# Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions

arXiv: https://arxiv.org/abs/2605.22697 · HTML: https://mlsanity.com/paper/2605.22697/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [Cross-view Action Modeling, Learning and Recognition](https://mlsanity.com/paper/1405.2941/) (2014)
- [Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings](https://mlsanity.com/paper/1908.03477/) (2019)
- [View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition](https://mlsanity.com/paper/1804.07453/) (2018)
- [Learning Robust Visual-Semantic Embeddings](https://mlsanity.com/paper/1703.05908/) (2017)
- [View-Invariant Probabilistic Embedding for Human Pose](https://mlsanity.com/paper/1912.01001/) (2019)
- [Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.18941/) (2024)
- [ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting](https://mlsanity.com/paper/2209.00065/) (2022)
- [Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition](https://mlsanity.com/paper/2210.16820/) (2022)
- [Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches](https://mlsanity.com/paper/2405.04771/) (2024)
- [Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization](https://mlsanity.com/paper/2012.01405/) (2020)
- [DVANet: Disentangling View and Action Features for Multi-View Action Recognition](https://mlsanity.com/paper/2312.05719/) (2023)
- [SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders](https://mlsanity.com/paper/2407.13460/) (2024)
- [Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2411.11288/) (2024)
- [PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose](https://mlsanity.com/paper/1910.12029/) (2019)
- [Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition](https://mlsanity.com/paper/2209.02986/) (2022)
- [STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences](https://mlsanity.com/paper/2407.10935/) (2024)

## Abstract (arXiv)

Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unseen actions from training. In this context, improving the recognition capabilities of Zero-Shot Action Recognition models (ZSAR), without requiring strong annotation efforts, remains a central challenge. Most ZSAR approaches assume that actions are observed under geometric conditions similar to those seen during training. In practice, variations in human body orientation and camera viewpoint add a significant domain gap in ZSAR, substantially limiting generalization to novel action-motion combinations. In this context, this paper presents a novel orientation-aware action recognition approach with improved cross-domain capabilities. Our approach combines motion cues of multiple camera viewpoints and text descriptions of human actions in the training phase. We present a new orientation-aware motion encoding network to learn different motion features, and adapt a specific orientation-aware text prompt to match the corresponding features at inference. Extensive experiments demonstrate that the proposed method consistently improves ZSAR performance across different recognition benchmarks, outperforming recent state-of-the-art zero-shot approaches on NTU-RGB+D, BABEL, NW-UCLA, and on two surveillance datasets. In addition, the learned representations exhibit strong transfer learning capabilities, yielding competitive performance on both cross-domain and same-domain recognition of seen actions. Code and trained models are available at: https://icb-vision-ai.github.io/OrientationAware-HAR