Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

Human Action Recognition (HAR) aims to understand human behavior and assign a label to
each action. It has a wide range of applications, and therefore has been attracting increasing …

Capitalizing on large pre-trained models for various downstream tasks of interest have
recently emerged with promising performance. Due to the ever-growing model size, the …

Video recognition has been dominated by the end-to-end learning paradigm–first initializing
a video recognition model with weights of a pretrained image model and then conducting …

Effectively extracting inter-frame motion and appearance information is important for video
frame interpolation (VFI). Previous works either extract both types of information in a mixed …

The canonical approach to video action recognition dictates a neural model to do a classic
and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined …

This paper presents X3D, a family of efficient video networks that progressively expand a
tiny 2D image classification architecture along multiple network axes, in space, time, width …

Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling
such visual tempos of different actions facilitates their recognition. Previous works often …

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, operating …

Adopting contrastive image-text pretrained models like CLIP towards video classification has
gained attention due to its cost-effectiveness and competitive performance. However, recent …