# Metric-Based Few-Shot Learning for Video Action Recognition

arXiv: https://arxiv.org/abs/1909.09602 · HTML: https://mlsanity.com/paper/1909.09602/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [Few-Shot Action Recognition with Compromised Metric via Optimal Transport](https://mlsanity.com/paper/2104.03737/) (2021)
- [Anomaly Crossing: New Horizons for Video Anomaly Detection as Cross-domain Few-shot Learning](https://mlsanity.com/paper/2112.06320/) (2021)
- [Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning](https://mlsanity.com/paper/2308.02173/) (2023)
- [Informative Sample-Aware Proxy for Deep Metric Learning](https://mlsanity.com/paper/2211.10382/) (2022)
- [Few-Shot Action Localization without Knowing Boundaries](https://mlsanity.com/paper/2106.04150/) (2021)
- [Few-Shot Video Recognition via Hierarchical Metric Learning](https://mlsanity.com/paper/2609.05242/) (2026)

## Abstract (arXiv)

In the few-shot scenario, a learner must effectively generalize to unseen classes given a small support set of labeled examples. While a relatively large amount of research has gone into few-shot learning for image classification, little work has been done on few-shot video classification. In this work, we address the task of few-shot video action recognition with a set of two-stream models. We evaluate the performance of a set of convolutional and recurrent neural network video encoder architectures used in conjunction with three popular metric-based few-shot algorithms. We train and evaluate using a few-shot split of the Kinetics 600 dataset. Our experiments confirm the importance of the two-stream setup, and find prototypical networks and pooled long short-term memory network embeddings to give the best performance as few-shot method and video encoder, respectively. For a 5-shot 5-way task, this setup obtains 84.2% accuracy on the test set and 59.4% on a special "challenge" test set, composed of highly confusable classes.