# PV-NAS: Practical Neural Architecture Search for Video Recognition

arXiv: https://arxiv.org/abs/2011.00826 · HTML: https://mlsanity.com/paper/2011.00826/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

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

- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [Rethinking Graph Neural Architecture Search from Message-passing](https://mlsanity.com/paper/2103.14282/) (2021)
- [Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition](https://mlsanity.com/paper/2303.02693/) (2023)
- [Searching for TrioNet: Combining Convolution with Local and Global Self-Attention](https://mlsanity.com/paper/2111.07547/) (2021)

## Abstract (arXiv)

Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability. Deep neural networks for video tasks is highly customized and the design of such networks requires domain experts and costly trial and error tests. Recent advance in network architecture search has boosted the image recognition performance in a large margin. However, automatic designing of video recognition network is less explored. In this study, we propose a practical solution, namely Practical Video Neural Architecture Search (PV-NAS).Our PV-NAS can efficiently search across tremendous large scale of architectures in a novel spatial-temporal network search space using the gradient based search methods. To avoid sticking into sub-optimal solutions, we propose a novel learning rate scheduler to encourage sufficient network diversity of the searched models. Extensive empirical evaluations show that the proposed PV-NAS achieves state-of-the-art performance with much fewer computational resources. 1) Within light-weight models, our PV-NAS-L achieves 78.7% and 62.5% Top-1 accuracy on Kinetics-400 and Something-Something V2, which are better than previous state-of-the-art methods (i.e., TSM) with a large margin (4.6% and 3.4% on each dataset, respectively), and 2) among median-weight models, our PV-NAS-M achieves the best performance (also a new record)in the Something-Something V2 dataset.