Despite the recent success of end-to-end learned representations, hand-crafted optical flow
features are still widely used in video analysis tasks. To fill this gap, we propose TVNet, a …

In this paper, the focus of this study is to explore two advanced deep learning
methodologies, specifically, Convolutional Long Short-Term Memory (ConvLSTM) networks …

This paper introduces a new video understanding network referred to as' ViViP'(Video Vision
Poolformer), which leverages poolformer and transformer techniques. It begins by encoding …

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 …

We propose a self-supervised learning method to jointly reason about spatial and temporal
context for video recognition. Recent self-supervised approaches have used spatial context …

Existing action recognition methods typically sample a few frames to represent each video to
avoid the enormous computation, which often limits the recognition performance. To tackle …

Deep learning has achieved tremendous success on various computer vision tasks.
However, deep learning methods and models are usually computationally expensive …

Abstract Human Activity Recognition (HAR) is the process of automatic recognition of
Activities of Daily Living (ADL) from human motion data captured in various data modalities …

Corrections to “Three-Stream Network With Bidirectional Self-Attention for Action
Recognition in Extreme Low Resoluti Page 1 2188 IEEE SIGNAL PROCESSING LETTERS …

The local key features in video are important for improving the accuracy of human action
recognition. However, most end-to-end methods focus on global feature learning from …