c648b9
Autor:
Rezaeianaran, Farzaneh, Shetty, Rakshith, Aljundi, Rahaf, Reino, Daniel Olmeda, Zhang, Shanshan, Schiele, Bernt
In order to robustly deploy object detectors across a wide range of scenarios, they should be adaptable to shifts in the input distribution without the need to constantly annotate new data. This has motivated research in Unsupervised Domain Adaptatio
Externí odkaz:
http://arxiv.org/abs/2110.01428
Autor:
Heylen, Jonas, De Wolf, Mark, Dawagne, Bruno, Proesmans, Marc, Van Gool, Luc, Abbeloos, Wim, Abdelkawy, Hazem, Reino, Daniel Olmeda
Monocular 3D object detection has recently shown promising results, however there remain challenging problems. One of those is the lack of invariance to different camera intrinsic parameters, which can be observed across different 3D object datasets.
Externí odkaz:
http://arxiv.org/abs/2110.00464
Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and transparency at deployment time. However, research in this area has only c
Externí odkaz:
http://arxiv.org/abs/2106.12964
Accurate prediction of pedestrian and bicyclist paths is integral to the development of reliable autonomous vehicles in dense urban environments. The interactions between vehicle and pedestrian or bicyclist have a significant impact on the trajectori
Externí odkaz:
http://arxiv.org/abs/2106.12442