# Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition

arXiv: https://arxiv.org/abs/1907.09382 · HTML: https://mlsanity.com/paper/1907.09382/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [Learning to Align Sequential Actions in the Wild](https://mlsanity.com/paper/2111.09301/) (2021)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos](https://mlsanity.com/paper/2301.00794/) (2023)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [Continuous Human Action Recognition for Human-Machine Interaction: A Review](https://mlsanity.com/paper/2202.13096/) (2022)
- [Unified Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2311.13254/) (2023)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)
- [GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning](https://mlsanity.com/paper/2207.10158/) (2022)
- [Improving Generalization in Meta-Learning via Meta-Gradient Augmentation](https://mlsanity.com/paper/2306.08460/) (2023)

## Abstract (arXiv)

The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot transfer learning for first-person action classification. We leverage independently trained local visual cues to learn representations that can be transferred from a source domain, which provides primitive action labels, to a different target domain using only a handful of examples. Visual cues we employ include object-object interactions, hand grasps and motion within regions that are a function of hand locations. We employ a framework based on meta-learning to extract the distinctive and domain invariant components of the deployed visual cues. This enables transfer of action classification models across public datasets captured with diverse scene and action configurations. We present comparative results of our transfer learning methodology and report superior results over state-of-the-art action classification approaches for both inter-class and inter-dataset transfer.