# T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition

arXiv: https://arxiv.org/abs/2606.21607 · HTML: https://mlsanity.com/paper/2606.21607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 41 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [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)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding](https://mlsanity.com/paper/2105.09996/) (2021)
- [PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding](https://mlsanity.com/paper/1703.07475/) (2017)
- [Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition](https://mlsanity.com/paper/2112.03590/) (2021)
- [Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection](https://mlsanity.com/paper/2010.14982/) (2020)
- [Masked Motion Predictors are Strong 3D Action Representation Learners](https://mlsanity.com/paper/2308.07092/) (2023)
- [Temporal Gaussian Mixture Layer for Videos](https://mlsanity.com/paper/1803.06316/) (2018)
- [Graph Distillation for Action Detection with Privileged Modalities](https://mlsanity.com/paper/1712.00108/) (2017)
- [UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition](https://mlsanity.com/paper/2107.08580/) (2021)
- [Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection](https://mlsanity.com/paper/2108.03619/) (2021)
- [Online Human Action Detection using Joint Classification-Regression Recurrent Neural Networks](https://mlsanity.com/paper/1604.05633/) (2016)
- [ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting](https://mlsanity.com/paper/2209.00065/) (2022)
- [Privacy-Preserving Video Anomaly Detection: A Survey](https://mlsanity.com/paper/2411.14565/) (2024)

## Abstract (arXiv)

Vision-language models such as CLIP have recently achieved strong performance on a wide range of visual understanding tasks. However, most existing models rely primarily on appearance-level supervision from images or videos, and do not explicitly model human motion, which is essential for fine-grained and human-centric action recognition task as actions are defined by temporally structured and physically grounded body movements. To address this problem, we propose Transferable skeleton MOtion Representation (T-MOR), a motion-aware framework that learns transferable action representations from skeleton sequences with the aid of video and language supervision during training. T-MOR adopts a multi-modal contrastive learning scheme that aligns skeleton motion with visual and textual representations, while performing inference using only lightweight skeleton inputs. To support large-scale pre-training, we construct PoseCap-1M, a new dataset that contains over one million synchronized video, skeleton, and text triplets covering diverse human activities. We evaluate T-MOR on a range of human-centric action recognition benchmarks, including action classification and frame-wise temporal detection. Experimental results show that T-MOR consistently improves performance across multiple datasets, such as Toyota Smarthome, Penn Action, UAV-Human, TSU, and Charades. In addition, T-MOR demonstrates strong generalization ability in few-shot and zero-shot settings, highlighting the effectiveness of motion-centric and embodied representations for transferable action understanding.