# Every Shot Counts: Using Exemplars for Repetition Counting in Videos

arXiv: https://arxiv.org/abs/2403.18074 · HTML: https://mlsanity.com/paper/2403.18074/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 74 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Builds on (most cited first, 30 of 40)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1806.02964/) (2018)
- [The THUMOS Challenge on Action Recognition for Videos "in the Wild"](https://mlsanity.com/paper/1604.06182/) (2016)
- [Rethinking the Faster R-CNN Architecture for Temporal Action Localization](https://mlsanity.com/paper/1804.07667/) (2018)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [TriDet: Temporal Action Detection with Relative Boundary Modeling](https://mlsanity.com/paper/2303.07347/) (2023)
- [Gaussian Temporal Awareness Networks for Action Localization](https://mlsanity.com/paper/1909.03877/) (2019)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [Representation Learning by Learning to Count](https://mlsanity.com/paper/1708.06734/) (2017)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [CLIP-Count: Towards Text-Guided Zero-Shot Object Counting](https://mlsanity.com/paper/2305.07304/) (2023)
- [Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting](https://mlsanity.com/paper/2203.08354/) (2022)
- [CounTR: Transformer-based Generalised Visual Counting](https://mlsanity.com/paper/2208.13721/) (2022)
- [HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training](https://mlsanity.com/paper/2212.14546/) (2022)
- [Counting Out Time: Class Agnostic Video Repetition Counting in the Wild](https://mlsanity.com/paper/2006.15418/) (2020)
- [Zero-shot Object Counting](https://mlsanity.com/paper/2303.02001/) (2023)
- [Where are the Blobs: Counting by Localization with Point Supervision](https://mlsanity.com/paper/1807.09856/) (2018)
- [From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer](https://mlsanity.com/paper/1908.06473/) (2019)
- [NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory](https://mlsanity.com/paper/2301.00746/) (2023)
- [TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting](https://mlsanity.com/paper/2204.01018/) (2022)
- [Clover: Towards A Unified Video-Language Alignment and Fusion Model](https://mlsanity.com/paper/2207.07885/) (2022)
- [Open-world Text-specified Object Counting](https://mlsanity.com/paper/2306.01851/) (2023)
- [Object Counting and Instance Segmentation with Image-level Supervision](https://mlsanity.com/paper/1903.02494/) (2019)

## Built on by (most cited first, 9 of 9)

- [Human Motion Instruction Tuning](https://mlsanity.com/paper/2411.16805/) (2024)
- [CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model](https://mlsanity.com/paper/2503.17690/) (2025)
- [Open-World Object Counting in Videos](https://mlsanity.com/paper/2506.15368/) (2025)
- [OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos](https://mlsanity.com/paper/2407.17085/) (2024)
- [WeaveLA: Event Driven Cross-Subtask Latent Memory Weaving for Repetitive Robot Manipulation](https://mlsanity.com/paper/2606.17463/) (2026)
- [Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities](https://mlsanity.com/paper/2511.14945/) (2025)
- [Every Step of the Way: Video-based Parkinsonian Turning Step Counting](https://mlsanity.com/paper/2606.27918/) (2026)
- [TReViS: Temporal Repetition Structure Aware Video Synthesis for Self-supervised Repetitive Action Counting](https://mlsanity.com/paper/2609.24367/) (2026)
- [RepProbe: Can Video Language Models Count Repeated Actions? A Diagnostic Benchmark](https://mlsanity.com/paper/2610.18844/) (2026)

## Abstract (arXiv)

Video repetition counting infers the number of repetitions of recurring actions or motion within a video. We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos. Our proposed Every Shot Counts (ESCounts) model is an attention-based encoder-decoder that encodes videos of varying lengths alongside exemplars from the same and different videos. In training, ESCounts regresses locations of high correspondence to the exemplars within the video. In tandem, our method learns a latent that encodes representations of general repetitive motions, which we use for exemplar-free, zero-shot inference. Extensive experiments over commonly used datasets (RepCount, Countix, and UCFRep) showcase ESCounts obtaining state-of-the-art performance across all three datasets. Detailed ablations further demonstrate the effectiveness of our method.