Human activity recognition (HAR) is one of the most important and challenging problems in
the computer vision. It has critical application in wide variety of tasks including gaming …

Neural Architecture Search (NAS) methods have been growing in popularity. These
techniques have been fundamental to automate and speed up the time consuming and error …

Abstract We present Mobile Video Networks (MoViNets), a family of computation and
memory efficient video networks that can operate on streaming video for online inference …

Abstract We introduce Video Transformer (VidTr) with separable-attention for video
classification. Comparing with commonly used 3D networks, VidTr is able to aggregate …

Video action recognition is one of the representative tasks for video understanding. Over the
last decade, we have witnessed great advancements in video action recognition thanks to …

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial
intelligence (AI), including computer vision, natural language processing, and speech …

Action recognition is an open and challenging problem in computer vision. While current
state-of-the-art models offer excellent recognition results, their computational expense limits …

In this paper, we introduce a novel visual representation learning which relies on a handful
of adaptively learned tokens, and which is applicable to both image and video …

Abstract Efficient Neural Architecture Search methods based on weight sharing have shown
good promise in democratizing Neural Architecture Search for computer vision models …

In this paper, we propose a conditional early exiting framework for efficient video
recognition. While existing works focus on selecting a subset of salient frames to reduce the …