# Curriculum-Based Strategies for Efficient Cross-Domain Action Recognition

arXiv: https://arxiv.org/abs/2601.14101 · HTML: https://mlsanity.com/paper/2601.14101/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 17 of 17)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes](https://mlsanity.com/paper/1707.09465/) (2017)
- [UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles](https://mlsanity.com/paper/2104.00946/) (2021)
- [Synthetic Humans for Action Recognition from Unseen Viewpoints](https://mlsanity.com/paper/1912.04070/) (2019)
- [Robust Learning with Progressive Data Expansion Against Spurious Correlation](https://mlsanity.com/paper/2306.04949/) (2023)
- [Procedural Generation of Videos to Train Deep Action Recognition Networks](https://mlsanity.com/paper/1612.00881/) (2016)
- [Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances](https://mlsanity.com/paper/2303.10280/) (2023)
- [Progressive Transformation Learning for Leveraging Virtual Images in Training](https://mlsanity.com/paper/2211.01778/) (2022)

## Abstract (arXiv)

Despite significant progress in human action recognition, generalizing to diverse viewpoints remains a challenge. Most existing datasets are captured from ground-level perspectives, and models trained on them often struggle to transfer to drastically different domains such as aerial views. This paper examines how curriculum-based training strategies can improve generalization to unseen real aerial-view data without using any real aerial data during training. We explore curriculum learning for cross-view action recognition using two out-of-domain sources: synthetic aerial-view data and real ground-view data. Our results on the evaluation on order of training (fine-tuning on synthetic aerial data vs. real ground data) shows that fine-tuning on real ground data but differ in how they transition from synthetic to real. The first uses a two-stage curriculum with direct fine-tuning, while the second applies a progressive curriculum that expands the dataset in multiple stages before fine-tuning. We evaluate both methods on the REMAG dataset using SlowFast (CNN-based) and MViTv2 (Transformer-based) architectures. Results show that combining the two out-of-domain datasets clearly outperforms training on a single domain, whether real ground-view or synthetic aerial-view. Both curriculum strategies match the top-1 accuracy of simple dataset combination while offering efficiency gains. With the two-step fine-tuning method, SlowFast achieves up to a 37% reduction in iterations and MViTv2 up to a 30% reduction compared to simple combination. The multi-step progressive approach further reduces iterations, by up to 9% for SlowFast and 30% for MViTv2, relative to the two-step method. These findings demonstrate that curriculum-based training can maintain comparable performance (top-1 accuracy within 3% range) while improving training efficiency in cross-view action recognition.