# From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation

Source: [From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation](<https://www.sota2.com/research/paper/69f03f0b55a3c32af89f9fd1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-29T05:00:05.003Z

Authors: Zhong Han Ervin Yeoh, Jiang Kan

Published: 2026-04-21T06:43:04.000Z

## Abstract

Precise Event Spotting (PES) is essential in fast-paced sports such as tennis, where fine-grained events occur within very short temporal windows. Accurate frame-level localization is challenging because of motion blur, subtle action differences, and limited annotated data. We study two complementary distillation strategies for few-shot PES: Adaptive Weight Distillation (AWD), a prediction-level method that adaptively weights teacher supervision on unlabeled data, and Annealed Multimodal Distillation for Few-Shot Event Detection (AMD-FED), a representation-level framework that transfers robust skeleton knowledge into visual modalities through annealed pseudo-labeling. Both methods use multimodal distillation to improve generalization under limited supervision. We evaluate them on F3Set-Tennis(sub) under few-shot k-clip settings, where they consistently outperform single-modality baselines and prior PES approaches. After observing the stronger performance of representation-level distillation on tennis, we further validate AMD-FED on a second sports dataset, Figure Skating, where it also shows robust performance in the k-clip scenario. These results highlight the effectiveness of multimodal distillation, especially representation-level transfer, for few-shot precise event spotting.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Pose-based Event Segmentation on F3Set Tennis 50-clip few-shot sub](<https://www.sota2.com/research/sota/pose-based-event-segmentation-on-f3set-tennis-50-clip-few-shot-sub.md>): Pose-based Event Segmentation; F3Set Tennis 50-clip few-shot sub; Edit Rate: 72.58.

- [Pose-based Event Segmentation on F3Set-Tennis 100-clip few-shot sub](<https://www.sota2.com/research/sota/pose-based-event-segmentation-on-f3set-tennis-100-clip-few-shot-sub.md>): Pose-based Event Segmentation; F3Set-Tennis 100-clip few-shot sub; Edit Error: 77.03.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.22839>)

[PDF](<https://arxiv.org/pdf/2604.22839.pdf>)