# Full Resolution Repetition Counting

arXiv: https://arxiv.org/abs/2305.13778 · HTML: https://mlsanity.com/paper/2305.13778/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [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)
- [Counting Out Time: Class Agnostic Video Repetition Counting in the Wild](https://mlsanity.com/paper/2006.15418/) (2020)
- [TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting](https://mlsanity.com/paper/2204.01018/) (2022)
- [Context-aware and Scale-insensitive Temporal Repetition Counting](https://mlsanity.com/paper/2005.08465/) (2020)
- [PoseRAC: Pose Saliency Transformer for Repetitive Action Counting](https://mlsanity.com/paper/2303.08450/) (2023)

## Built on by (most cited first, 4 of 4)

- [CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model](https://mlsanity.com/paper/2503.17690/) (2025)
- [OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos](https://mlsanity.com/paper/2407.17085/) (2024)
- [Rethinking temporal self-similarity for repetitive action counting](https://mlsanity.com/paper/2407.09431/) (2024)
- [MultiCounter: Multiple Action Agnostic Repetition Counting in Untrimmed Videos](https://mlsanity.com/paper/2409.04035/) (2024)

## Abstract (arXiv)

Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive actions, also optimization challenges in end-to-end video model training, down-sampling is commonly utilized in recent state-of-the-art methods, leading to ignorance of several repetitive samples. In this paper, we attempt to understand repetitive actions from a full temporal resolution view, by combining offline feature extraction and temporal convolution networks. The former step enables us to train repetition counting network without down-sampling while preserving all repetition regardless of the video length and action frequency, and the later network models all frames in a flexible and dynamically expanding temporal receptive field to retrieve all repetitions with a global aspect. We experimentally demonstrate that our method achieves better or comparable performance in three public datasets, i.e., TransRAC, UCFRep and QUVA. We expect this work will encourage our community to think about the importance of full temporal resolution.