Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition

• URL: http://arxiv.org/abs/2503.14960v2
• Date: Fri, 21 Mar 2025 20:54:33 GMT
• Title: Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition
• Authors: Seungyeon Cho, Tae-Kyun Kim,
• Abstract summary: BHaRNet is a novel framework that augments a typical body-expert model with a hand-expert model.<n>Our model jointly trains both streams with an ensemble loss that fosters cooperative specialization.<n>Inspired by MMNet, we also demonstrate the applicability of our approach to multi-modal tasks by leveraging RGB information.
• Score: 28.174638880324014
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Skeleton-based Human Action Recognition (HAR) is a vital technology in robotics and human-robot interaction. However, most existing methods concentrate primarily on full-body movements and often overlook subtle hand motions that are critical for distinguishing fine-grained actions. Recent work leverages a unified graph representation that combines body, hand, and foot keypoints to capture detailed body dynamics. Yet, these models often blur fine hand details due to the disparity between body and hand action characteristics and the loss of subtle features during the spatial-pooling. In this paper, we propose BHaRNet (Body-Hand action Recognition Network), a novel framework that augments a typical body-expert model with a hand-expert model. Our model jointly trains both streams with an ensemble loss that fosters cooperative specialization, functioning in a manner reminiscent of a Mixture-of-Experts (MoE). Moreover, cross-attention is employed via an expertized branch method and a pooling-attention module to enable feature-level interactions and selectively fuse complementary information. Inspired by MMNet, we also demonstrate the applicability of our approach to multi-modal tasks by leveraging RGB information, where body features guide RGB learning to capture richer contextual cues. Experiments on large-scale benchmarks (NTU RGB+D 60, NTU RGB+D 120, PKU-MMD, and Northwestern-UCLA) demonstrate that BHaRNet achieves SOTA accuracies -- improving from 86.4\% to 93.0\% in hand-intensive actions -- while maintaining fewer GFLOPs and parameters than the relevant unified methods.

Related papers

• Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter [32.64004722423187]
  We show how to improve the robustness of RGB-skeleton action recognition models. We propose the formatwordAttention-based formatwordModality formatwordReweighter (formatwordAMR) Our AMR is plug-and-play, allowing easy integration with multimodal models.
  arXiv  Detail & Related papers  (2024-07-29T13:15:51Z)
• MARS: Multimodal Active Robotic Sensing for Articulated Characterization [6.69660410213287]
  We introduce MARS, a novel framework for articulated object characterization. It features a multi-modal fusion module utilizing multi-scale RGB features to enhance point cloud features. Our method effectively generalizes to real-world articulated objects, enhancing robot interactions.
  arXiv  Detail & Related papers  (2024-07-01T11:32:39Z)
• An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition [49.45660055499103]
  Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training. Previous research has focused on aligning sequences' visual and semantic spatial distributions. We introduce a new loss function sampling method to obtain a tight and robust representation.
  arXiv  Detail & Related papers  (2024-06-02T06:53:01Z)
• Egocentric RGB+Depth Action Recognition in Industry-Like Settings [50.38638300332429]
  Our work focuses on recognizing actions from egocentric RGB and Depth modalities in an industry-like environment. Our framework is based on the 3D Video SWIN Transformer to encode both RGB and Depth modalities effectively. Our method also secured first place at the multimodal action recognition challenge at ICIAP 2023.
  arXiv  Detail & Related papers  (2023-09-25T08:56:22Z)
• Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition [32.07659338674024]
  Graph convolutional networks (GCNs) can model the human body skeletons as spatial and temporal graphs. In this work, we propose pose-guided GCN (PG-GCN), a multi-modal framework for high-performance human action recognition. The core idea of this module is to utilize a trainable graph to aggregate features from the skeleton stream with that of the pose stream, which leads to a network with more robust feature representation ability.
  arXiv  Detail & Related papers  (2022-10-10T02:08:49Z)
• SpatioTemporal Focus for Skeleton-based Action Recognition [66.8571926307011]
  Graph convolutional networks (GCNs) are widely adopted in skeleton-based action recognition. We argue that the performance of recent proposed skeleton-based action recognition methods is limited by the following factors. Inspired by the recent attention mechanism, we propose a multi-grain contextual focus module, termed MCF, to capture the action associated relation information.
  arXiv  Detail & Related papers  (2022-03-31T02:45:24Z)
• Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition [65.78703941973183]
  We propose a novel correlation-driven joint-bone fusion graph convolutional network (CD-JBF-GCN) as an encoder and use a pose prediction head as a decoder. Specifically, the CD-JBF-GC can explore the motion transmission between the joint stream and the bone stream. The pose prediction based auto-encoder in the self-supervised training stage allows the network to learn motion representation from unlabeled data.
  arXiv  Detail & Related papers  (2022-02-08T16:03:15Z)
• Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition [49.163326827954656]
  We propose a novel multi-granular-temporal graph network for skeleton-based action classification. We develop a dual-head graph network consisting of two inter-leaved branches, which enables us to extract at least two-temporal resolutions. We conduct extensive experiments on three large-scale datasets.
  arXiv  Detail & Related papers  (2021-08-10T09:25:07Z)
• Pose And Joint-Aware Action Recognition [87.4780883700755]
  We present a new model for joint-based action recognition, which first extracts motion features from each joint separately through a shared motion encoder. Our joint selector module re-weights the joint information to select the most discriminative joints for the task. We show large improvements over the current state-of-the-art joint-based approaches on JHMDB, HMDB, Charades, AVA action recognition datasets.
  arXiv  Detail & Related papers  (2020-10-16T04:43:34Z)
• Skeleton Focused Human Activity Recognition in RGB Video [11.521107108725188]
  We propose a multimodal feature fusion model that utilizes both skeleton and RGB modalities to infer human activity. The model could be either individually or uniformly trained by the back-propagation algorithm in an end-to-end manner.
  arXiv  Detail & Related papers  (2020-04-29T06:40:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.