Exploració per altres contribucions "Dimiccoli, Mariella"
Ara es mostren els items 1-7 de 7
-
Estudio e implementación de un algoritmo de image inpainting: priority belief propagation
(Universitat Politècnica de Catalunya, 2009-09)
Projecte/Treball Final de Carrera
Accés obertEn este proyecto se presenta un algoritmo que permite realizar tanto image inpainting como síntesis de texturas. Image inpainting consiste básicamente en recuperar de una forma visualmente plausible, una parte o región ... -
Exploring Graph Neural Networks for Video Action Segmentation
(Universitat Politècnica de Catalunya, 2023-05-30)
Projecte Final de Màster Oficial
Accés obertA common challenge in computer vision is the applicability of algorithms developed in a controlled dataset to real-world problems, such as unscripted or uncontrolled videos. Graph neural networks (GNNs) have emerged as a ... -
First-person activity recognition: how to generalize to unseen users?
(Universitat Politècnica de Catalunya, 2017)
Projecte Final de Màster Oficial
Accés obertRecent advances in wearable technology, accompanied by the decreasing cost of data storage and increase of data availability have made possible to take pictures everywhere at every time. Wearable cameras are nowadays ... -
Human motion dataset in the wild (MAT)
(Universitat Politècnica de Catalunya, 2019-03-07)
Treball Final de Grau
Accés obertThe popularity of wearable cameras is steadily increasing, both for entertainment and productivity purposes. Understanding the footage and inferring the body pose of the camera wearer can be of great importance in many ... -
Improving object detection by exploiting semantic relations between objects
(Universitat Politècnica de Catalunya, 2017-05)
Projecte Final de Màster Oficial
Accés obertObject detection is a fundamental and challenging problem in computer vision. Detecting the objects visible in an image can give us a good understanding and description of the image. The extracted information can later ... -
Learning graph-based event representations for unconstrained video segmentation
(Universitat Politècnica de Catalunya, 2021-05)
Projecte Final de Màster Oficial
Accés restringit per acord de confidencialitat
Realitzat a/amb: Institut de Robòtica i Informàtica IndustrialRecent research has shown that, in particular domains, unsupervised learning algorithms are achieving on par, or even better performance than fully supervised algorithms, avoiding the need of human labelled data. The ... -
Social relation recognition in egocentric photo-strems
(Universitat Politècnica de Catalunya, 2018-04-17)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat de Barcelona / Universitat Rovira i VirgiliPresentamos un método para la categorización automática de relaciones sociales en secuencias de imágenes egocéntricas. Por cada imagen, extraemos características visuales con redes convolucionales (atributos como edad, ...