# A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination

arXiv: https://arxiv.org/abs/2603.04125 · HTML: https://mlsanity.com/paper/2603.04125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Few-Shot Video Classification via Temporal Alignment](https://mlsanity.com/paper/1906.11415/) (2019)
- [Evidential Deep Learning for Open Set Action Recognition](https://mlsanity.com/paper/2107.10161/) (2021)
- [Temporal-Relational CrossTransformers for Few-Shot Action Recognition](https://mlsanity.com/paper/2101.06184/) (2021)
- [Spatio-temporal Relation Modeling for Few-shot Action Recognition](https://mlsanity.com/paper/2112.05132/) (2021)
- [Few-Shot Open-Set Recognition using Meta-Learning](https://mlsanity.com/paper/2005.13713/) (2020)
- [CLIP-guided Prototype Modulating for Few-shot Action Recognition](https://mlsanity.com/paper/2303.02982/) (2023)
- [MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition](https://mlsanity.com/paper/2304.00946/) (2023)
- [Few-shot Open-set Recognition by Transformation Consistency](https://mlsanity.com/paper/2103.01537/) (2021)
- [Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching](https://mlsanity.com/paper/2308.09346/) (2023)
- [Navigating Open Set Scenarios for Skeleton-based Action Recognition](https://mlsanity.com/paper/2312.06330/) (2023)
- [Task-Adaptive Negative Envision for Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2012.13073/) (2020)
- [Open-Set Recognition in the Age of Vision-Language Models](https://mlsanity.com/paper/2403.16528/) (2024)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [Glocal Energy-based Learning for Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2304.11855/) (2023)
- [Towards Generalized Few-Shot Open-Set Object Detection](https://mlsanity.com/paper/2210.15996/) (2022)
- [Semantic-aware Video Representation for Few-shot Action Recognition](https://mlsanity.com/paper/2311.06218/) (2023)
- [Few-shot Open-set Recognition Using Background as Unknowns](https://mlsanity.com/paper/2207.09059/) (2022)
- [Knowledge Prompting for Few-shot Action Recognition](https://mlsanity.com/paper/2211.12030/) (2022)
- [Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection](https://mlsanity.com/paper/2405.16146/) (2024)
- [One-Shot Open-Set Skeleton-Based Action Recognition](https://mlsanity.com/paper/2209.04288/) (2022)
- [Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition](https://mlsanity.com/paper/2303.15467/) (2023)
- [Large-Scale Evaluation of Open-Set Image Classification Techniques](https://mlsanity.com/paper/2406.09112/) (2024)

## Abstract (arXiv)

Few-Shot Action Recognition (FS-AR) has shown promising results but is often limited by a closed-set assumption that fails in real-world open-set scenarios. While Few-Shot Open-Set (FSOS) recognition is well-established for images, its extension to spatio-temporal video data remains underexplored. To address this, we propose an architectural extension based on a Feature-Residual Discriminator (FR-Disc), adapting previous work on skeletal data to the more complex video domain. Extensive experiments on five datasets demonstrate that while common open-set techniques provide only marginal gains, our FR-Disc significantly enhances unknown rejection capabilities without compromising closed-set accuracy, setting a new state-of-the-art for FSOS-AR. The project website, code, and benchmark are available at: https://hsp-iit.github.io/fsosar/.