# Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain

arXiv: https://arxiv.org/abs/2012.13726 · HTML: https://mlsanity.com/paper/2012.13726/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [RGB no more: Minimally-decoded JPEG Vision Transformers](https://mlsanity.com/paper/2211.16421/) (2022)
- [Less is More: Accelerating Faster Neural Networks Straight from JPEG](https://mlsanity.com/paper/2104.00185/) (2021)
- [Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers](https://mlsanity.com/paper/2109.02693/) (2021)
- [Mixup-based Deep Metric Learning Approaches for Incomplete Supervision](https://mlsanity.com/paper/2204.13572/) (2022)
- [CNNs for JPEGs: A Study in Computational Cost](https://mlsanity.com/paper/2309.11417/) (2023)

## Abstract (arXiv)

Human action recognition has become one of the most active field of research in computer vision due to its wide range of applications, like surveillance, medical, industrial environments, smart homes, among others. Recently, deep learning has been successfully used to learn powerful and interpretable features for recognizing human actions in videos. Most of the existing deep learning approaches have been designed for processing video information as RGB image sequences. For this reason, a preliminary decoding process is required, since video data are often stored in a compressed format. However, a high computational load and memory usage is demanded for decoding a video. To overcome this problem, we propose a deep neural network capable of learning straight from compressed video. Our approach was evaluated on two public benchmarks, the UCF-101 and HMDB-51 datasets, demonstrating comparable recognition performance to the state-of-the-art methods, with the advantage of running up to 2 times faster in terms of inference speed.