# Rethinking matching-based few-shot action recognition

arXiv: https://arxiv.org/abs/2303.16084 · HTML: https://mlsanity.com/paper/2303.16084/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 28 Mar 2023.

## Builds on (most cited first, 28 of 28)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Probabilistic Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.02817/) (2018)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [Recasting Gradient-Based Meta-Learning as Hierarchical Bayes](https://mlsanity.com/paper/1801.08930/) (2018)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [Few-Shot Video Classification via Temporal Alignment](https://mlsanity.com/paper/1906.11415/) (2019)
- [Temporal-Relational CrossTransformers for Few-Shot Action Recognition](https://mlsanity.com/paper/2101.06184/) (2021)
- [D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation](https://mlsanity.com/paper/1901.02598/) (2019)
- [TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition](https://mlsanity.com/paper/1907.09021/) (2019)
- [Dense Classification and Implanting for Few-Shot Learning](https://mlsanity.com/paper/1903.05050/) (2019)
- [Spatio-temporal Relation Modeling for Few-shot Action Recognition](https://mlsanity.com/paper/2112.05132/) (2021)
- [Hybrid Relation Guided Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2204.13423/) (2022)
- [ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning](https://mlsanity.com/paper/1908.07410/) (2019)
- [ProtoGAN: Towards Few Shot Learning for Action Recognition](https://mlsanity.com/paper/1909.07945/) (2019)
- [Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers](https://mlsanity.com/paper/2108.11996/) (2021)
- [TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition](https://mlsanity.com/paper/2107.04782/) (2021)
- [Compound Prototype Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2207.05515/) (2022)
- [Few-shot Action Recognition with Prototype-centered Attentive Learning](https://mlsanity.com/paper/2101.08085/) (2021)
- [A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark](https://mlsanity.com/paper/2110.12358/) (2021)
- [Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation](https://mlsanity.com/paper/2007.04755/) (2020)

## Abstract (arXiv)

Few-shot action recognition, i.e. recognizing new action classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such information in the representation itself and learns classifiers at test time, or obtains frame-level features and performs pairwise temporal matching. We first evaluate a number of matching-based approaches using features from spatio-temporal backbones, a comparison missing from the literature, and show that the gap in performance between simple baselines and more complicated methods is significantly reduced. Inspired by this, we propose Chamfer++, a non-temporal matching function that achieves state-of-the-art results in few-shot action recognition. We show that, when starting from temporal features, our parameter-free and interpretable approach can outperform all other matching-based and classifier methods for one-shot action recognition on three common datasets without using temporal information in the matching stage. Project page: https://jbertrand89.github.io/matching-based-fsar