BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cho, Seungyeon, Kim, Tae-kyun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915703858135040
author Cho, Seungyeon
Kim, Tae-kyun
author_facet Cho, Seungyeon
Kim, Tae-kyun
contents Skeleton-based human action recognition (HAR) has achieved remarkable progress with graph-based architectures. However, most existing methods remain body-centric, focusing on large-scale motions while neglecting subtle hand articulations that are crucial for fine-grained recognition. This work presents a probabilistic dual-stream framework that unifies reliability modeling and multi-modal integration, generalizing expertized learning under uncertainty across both intra-skeleton and cross-modal domains. The framework comprises three key components: (1) a calibration-free preprocessing pipeline that removes canonical-space transformations and learns directly from native coordinates; (2) a probabilistic Noisy-OR fusion that stabilizes reliability-aware dual-stream learning without requiring explicit confidence supervision; and (3) an intra- to cross-modal ensemble that couples four skeleton modalities (Joint, Bone, Joint Motion, and Bone Motion) to RGB representations, bridging structural and visual motion cues in a unified cross-modal formulation. Comprehensive evaluations across multiple benchmarks (NTU RGB+D~60/120, PKU-MMD, N-UCLA) and a newly defined hand-centric benchmark exhibit consistent improvements and robustness under noisy and heterogeneous conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00369
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognition
Cho, Seungyeon
Kim, Tae-kyun
Computer Vision and Pattern Recognition
Skeleton-based human action recognition (HAR) has achieved remarkable progress with graph-based architectures. However, most existing methods remain body-centric, focusing on large-scale motions while neglecting subtle hand articulations that are crucial for fine-grained recognition. This work presents a probabilistic dual-stream framework that unifies reliability modeling and multi-modal integration, generalizing expertized learning under uncertainty across both intra-skeleton and cross-modal domains. The framework comprises three key components: (1) a calibration-free preprocessing pipeline that removes canonical-space transformations and learns directly from native coordinates; (2) a probabilistic Noisy-OR fusion that stabilizes reliability-aware dual-stream learning without requiring explicit confidence supervision; and (3) an intra- to cross-modal ensemble that couples four skeleton modalities (Joint, Bone, Joint Motion, and Bone Motion) to RGB representations, bridging structural and visual motion cues in a unified cross-modal formulation. Comprehensive evaluations across multiple benchmarks (NTU RGB+D~60/120, PKU-MMD, N-UCLA) and a newly defined hand-centric benchmark exhibit consistent improvements and robustness under noisy and heterogeneous conditions.
title BHaRNet: Reliability-Aware Body-Hand Modality Expertized Networks for Fine-grained Skeleton Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.00369