MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition. (arXiv:2201.08383v1 [cs.CV])

While today's video recognition systems parse snapshots or short clips
accurately, they cannot connect the dots and reason across a longer range of
time yet. Most existing video architectures can only process <5 seconds of a
video without hitting the computation or memory bottlenecks.

In this paper, we propose a new strategy to overcome this challenge. Instead
of trying to process more frames at once like most existing methods, we propose
to process videos in an online fashion and cache …

arxiv cv transformer video vision