research
∙
01/28/2022
Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation
Learning generalizeable policies from visual input in the presence of vi...
share
research
∙
12/02/2021
Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models
Modeling the world can benefit robot learning by providing a rich traini...
research
∙
05/28/2021
An Attention Free Transformer
We introduce Attention Free Transformer (AFT), an efficient variant of T...
research
∙
05/17/2021
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from...
research
∙
04/01/2021
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
We tackle the challenge of learning a distribution over complex, realist...
research
∙
06/27/2020
On the generalization of learning-based 3D reconstruction
State-of-the-art learning-based monocular 3D reconstruction methods lear...
research
∙
02/12/2020
Capsules with Inverted Dot-Product Attention Routing
We introduce a new routing algorithm for capsule networks, in which a ch...
research
∙
12/06/2019
Geometric Capsule Autoencoders for 3D Point Clouds
We propose a method to learn object representations from 3D point clouds...
research
∙
03/25/2015
Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
We propose a new way of incorporating temporal information present in vi...
research
∙
03/13/2015
Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
We conduct an in-depth exploration of different strategies for doing eve...
research
∙
02/16/2015
Unsupervised Learning of Video Representations using LSTMs
We use multilayer Long Short Term Memory (LSTM) networks to learn repres...
research
∙
12/20/2013
Learning Generative Models with Visual Attention
Attention has long been proposed by psychologists as important for effec...
research
∙
09/26/2013
Modeling Documents with Deep Boltzmann Machines
We introduce a Deep Boltzmann Machine model suitable for modeling and ex...
research
∙
07/03/2012
