# TReViS: Temporal Repetition Structure Aware Video Synthesis for Self-supervised Repetitive Action Counting

arXiv: https://arxiv.org/abs/2609.24367 · HTML: https://mlsanity.com/paper/2609.24367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)
- [TAM: Temporal Adaptive Module for Video Recognition](https://mlsanity.com/paper/2005.06803/) (2020)
- [Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning](https://mlsanity.com/paper/2006.11476/) (2020)
- [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)
- [VideoMix: Rethinking Data Augmentation for Video Classification](https://mlsanity.com/paper/2012.03457/) (2020)
- [SimPer: Simple Self-Supervised Learning of Periodic Targets](https://mlsanity.com/paper/2210.03115/) (2022)
- [Context-aware and Scale-insensitive Temporal Repetition Counting](https://mlsanity.com/paper/2005.08465/) (2020)
- [Self-supervised Video Representation Learning by Context and Motion Decoupling](https://mlsanity.com/paper/2104.00862/) (2021)
- [Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition](https://mlsanity.com/paper/2102.07092/) (2021)
- [Temporal Reasoning Graph for Activity Recognition](https://mlsanity.com/paper/1908.09995/) (2019)
- [Real-World Repetition Estimation by Div, Grad and Curl](https://mlsanity.com/paper/1802.09971/) (2018)
- [Repetitive Action Counting with Hybrid Temporal Relation Modeling](https://mlsanity.com/paper/2412.07233/) (2024)
- [Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance](https://mlsanity.com/paper/2204.10312/) (2022)
- [Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models](https://mlsanity.com/paper/2411.08466/) (2024)
- [Every Shot Counts: Using Exemplars for Repetition Counting in Videos](https://mlsanity.com/paper/2403.18074/) (2024)
- [CycleCL: Self-supervised Learning for Periodic Videos](https://mlsanity.com/paper/2311.03402/) (2023)
- [Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos](https://mlsanity.com/paper/2003.06838/) (2020)
- [Rethinking temporal self-similarity for repetitive action counting](https://mlsanity.com/paper/2407.09431/) (2024)
- [Perturbation-based Self-supervised Attention for Attention Bias in Text Classification](https://mlsanity.com/paper/2305.15684/) (2023)

## Abstract (arXiv)

Fully supervised repetitive action counting (RAC) has achieved strong performance, but requires dense temporal annotations that are costly and difficult to scale. We propose TReViS, a self-supervised video synthesis framework that enables training RAC models without any repetition labels. TReViS estimates the underlying temporal repetition structure of an unlabeled video via a Temporal Self-Similarity Matrix, infers its cycle statistics, and synthesizes new training sequences that preserve realistic repetition patterns while introducing controlled temporal variability. These synthesized videos are paired with pseudo-labels and used to train existing RAC architectures from scratch. Across multiple datasets and backbones, TReViS consistently outperforms prior self-supervised methods and achieves performance competitive with several supervised baselines, while remaining fully label-free, demonstrating the effectiveness of structure-aware video synthesis for label-free RAC. The source code is available at https://github.com/yfqi/TReViS.