# SRG: Snippet Relatedness-based Temporal Action Proposal Generator

arXiv: https://arxiv.org/abs/1911.11306 · HTML: https://mlsanity.com/paper/1911.11306/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation](https://mlsanity.com/paper/2210.02578/) (2022)
- [Agent-Environment Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/2107.08323/) (2021)
- [ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation](https://mlsanity.com/paper/2203.08942/) (2022)
- [Contextual Explainable Video Representation: Human Perception-based Understanding](https://mlsanity.com/paper/2212.06206/) (2022)
- [Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization](https://mlsanity.com/paper/2211.11324/) (2022)
- [Boundary Discretization and Reliable Classification Network for Temporal Action Detection](https://mlsanity.com/paper/2310.06403/) (2023)
- [PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization](https://mlsanity.com/paper/2103.05270/) (2021)

## Abstract (arXiv)

Recent temporal action proposal generation approaches have suggested integrating segment- and snippet score-based methodologies to produce proposals with high recall and accurate boundaries. In this paper, different from such a hybrid strategy, we focus on the potential of the snippet score-based approach. Specifically, we propose a new snippet score-based method, named Snippet Relatedness-based Generator (SRG), with a novel concept of "snippet relatedness". Snippet relatedness represents which snippets are related to a specific action instance. To effectively learn this snippet relatedness, we present "pyramid non-local operations" for locally and globally capturing long-range dependencies among snippets. By employing these components, SRG first produces a 2D relatedness score map that enables the generation of various temporal intervals reliably covering most action instances with high overlap. Then, SRG evaluates the action confidence scores of these temporal intervals and refines their boundaries to obtain temporal action proposals. On THUMOS-14 and ActivityNet-1.3 datasets, SRG outperforms state-of-the-art methods for temporal action proposal generation. Furthermore, compared to competing proposal generators, SRG leads to significant improvements in temporal action detection.