# PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition

arXiv: https://arxiv.org/abs/2605.11497 · HTML: https://mlsanity.com/paper/2605.11497/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [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)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding](https://mlsanity.com/paper/1703.07475/) (2017)
- [Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings](https://mlsanity.com/paper/1908.03477/) (2019)
- [Learning Robust Visual-Semantic Embeddings](https://mlsanity.com/paper/1703.05908/) (2017)
- [Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2101.11530/) (2021)
- [Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization](https://mlsanity.com/paper/2308.03950/) (2023)
- [Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition](https://mlsanity.com/paper/2406.13327/) (2024)
- [Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space](https://mlsanity.com/paper/1911.11344/) (2019)
- [Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2404.07487/) (2024)
- [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)
- [Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment](https://mlsanity.com/paper/2409.14336/) (2024)
- [Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.10745/) (2024)
- [Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2506.22179/) (2025)
- [SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living](https://mlsanity.com/paper/2502.03459/) (2025)
- [Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition](https://mlsanity.com/paper/2511.09388/) (2025)
- [SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2603.29692/) (2026)

## Abstract (arXiv)

Zero-shot skeleton-based action recognition (ZSSAR) is typically treated as a skeleton-text alignment problem: encode joint-coordinate sequences, align them with language, and classify unseen actions. We argue that this alignment is often too late. Skeletons are not complete action observations, but compressed outputs of human pose estimation (HPE); by the time alignment begins, human-object interactions and pose-relative visual cues may no longer be explicit. We call this upstream semantic loss. To address it, we propose PoseBridge, an HPE-aware ZSSAR framework that bridges intermediate HPE representations to skeleton-text alignment. Rather than adding an RGB action branch or object detector, PoseBridge extracts pose-anchored semantic cues from the same HPE process that produces skeletons, then transfers them through skeleton-conditioned bridging and semantic prototype adaptation. Across NTU-RGB+D 60/120, PKU-MMD, and Kinetics-200/400, PoseBridge improves ZSSAR performance under the evaluated protocols. On the Kinetics-200/400 PURLS benchmark, which contains in-the-wild videos with diverse scenes and action contexts, PoseBridge shows the clearest separation, improving the strongest compared baseline by 13.3-17.4 points across all eight splits. Our code will be publicly released.