331 citations · 831 across the 12 of their papers we have counts for
20 papers · 1 filter
Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors
Yedid Hoshen, Jitendra Malik
Unconditional image generation has recently been dominated by generative adversarial networks (GANs). GAN methods train a generator which regresses images from random noise vectors…
Visual Memory for Robust Path Following
Ashish Kumar, Saurabh Gupta, David Fouhey +2
Humans routinely retrace paths in a novel environment both forwards and backwards despite uncertainty in their motion. This paper presents an approach for doing so. Given a demonst…
Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies
Alexander Sax, Bradley Emi, Amir R. Zamir +3
How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study t…
SlowFast Networks for Video Recognition
Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik +1
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, opera…
Learning 3D Human Dynamics from Video
Angjoo Kanazawa, Jason Y. Zhang, Panna Felsen +1
From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics t…
Are All Training Examples Created Equal? An Empirical Study
Kailas Vodrahalli, Ke Li, Jitendra Malik
Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for traini…