Neural Information Processing Systems http://nips.cc/

Indeed, this is a central question of recent workstudyinggeneralized lowrankmodels.

Consequently, these methods can hardly be deployed on resource-limited mobile devices.

Neural Information Processing Systems http://nips.cc/

The reviewer further mentions relevant work around deformable convolutions and MSDNet which we will add to19 ourdiscussions. The24 reviewer mentions a parallel between our CondConv approach and Inception modules, but the methods are quite25 different. The reviewer then mentions specific questions with our discussion ofWi. In our CondConv approach, theWi are32 tensors of the same shape as the original kernels for the convolutional layer being replaced, with the same number33 ofchannels. The reviewer then suggests we analyze other non-linear activation functions to compute routing weights r(x).

With acareful study, we find amore general problem which is rooted in low-frequency words in the text corpus.

Neural Information Processing Systems http://nips.cc/

Our approach builds upon variational autoencoder (V AE) models for sequential data and combines them with recent work on neural image compression.

Dear Reviewers, we thank you for taking the time to provide valuable feedback. Below we address the main issues raised. Its performance depends on our ability to predict the distribution over future frames with low entropy. We will emphasize these aspects more in a revised version. RNNs to model dynamics in the latent space.

Transformer-based models, their huge parameter size poses a serious challenge to their training, both from the storage and computation perspectives.