Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Sandro Cavallari"'
Publikováno v:
Neurocomputing. 465:228-237
Video engagement is important in online advertisements where there is no physical interaction with the consumer. Engagement can be directly measured as the number of seconds after which a consumer skips an advertisement. In this paper, we propose a m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::058030630f4609a1847feec2d4ef9826
https://doi.org/10.1016/j.neucom.2021.08.127
https://doi.org/10.1016/j.neucom.2021.08.127
Publikováno v:
IEEE Computational Intelligence Magazine. 14:39-50
In this paper, we introduce a new setting for graph embedding, which considers embedding communities instead of individual nodes. We find that community embedding is not only useful for community-level applications such as graph visualization but als
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::729454b01256c89d1737cb566bee4da1
https://doi.org/10.1109/mci.2019.2919396
https://doi.org/10.1109/mci.2019.2919396
Publikováno v:
CEC
There is a large variety of products sold online and the websites are in several languages. Hence, it is desirable to train a model that can predict sentiments in different domains simultaneously. Previous authors have used deep learning to extract f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a56fa9ec337eadc2ff3e4eb7385d73b
https://doi.org/10.1109/cec48606.2020.9185713
https://doi.org/10.1109/cec48606.2020.9185713
Autor:
Sandro Cavallari
In the last few years, graphs have become an instinctive representative tool to better study complex structures. For example, in chemistry, it is common to represent and study the interaction between different proteins as a graph, reducing the experi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c74254747bb60ee3e8f3e4f38c4af36d
https://doi.org/10.32657/10220/48265
https://doi.org/10.32657/10220/48265
Publikováno v:
IJCNN
Microtext analysis is a crucial task for gauging social media opinion. In this paper, we compare four different deep learning encoder-decoder frameworks to handle microtext normalization problem. The frameworks have been evaluated on four different d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1d9fb5284fbb327ba42593bff7f2c53f
https://doi.org/10.1109/ijcnn.2019.8851895
https://doi.org/10.1109/ijcnn.2019.8851895
Publikováno v:
IJCNN
In the physical world, complex systems are generally created as the composition of multiple primitive components that interact with each other rather than a single monolithic structure. Recently, spatio-temporal graphs received a reasonable amount of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c2a8a955a93f0e4feb1a45d01f6fd89b
https://doi.org/10.1109/ijcnn.2019.8852191
https://doi.org/10.1109/ijcnn.2019.8852191
Publikováno v:
CIKM
In this paper, we study an important yet largely under-explored setting of graph embedding, i.e., embedding communities instead of each individual nodes. We find that community embedding is not only useful for community-level applications such as gra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5713c04916a21bb605edf02d72d91b3f
https://doi.org/10.1145/3132847.3132925
https://doi.org/10.1145/3132847.3132925