Cover Image

Foundation Model for Skeleton-Based Human Action Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Hongsong, Weng, Wanjiang, Wang, Junbo, Zhao, Fang, Xie, Guo-Sen, Geng, Xin, Wang, Liang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
by: Weng, Wanjiang, et al.
Published: (2024)

ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
by: Weng, Wanjiang, et al.
Published: (2025)

MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation
by: Tan, Xiaofeng, et al.
Published: (2026)

Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection
by: Tan, Xiaofeng, et al.
Published: (2024)

EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation
by: Tan, Xiaofeng, et al.
Published: (2026)

Point-Supervised Skeleton-Based Human Action Segmentation
by: Wang, Hongsong, et al.
Published: (2026)

ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
by: Weng, Wanjiang, et al.
Published: (2025)

Bilingual Text-to-Motion Generation: A New Benchmark and Baselines
by: Weng, Wanjiang, et al.
Published: (2026)

Towards Universal Skeleton-Based Action Recognition
by: Kuang, Jidong, et al.
Published: (2026)

Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition
by: Kuang, Jidong, et al.
Published: (2026)

Heterogeneous Skeleton-Based Action Representation Learning
by: Wang, Hongsong, et al.
Published: (2025)

Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition
by: Wang, Hongsong, et al.
Published: (2025)

Region-aware Image-based Human Action Retrieval with Transformers
by: Wang, Hongsong, et al.
Published: (2024)

PAMD: Plausibility-Aware Motion Diffusion Model for Long Dance Generation
by: Wang, Hongsong, et al.
Published: (2025)

Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
by: Kuang, Jidong, et al.
Published: (2024)

Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees
by: Lei, Haodong, et al.
Published: (2025)

Active Generation Network of Human Skeleton for Action Recognition
by: Liu, Long, et al.
Published: (2024)

IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition
by: Wang, Qingtian, et al.
Published: (2021)

OZ-TAL: Online Zero-Shot Temporal Action Localization
by: Han, Chaolei, et al.
Published: (2026)

Temporal Consistency-Aware Text-to-Motion Generation
by: Wang, Hongsong, et al.
Published: (2026)

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
by: Tan, Xiaofeng, et al.
Published: (2024)

Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
by: Chen, Bowen, et al.
Published: (2024)

Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection
by: Xu, Jing, et al.
Published: (2024)

SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition
by: Liu, Hongda, et al.
Published: (2025)

Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
by: Diao, Yunfeng, et al.
Published: (2022)

Controllable Dance Generation with Style-Guided Motion Diffusion
by: Wang, Hongsong, et al.
Published: (2024)

Coordinate-Based Dual-Constrained Autoregressive Motion Generation
by: Ding, Kang, et al.
Published: (2026)

Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
by: Liu, Hongda, et al.
Published: (2026)

Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning
by: Wang, Xinshun, et al.
Published: (2023)

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
by: Zhou, Yuxuan, et al.
Published: (2023)

Spatio-Temporal Encoding and Decoding-Based Method for Future Human Activity Skeleton Synthesis
by: Liu, Tingyu, et al.
Published: (2024)

Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors
by: Feng, Yingjie, et al.
Published: (2026)

Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
by: Han, Chaolei, et al.
Published: (2025)

SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition
by: Wang, Ning, et al.
Published: (2026)

Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation
by: Gökay, Uzay, et al.
Published: (2025)

GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition
by: Jiang, Lei, et al.
Published: (2024)

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation
by: Wang, Xinshun, et al.
Published: (2026)

LAC: Latent Action Composition for Skeleton-based Action Segmentation
by: Yang, Di, et al.
Published: (2023)

Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution
by: Wang, Jingyao, et al.
Published: (2024)

Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay
by: Wang, Hongsong, et al.
Published: (2025)