# Counting Out Time: Class Agnostic Video Repetition Counting in the Wild

arXiv: https://arxiv.org/abs/2006.15418 · HTML: https://mlsanity.com/paper/2006.15418/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2020.

## Built on by (most cited first, 30 of 68)

- [Knowing Where to Focus: Event-aware Transformer for Video Grounding](https://mlsanity.com/paper/2308.06947/) (2023)
- [The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video](https://mlsanity.com/paper/2111.09748/) (2021)
- [Seed1.8 Model Card: Towards Generalized Real-World Agency](https://mlsanity.com/paper/2603.20633/) (2026)
- [TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting](https://mlsanity.com/paper/2204.01018/) (2022)
- [SimPer: Simple Self-Supervised Learning of Periodic Targets](https://mlsanity.com/paper/2210.03115/) (2022)
- [Zero-shot Natural Language Video Localization](https://mlsanity.com/paper/2110.00428/) (2021)
- [Mavors: Multi-granularity Video Representation for Multimodal Large Language Model](https://mlsanity.com/paper/2504.10068/) (2025)
- [Self-Supervised Representation Learning from Flow Equivariance](https://mlsanity.com/paper/2101.06553/) (2021)
- [SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis](https://mlsanity.com/paper/2310.15247/) (2023)
- [Text-Conditioned Resampler For Long Form Video Understanding](https://mlsanity.com/paper/2312.11897/) (2023)
- [Language-free Training for Zero-shot Video Grounding](https://mlsanity.com/paper/2210.12977/) (2022)
- [UBoCo : Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection](https://mlsanity.com/paper/2111.14799/) (2021)
- [Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection](https://mlsanity.com/paper/2112.04771/) (2021)
- [PoseRAC: Pose Saliency Transformer for Repetitive Action Counting](https://mlsanity.com/paper/2303.08450/) (2023)
- [PrivHAR: Recognizing Human Actions From Privacy-preserving Lens](https://mlsanity.com/paper/2206.03891/) (2022)
- [AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs](https://mlsanity.com/paper/2506.05328/) (2025)
- [CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model](https://mlsanity.com/paper/2503.17690/) (2025)
- [Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach](https://mlsanity.com/paper/2106.11549/) (2021)
- [Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos](https://mlsanity.com/paper/2303.12370/) (2023)
- [OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos](https://mlsanity.com/paper/2407.17085/) (2024)
- [Exploring Temporally Dynamic Data Augmentation for Video Recognition](https://mlsanity.com/paper/2206.15015/) (2022)
- [Every Shot Counts: Using Exemplars for Repetition Counting in Videos](https://mlsanity.com/paper/2403.18074/) (2024)
- [Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects](https://mlsanity.com/paper/2604.05546/) (2026)
- [Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks](https://mlsanity.com/paper/2211.06023/) (2022)
- [Full Resolution Repetition Counting](https://mlsanity.com/paper/2305.13778/) (2023)
- [CycleCL: Self-supervised Learning for Periodic Videos](https://mlsanity.com/paper/2311.03402/) (2023)
- [Seeing without Pixels: Perception from Camera Trajectories](https://mlsanity.com/paper/2511.21681/) (2025)
- [Echo-SyncNet: Self-supervised Cardiac View Synchronization in Echocardiography](https://mlsanity.com/paper/2102.02287/) (2021)
- [Viewpoint-Invariant Exercise Repetition Counting](https://mlsanity.com/paper/2107.13760/) (2021)
- [Rehabilitation Exercise Repetition Segmentation and Counting using Skeletal Body Joints](https://mlsanity.com/paper/2304.09735/) (2023)

## Abstract (arXiv)

We present an approach for estimating the period with which an action is repeated in a video. The crux of the approach lies in constraining the period prediction module to use temporal self-similarity as an intermediate representation bottleneck that allows generalization to unseen repetitions in videos in the wild. We train this model, called Repnet, with a synthetic dataset that is generated from a large unlabeled video collection by sampling short clips of varying lengths and repeating them with different periods and counts. This combination of synthetic data and a powerful yet constrained model, allows us to predict periods in a class-agnostic fashion. Our model substantially exceeds the state of the art performance on existing periodicity (PERTUBE) and repetition counting (QUVA) benchmarks. We also collect a new challenging dataset called Countix (~90 times larger than existing datasets) which captures the challenges of repetition counting in real-world videos. Project webpage: https://sites.google.com/view/repnet .