Pedestrian detection is a key problem in computer vision, with several applications that have
the potential to positively impact quality of life. In recent years, the number of approaches to …

Abstract Human Action Recognition (HAR) involves human activity monitoring task in
different areas of medical, education, entertainment, visual surveillance, video retrieval, as …

Abstract We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training
of video models. Our approach first randomly masks out a portion of the input sequence and …

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 …

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and
study their effects on action recognition. Our motivation stems from the observation that 2D …

We investigate architectures of discriminatively trained deep Convolutional Networks
(ConvNets) for action recognition in video. The challenge is to capture the complementary …

Anomaly detection in videos refers to the identification of events that do not conform to
expected behavior. However, almost all existing methods tackle the problem by minimizing …

Recently dense trajectories were shown to be an efficient video representation for action
recognition and achieved state-of-the-art results on a variety of datasets. This paper …

Perceiving meaningful activities in a long video sequence is a challenging problem due to
ambiguous definition ofmeaningfulness' as well as clutters in the scene. We approach this …

This paper presents a general ConvNet architecture for video action recognition based on
multiplicative interactions of spacetime features. Our model combines the appearance and …