Cover Image

Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Zeyu, Xia, Hailun, Zheng, Naichuan
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

SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion
by: Zheng, Naichuan, et al.
Published: (2025)

MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition
by: Zheng, Naichuan, et al.
Published: (2024)

Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics
by: Zheng, Naichuan, et al.
Published: (2024)

Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition
by: Liang, Zeyu, et al.
Published: (2024)

S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition
by: Zheng, Naichuan, et al.
Published: (2026)

LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation
by: Sun, Zepeng, et al.
Published: (2026)

Signal-SGN++: Topology-Enhanced Time-Frequency Spiking Graph Network for Skeleton-Based Action Recognition
by: Zheng, Naichuan, et al.
Published: (2025)

Human-Centric Transformer for Domain Adaptive Action Recognition
by: Lin, Kun-Yu, et al.
Published: (2024)

Representation-Centric Survey of Supervised Skeletal Action Recognition and the New Benchmark
by: Liu, Yang, et al.
Published: (2022)

ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding
by: Peng, Yi-Xing, et al.
Published: (2025)

Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?
by: Xie, Jianyang, et al.
Published: (2025)

Leveraging Foundation Models for Multimodal Graph-Based Action Recognition
by: Ziaeetabar, Fatemeh, et al.
Published: (2025)

Prompt-guided Disentangled Representation for Action Recognition
by: Wu, Tianci, et al.
Published: (2025)

BikeActions: An Open Platform and Benchmark for Cyclist-Centric VRU Action Recognition
by: Buettner, Max A., et al.
Published: (2026)

Learning Adaptive Node Selection with External Attention for Human Interaction Recognition
by: Pang, Chen, et al.
Published: (2025)

InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition
by: Chi, Seunggeun, et al.
Published: (2023)

Towards Adaptive Fusion of Multimodal Deep Networks for Human Action Recognition
by: Yudistira, Novanto
Published: (2025)

Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition
by: Li, Xunsong, et al.
Published: (2024)

MultiTSF: Transformer-based Sensor Fusion for Human-Centric Multi-view and Multi-modal Action Recognition
by: Nguyen, Trung Thanh, et al.
Published: (2025)

SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition
by: Peng, Zhuoxuan, et al.
Published: (2026)

MaskFi: Unsupervised Learning of WiFi and Vision Representations for Multimodal Human Activity Recognition
by: Yang, Jianfei, et al.
Published: (2024)

Collaboratively Self-supervised Video Representation Learning for Action Recognition
by: Zhang, Jie, et al.
Published: (2024)

Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning
by: Giannakakis, Nikos, et al.
Published: (2025)

Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement
by: Bai, Long, et al.
Published: (2025)

SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition
by: Ye, Qilang, et al.
Published: (2025)

Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition
by: Liu, Hongda, et al.
Published: (2023)

Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition
by: Hatano, Masashi, et al.
Published: (2024)

NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose Estimation
by: Huynh, Quang Dang, et al.
Published: (2026)

Human Action Recognition without Human
by: Kataoka, Hirokatsu, et al.
Published: (2016)

Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction
by: Heo, KunHo, et al.
Published: (2025)

Modular Retrieval-Augmented Generalization for Human Action Recognition
by: Liao, Peng, et al.
Published: (2026)

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

EPIR: An Efficient Patch Tokenization, Integration and Representation Framework for Micro-expression Recognition
by: Wang, Junbo, et al.
Published: (2026)

MS-CLR: Multi-Skeleton Contrastive Learning for Human Action Recognition
by: Kiray, Mert, et al.
Published: (2025)

ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition
by: Zhou, Jiaming, et al.
Published: (2024)

Video Domain Incremental Learning for Human Action Recognition in Home Environments
by: Hu, Yuanda, et al.
Published: (2024)

HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding
by: Li, Keliang, et al.
Published: (2024)

ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection
by: Hyun, Jeeho, et al.
Published: (2023)

Boundary-Centric Active Learning for Temporal Action Segmentation
by: Helvaci, Halil Ismail, et al.
Published: (2026)

Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning
by: Xi, Zeyu, et al.
Published: (2025)