Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Mahdisoltani, Farzaneh"'
Autor:
Mahdisoltani, Farzaneh
Bayesian methods estimate a measure of uncertainty by using the posterior distribution. One source of difficulty in these methods is the computation of the normalizing constant. Calculating exact posterior is generally intractable and we usually appr
Externí odkaz:
http://arxiv.org/abs/2111.08002
Autor:
Zolfaghari, Mohammadreza, Çiçek, Özgün, Ali, Syed Mohsin, Mahdisoltani, Farzaneh, Zhang, Can, Brox, Thomas
Foreseeing the future is one of the key factors of intelligence. It involves understanding of the past and current environment as well as decent experience of its possible dynamics. In this work, we address future prediction at the abstract level of
Externí odkaz:
http://arxiv.org/abs/1905.03578
We introduce a hierarchical architecture for video understanding that exploits the structure of real world actions by capturing targets at different levels of granularity. We design the model such that it first learns simpler coarse-grained tasks, an
Externí odkaz:
http://arxiv.org/abs/1809.03316
We describe a DNN for video classification and captioning, trained end-to-end, with shared features, to solve tasks at different levels of granularity, exploring the link between granularity in a source task and the quality of learned features for tr
Externí odkaz:
http://arxiv.org/abs/1804.09235