This paper presents VTN, a transformer-based framework for video recognition. Inspired by
recent developments in vision transformers, we ditch the standard approach in video action …

We present a general and flexible video-level framework for learning action models in
videos. This method, called temporal segment network (TSN), aims to model long-range …

Temporal modeling still remains challenging for action recognition in videos. To mitigate this
issue, this paper presents a new video architecture, termed as Temporal Difference Network …

Learning by deep convolutional networks have shown an outstanding effectiveness in a
variety of vision based classification tasks, and for which, large datasets are the …

This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video
Transformer (MM-ViT), for video action recognition. Different from other schemes which …

Temporal modeling has attracted the attention of a large number of researchers in the past
few years. In this work, we propose a new video architecture, termed as Temporal Excitation …

The two-stream convolutional network has been proved to be one milestone in the study of
video-based action recognition. Lots of recent works modify internal structure of two-stream …

In video action recognition, motion is a very crucial clue, which is usually represented by
optical flow. However, optical flow is computationally expensive to obtain, which becomes …

This study introduces an optimal topology of vision transformers for real-time video action
recognition in a cloud-based solution. Although model performance is a key criterion for real …

Current compressed video action recognition methods are mainly based on complete data.
However, in a real transmission scenario, the compressed video packets are usually …