Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.04125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917314129035264 |
|---|---|
| author | Berti, Stefano Pasquale, Giulia Natale, Lorenzo |
| author_facet | Berti, Stefano Pasquale, Giulia Natale, Lorenzo |
| contents | 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/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04125 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination Berti, Stefano Pasquale, Giulia Natale, Lorenzo Computer Vision and Pattern Recognition 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/. |
| title | A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.04125 |