# Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting

arXiv: https://arxiv.org/abs/2406.08814 · HTML: https://mlsanity.com/paper/2406.08814/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 64 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Expanding Language-Image Pretrained Models for General Video Recognition](https://mlsanity.com/paper/2208.02816/) (2022)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [Context-Aware Crowd Counting](https://mlsanity.com/paper/1811.10452/) (2018)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [TAM: Temporal Adaptive Module for Video Recognition](https://mlsanity.com/paper/2005.06803/) (2020)
- [Counting Out Time: Class Agnostic Video Repetition Counting in the Wild](https://mlsanity.com/paper/2006.15418/) (2020)
- [Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization](https://mlsanity.com/paper/2302.00624/) (2023)
- [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)
- [FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2402.03241/) (2024)
- [AutoScale: Learning to Scale for Crowd Counting and Localization](https://mlsanity.com/paper/1912.09632/) (2019)
- [Context-aware and Scale-insensitive Temporal Repetition Counting](https://mlsanity.com/paper/2005.08465/) (2020)
- [Real-World Repetition Estimation by Div, Grad and Curl](https://mlsanity.com/paper/1802.09971/) (2018)
- [Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes](https://mlsanity.com/paper/2012.00946/) (2020)
- [(Quasi)Periodicity Quantification in Video Data, Using Topology](https://mlsanity.com/paper/1704.08382/) (2017)
- [3D Crowd Counting via Geometric Attention-guided Multi-View Fusion](https://mlsanity.com/paper/2003.08162/) (2020)

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

- [Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities](https://mlsanity.com/paper/2511.14945/) (2025)

## Abstract (arXiv)

The key to action counting is accurately locating each video's repetitive actions. Instead of estimating the probability of each frame belonging to an action directly, we propose a dual-branch network, i.e., SkimFocusNet, working in a two-step manner. The model draws inspiration from empirical observations indicating that humans typically engage in coarse skimming of entire sequences to grasp the general action pattern initially, followed by a finer, frame-by-frame focus to determine if it aligns with the target action. Specifically, SkimFocusNet incorporates a skim branch and a focus branch. The skim branch scans the global contextual information throughout the sequence to identify potential target action for guidance. Subsequently, the focus branch utilizes the guidance to diligently identify repetitive actions using a long-short adaptive guidance (LSAG) block. Additionally, we have observed that videos in existing datasets often feature only one type of repetitive action, which inadequately represents real-world scenarios. To more accurately describe real-life situations, we establish the Multi-RepCount dataset, which includes videos containing multiple repetitive motions. On Multi-RepCount, our SkimFoucsNet can perform specified action counting, that is, to enable counting a particular action type by referencing an exemplary video. This capability substantially exhibits the robustness of our method. Extensive experiments demonstrate that SkimFocusNet achieves state-of-the-art performances with significant improvements. We also conduct a thorough ablation study to evaluate the network components. The source code will be published upon acceptance.