activity
20152023
most citedNAS-Bench-101: Towards Reproducible Neural Architecture Search

252 citations · 611 across the 14 of their papers we have counts for

collaborators
Showing 2019Show all

11 papers · 1 filter

cs.CV2019

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

Junwei Liang, Lu Jiang, Kevin Murphy +2

This paper studies the problem of predicting the distribution over multiple possible future paths of people as they move through various visual scenes. We make two main contributio…

cs.LG20194 cited

Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems

Zhe Dong, Bryan A. Seybold, Kevin P. Murphy +1

We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for t…

cs.CV2019

Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction

Steven Hickson, Karthik Raveendran, Alireza Fathi +2

We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These ins…

cs.CV2019

Unsupervised Learning of Object Structure and Dynamics from Videos

Matthias Minderer, Chen Sun, Ruben Villegas +3

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-bas…

cs.LG2019

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

Yiding Jiang, Shixiang Gu, Kevin Murphy +1

Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notio…

cs.LG2019

Learning Video Representations using Contrastive Bidirectional Transformer

Chen Sun, Fabien Baradel, Kevin Murphy +1

This paper proposes a self-supervised learning approach for video features that results in significantly improved performance on downstream tasks (such as video classification, cap…