DistillH-Mamba: A Hypergraph-Mamba-Based Knowledge Distillation Model for Efficient Impact Fall Detection

• URL: http://arxiv.org/abs/2607.03156v1
• Date: Fri, 03 Jul 2026 09:56:57 GMT
• Title: DistillH-Mamba: A Hypergraph-Mamba-Based Knowledge Distillation Model for Efficient Impact Fall Detection
• Abstract summary: Falls among the elderly represent a significant public health concern due to their prevalence, consequences, and societal burden.<n>We propose DistillH-Mamba, a novel architecture for impact fall detection that addresses these challenges through three key innovations.<n>First, we introduce a hypergraph-based approach that captures higher-order relationships between multiple joints simultaneously.<n>Second, we integrate the Mamba architecture with hypergraphs for impact detection, significantly accelerating processing speed.<n>Third, we employ relational knowledge distillation that preserves crucial spatial-temporal relationships while reducing computational demands for real-time impact fall detection.
• Score: 1.1654568410166084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Falls among the elderly represent a significant public health concern due to their prevalence, consequences, and societal burden. While deep learning has improved fall detection, accurately identifying impact moments (when an individual hits the ground) remains challenging. Additionally, current algorithms often rely on complex models with high computational demands, limiting real-time deployment feasibility. In this work, we propose DistillH-Mamba, a novel architecture for impact fall detection that addresses these challenges through three key innovations: First, we introduce a hypergraph-based approach that captures higher-order relationships between multiple joints simultaneously, enabling more accurate modeling of complex interactions during impact falls. Second, we integrate the Mamba architecture with hypergraphs for impact detection, significantly accelerating processing speed while efficiently capturing both long-term dependencies and sudden skeletal motion changes. Third, we employ relational knowledge distillation that preserves crucial spatial-temporal relationships while reducing computational demands for real-time impact fall detection. Evaluated on the 3D Skeletons UP-Fall and UMAFall datasets, our DistillH-Mamba model achieves 97.38% accuracy in detecting impact within fall events and 73.8% reduction in inference time compared to its teacher model, outperforming state-of-the-art methods in both precision and efficiency.

