# Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning

arXiv: https://arxiv.org/abs/2405.20606 · HTML: https://mlsanity.com/paper/2405.20606/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 68 references that are in the map.
- First posted on arXiv 31 May 2024.

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [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)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition](https://mlsanity.com/paper/1607.07043/) (2016)
- [Self-Knowledge Distillation with Progressive Refinement of Targets](https://mlsanity.com/paper/2006.12000/) (2020)
- [3D Human Action Representation Learning via Cross-View Consistency Pursuit](https://mlsanity.com/paper/2104.14466/) (2021)
- [View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1703.08274/) (2017)
- [PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding](https://mlsanity.com/paper/1703.07475/) (2017)
- [MS2L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition](https://mlsanity.com/paper/2010.05599/) (2020)
- [PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition](https://mlsanity.com/paper/1911.12409/) (2019)
- [Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training](https://mlsanity.com/paper/2301.02280/) (2023)
- [Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition](https://mlsanity.com/paper/2112.03590/) (2021)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Robust Audio-Visual Instance Discrimination](https://mlsanity.com/paper/2103.15916/) (2021)
- [Skeleton-Contrastive 3D Action Representation Learning](https://mlsanity.com/paper/2108.03656/) (2021)
- [Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning](https://mlsanity.com/paper/2108.01959/) (2021)
- [SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger](https://mlsanity.com/paper/2303.17561/) (2023)
- [Robust Cross-Modal Representation Learning with Progressive Self-Distillation](https://mlsanity.com/paper/2204.04588/) (2022)
- [Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models](https://mlsanity.com/paper/2301.00182/) (2022)
- [Generative Action Description Prompts for Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.05318/) (2022)
- [Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition](https://mlsanity.com/paper/2303.10904/) (2023)
- [CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation](https://mlsanity.com/paper/2208.12448/) (2022)

## Built on by (most cited first, 11 of 11)

- [Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2411.11288/) (2024)
- [Towards Robust and Realistic Human Pose Estimation via WiFi Signals](https://mlsanity.com/paper/2501.09411/) (2025)
- [Information-Theoretic Constraints for Continual Vision-Language-Action Alignment](https://mlsanity.com/paper/2603.13335/) (2026)
- [Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2409.02438/) (2024)
- [DoGCLR: Dominance-Game Contrastive Learning Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2511.14179/) (2025)
- [M3GCLR: Multi-View Mini-Max Infinite Skeleton-Data Game Contrastive Learning For Skeleton-Based Action Recognition](https://mlsanity.com/paper/2603.09367/) (2026)
- [Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection](https://mlsanity.com/paper/2606.02352/) (2026)
- [STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition](https://mlsanity.com/paper/2607.17342/) (2026)
- [Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2608.04623/) (2026)
- [BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emotion Recognition](https://mlsanity.com/paper/2608.06023/) (2026)
- [Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain](https://mlsanity.com/paper/2609.00788/) (2026)

## Abstract (arXiv)

Skeleton-based action representation learning aims to interpret and understand human behaviors by encoding the skeleton sequences, which can be categorized into two primary training paradigms: supervised learning and self-supervised learning. However, the former one-hot classification requires labor-intensive predefined action categories annotations, while the latter involves skeleton transformations (e.g., cropping) in the pretext tasks that may impair the skeleton structure. To address these challenges, we introduce a novel skeleton-based training framework (C2VL) based on Cross-modal Contrastive learning that uses the progressive distillation to learn task-agnostic human skeleton action representation from the Vision-Language knowledge prompts. Specifically, we establish the vision-language action concept space through vision-language knowledge prompts generated by pre-trained large multimodal models (LMMs), which enrich the fine-grained details that the skeleton action space lacks. Moreover, we propose the intra-modal self-similarity and inter-modal cross-consistency softened targets in the cross-modal representation learning process to progressively control and guide the degree of pulling vision-language knowledge prompts and corresponding skeletons closer. These soft instance discrimination and self-knowledge distillation strategies contribute to the learning of better skeleton-based action representations from the noisy skeleton-vision-language pairs. During the inference phase, our method requires only the skeleton data as the input for action recognition and no longer for vision-language prompts. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that our method outperforms the previous methods and achieves state-of-the-art results. Code is available at: https://github.com/cseeyangchen/C2VL.