In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior are trained jointly to minimize a ratedistortion loss, which is closely related to the ELBO used in variational autoencoders. Despite its simplicity, we find that our method outperforms the state-of-the-art learned video compression networks based on motion compensation or interpolation. We systematically evaluate various design choices, such as the use of frame-based or spatio-temporal autoencoders, and the type of autoregressive prior.In addition, we present three extensions of the basic method that demonstrate the benefits over classical approaches to compression. First, we introduce semantic compression, where the model is trained to allocate more bits to objects of interest. Second, we study adaptive compression, where the model is adapted to a domain with limited variability, e.g. videos taken from an autonomous car, to achieve superior compression on that domain. Finally, we introduce multimodal compression, where we demonstrate the effectiveness of our model in joint compression of multiple modalities captured by non-standard imaging sensors, such as quad cameras. We believe that this opens up novel video compression applications, which have not been feasible with classical codecs.
An efficient treatment against a COVID-19 disease, caused by the novel coronavirus SARS-CoV-2 (CoV2), remains a challenge. The papain-like protease (PLpro) from the human coronavirus is a protease that plays a critical role in virus replication. Moreover, CoV2 uses this enzyme to modulate the host’s immune system to its own benefit. Therefore, it represents a highly promising target for the development of antiviral drugs. We used Approximate Bayesian Computation tools, molecular modelling and enzyme activity studies to identify highly active inhibitors of the PLpro. We discovered organoselenium compounds, ebselen and its structural analogues, as a novel approach for inhibiting the activity of PLproCoV2. Furthermore, we identified, for the first time, inhibitors of PLproCoV2 showing potency in the nanomolar range. Moreover, we found a difference between PLpro from SARS and CoV2 that can be correlated with the diverse dynamics of their replication, and, putatively to disease progression.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.