# PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition

Source: [PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition](<https://www.sota2.com/research/paper/68fa67b61e209131cea1800e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:21:05.859Z

Authors: Yuecong Xu, Haozhi Cao, Jianfei Yang, Kezhi Mao, Jianxiong Yin, Simon See

Published: 2020-06-09T07:40:23.000Z

## Abstract

Long-range spatiotemporal dependencies capturing plays an essential role in improving video features for action recognition. The non-local block inspired by the non-local means is designed to address this challenge and have shown excellent performance. However, the non-local block brings significant increase in computation cost to the original network. It also lacks the ability to model regional correlation in videos. To address the above limitations, we propose Pyramid Non-Local (PNL) module, which extends the non-local block by incorporating regional correlation at multiple scales through a pyramid structured module. This extension upscales the effectiveness of non-local operation by attending to the interaction between different regions. Empirical results prove the effectiveness and efficiency of our PNL module, which achieves state-of-the-art performance of 83.09% on the Mini-Kinetics dataset, with decreased computation cost compared to the non-local block.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.05091>)

[PDF](<https://arxiv.org/pdf/2006.05091.pdf>)