# High-Speed Vision Improves Zero-Shot Semantic Understanding of Human Actions

arXiv: https://arxiv.org/abs/2605.00496 · HTML: https://mlsanity.com/paper/2605.00496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling](https://mlsanity.com/paper/2501.12386/) (2025)
- [Generative Action Description Prompts for Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.05318/) (2022)
- [LLMs are Good Action Recognizers](https://mlsanity.com/paper/2404.00532/) (2024)
- [Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.18941/) (2024)
- [The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction](https://mlsanity.com/paper/2204.13340/) (2022)
- [Text-Enhanced Zero-Shot Action Recognition: A training-free approach](https://mlsanity.com/paper/2408.16412/) (2024)
- [Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models](https://mlsanity.com/paper/2501.13795/) (2025)
- [Rich Action-semantic Consistent Knowledge for Early Action Prediction](https://mlsanity.com/paper/2201.09169/) (2022)

## Abstract (arXiv)

Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. In scenarios such as rapid and less common activities, collecting sufficient labeled data for supervised learning is challenging, making zero-shot approaches a practical alternative for semantic understanding without task-specific training. While recent advances in large-scale pretrained models enable such zero-shot reasoning, the impact of temporal resolution, especially for rapid and fine-grained motions, remains underexplored. In this study, we investigate how temporal resolution affects zero-shot semantic understanding of high-speed human actions. Using kendo as a representative case of rapid and subtle motion patterns, we propose a training-free pipeline that combines a pre-trained video-language model for semantic representation with large language model-based reasoning for pairwise action comparison. Through controlled experiments across multiple frame rates (120 Hz, 60 Hz, and 30 Hz), we show that higher temporal resolution significantly improves semantic separability in zero-shot settings. We further analyze the role of tracking-based human joint information under both full and partial observation scenarios. Quantitative evaluation using a nearest-class prototype strategy demonstrates that high-speed video provides more stable and interpretable semantic representations for fast actions. These findings highlight the importance of temporal resolution in training-free action recognition and suggest that high-speed perception can enhance semantic understanding capabilities.