Prototype-based meta-learning has emerged as a powerful technique for
ad...
We propose a self-supervised method for learning motion-focused video
re...
Despite the recent success of video self-supervised learning, there is m...
This paper strives to generate a synthetic computed tomography (CT) imag...
In this work, we introduce kernels with random Fourier features in the
m...
The 3rd annual installment of the ActivityNet Large- Scale Activity
Reco...
This paper addresses the problem of spatiotemporal localization of actio...
The ActivityNet Large Scale Activity Recognition Challenge 2017 Summary:...
In online action detection, the goal is to detect the start of an action...