Related papers

• FLASH: Efficient Impact Fall Detection with Unified Hypergraph State-Space Model [1.2731778729620478]
  Existing methods rely on graph neural networks modeling only pairwise joint connections.<n>We propose FLASH, a novel framework integrating single-matrix hypergraph representations with Mamba's selective state-space models.<n>Experiments on UP-Fall and UMAFall datasets demonstrate that FLASH achieves state-of-the-art accuracy with real-time inference capability.
  arXiv  Detail & Related papers  (2026-07-28T14:43:07Z)
• Impact Detection in Fall Events: Leveraging Spatio-Temporal Graph Convolutional Networks and Recurrent Neural Networks Using 3D Skeletons Data [1.1654568410166084]
  Fall represents a significant risk of accidental death among individuals aged over 65, presenting a global health concern.<n>This study proposes an efficient methodology for accurately detecting impacts within fall events by incorporating 3D joints skeleton data treated as a graph.<n>Our approach enhances precision by distinguishing between false falls and actual impacts, contributing to better healthcare resource allocation.
  arXiv  Detail & Related papers  (2026-07-28T13:33:57Z)
• Mask2Cause: Causal Discovery via Adjacency Constrained Causal Attention [0.13764085113103217]
  We propose an end-to-end framework that recovers the underlying causal graph directly during the forecasting forward pass.<n>We show that inferred causal structures can be used to reduce parameter count of forecasting models by more than 70% on average.
  arXiv  Detail & Related papers  (2026-05-08T05:43:47Z)
• Modeling Human Skeleton Joint Dynamics for Fall Detection [25.57448683000322]
  Fall detection from video streams is not an attractive option for real-life applications due to privacy issues.<n>Key points on the body such as skeleton joints, can convey significant information about motion dynamics.<n>We propose an efficient graph convolution network model that exploitstemporal joint dependencies and dynamics of human skeleton joints for accurate fall detection.
  arXiv  Detail & Related papers  (2025-03-10T05:35:56Z)
• Computer-Aided Fall Recognition Using a Three-Stream Spatial-Temporal GCN Model with Adaptive Feature Aggregation [0.5235143203977018]
  Prevention of falls is paramount in modern healthcare, particularly for the elderly. A computer-aided fall detection system is inevitable to save elderly people's lives worldwide. This paper proposes a novel three-stream spatial-temporal feature-based fall detection system.
  arXiv  Detail & Related papers  (2024-08-22T08:40:04Z)
• Accommodating Missing Modalities in Time-Continuous Multimodal Emotion Recognition [0.0]
  We propose a novel Transformer-based architecture for recognizing valence and arousal in a time-continuous manner. We use a coupling of cross-attention and self-attention mechanisms to emphasize relationships between modalities during time.
  arXiv  Detail & Related papers  (2023-11-16T09:22:48Z)
• On the Importance of Spatial Relations for Few-shot Action Recognition [109.2312001355221]
  In this paper, we investigate the importance of spatial relations and propose a more accurate few-shot action recognition method. A novel Spatial Alignment Cross Transformer (SA-CT) learns to re-adjust the spatial relations and incorporates the temporal information. Experiments reveal that, even without using any temporal information, the performance of SA-CT is comparable to temporal based methods on 3/4 benchmarks.
  arXiv  Detail & Related papers  (2023-08-14T12:58:02Z)
• Automatic diagnosis of knee osteoarthritis severity using Swin transformer [55.01037422579516]
  Knee osteoarthritis (KOA) is a widespread condition that can cause chronic pain and stiffness in the knee joint. We propose an automated approach that employs the Swin Transformer to predict the severity of KOA.
  arXiv  Detail & Related papers  (2023-07-10T09:49:30Z)
• Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation [106.42167050921718]
  We propose a very fast frame-level model for anomaly detection in video. It learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. Our model achieves the best trade-off between speed and accuracy, due to its previously unheard-of speed of 1480 FPS.
  arXiv  Detail & Related papers  (2022-11-28T17:50:19Z)
• Temporal Relevance Analysis for Video Action Models [70.39411261685963]
  We first propose a new approach to quantify the temporal relationships between frames captured by CNN-based action models. We then conduct comprehensive experiments and in-depth analysis to provide a better understanding of how temporal modeling is affected.
  arXiv  Detail & Related papers  (2022-04-25T19:06:48Z)
• An Enhanced Adversarial Network with Combined Latent Features for Spatio-Temporal Facial Affect Estimation in the Wild [1.3007851628964147]
  This paper proposes a novel model that efficiently extracts both spatial and temporal features of the data by means of its enhanced temporal modelling based on latent features. Our proposed model consists of three major networks, coined Generator, Discriminator, and Combiner, which are trained in an adversarial setting combined with curriculum learning to enable our adaptive attention modules.
  arXiv  Detail & Related papers  (2021-02-18T04:10:12Z)
• Consistency Guided Scene Flow Estimation [159.24395181068218]
  CGSF is a self-supervised framework for the joint reconstruction of 3D scene structure and motion from stereo video. We show that the proposed model can reliably predict disparity and scene flow in challenging imagery. It achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.
  arXiv  Detail & Related papers  (2020-06-19T17:28:07Z)
• Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition [133.35968094967626]
  Skeleton-based action recognition has attracted increasing attention due to its strong adaptability to dynamic circumstances. With the help of deep learning techniques, it has also witnessed substantial progress and currently achieved around 90% accuracy in benign environment. Research on the vulnerability of skeleton-based action recognition under different adversarial settings remains scant.
  arXiv  Detail & Related papers  (2020-05-14T17:12:52Z)
• Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition [56.844587127848854]
  We demonstrate that the state-of-the-art gait recognition model is vulnerable to such attacks. We employ a generative adversarial network based architecture to semantically generate adversarial high-quality gait silhouettes or video frames. The experimental results show that if only one-fortieth of the frames are attacked, the accuracy of the target model drops dramatically.
  arXiv  Detail & Related papers  (2020-02-22T10:08:42Z)

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.