# Localization-Aware Multi-Scale Representation Learning for Repetitive Action Counting

arXiv: https://arxiv.org/abs/2501.07312 · HTML: https://mlsanity.com/paper/2501.07312/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [TAM: Temporal Adaptive Module for Video Recognition](https://mlsanity.com/paper/2005.06803/) (2020)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [Diffusion Action Segmentation](https://mlsanity.com/paper/2303.17959/) (2023)
- [Counting Out Time: Class Agnostic Video Repetition Counting in the Wild](https://mlsanity.com/paper/2006.15418/) (2020)
- [Iterative Crowd Counting](https://mlsanity.com/paper/1807.09959/) (2018)
- [TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting](https://mlsanity.com/paper/2204.01018/) (2022)
- [Global2Local: Efficient Structure Search for Video Action Segmentation](https://mlsanity.com/paper/2101.00910/) (2021)
- [Context-aware and Scale-insensitive Temporal Repetition Counting](https://mlsanity.com/paper/2005.08465/) (2020)
- [Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition](https://mlsanity.com/paper/2102.07092/) (2021)
- [Real-World Repetition Estimation by Div, Grad and Curl](https://mlsanity.com/paper/1802.09971/) (2018)
- [Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization](https://mlsanity.com/paper/2010.06215/) (2020)

## Built on by (most cited first, 1 of 1)

- [CoSTL: Comprehensive Spatial-Temporal Representation Learning for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2606.01149/) (2026)

## Abstract (arXiv)

Repetitive action counting (RAC) aims to estimate the number of class-agnostic action occurrences in a video without exemplars. Most current RAC methods rely on a raw frame-to-frame similarity representation for period prediction. However, this approach can be significantly disrupted by common noise such as action interruptions and inconsistencies, leading to sub-optimal counting performance in realistic scenarios. In this paper, we introduce a foreground localization optimization objective into similarity representation learning to obtain more robust and efficient video features. We propose a Localization-Aware Multi-Scale Representation Learning (LMRL) framework. Specifically, we apply a Multi-Scale Period-Aware Representation (MPR) with a scale-specific design to accommodate various action frequencies and learn more flexible temporal correlations. Furthermore, we introduce the Repetition Foreground Localization (RFL) method, which enhances the representation by coarsely identifying periodic actions and incorporating global semantic information. These two modules can be jointly optimized, resulting in a more discerning periodic action representation. Our approach significantly reduces the impact of noise, thereby improving counting accuracy. Additionally, the framework is designed to be scalable and adaptable to different types of video content. Experimental results on the RepCountA and UCFRep datasets demonstrate that our proposed method effectively handles repetitive action counting.