Hailun Xia

Naichuan Zheng, Hailun Xia, Zepeng Sun et al.

Wearable IMU-based Human Activity Recognition (HAR) relies heavily on Deep Neural Networks (DNNs), which are burdened by immense computational and buffering demands. Their power-hungry floating-point operations and rigid requirement to process complete temporal windows severely cripple battery-constrained edge devices. While Spiking Neural Networks (SNNs) offer extreme event-driven energy efficiency, standard architectures struggle with complex biomechanical topologies and temporal gradient degradation. To bridge this gap, we propose the Physics-Aware Spiking Neural Network (PAS-Net), a fully multiplier-free architecture explicitly tailored for Green HAR. Spatially, an adaptive symmetric topology mixer enforces human-joint physical constraints. Temporally, an $O(1)$-memory causal neuromodulator yields context-aware dynamic threshold neurons, adapting actively to non-stationary movement rhythms. Furthermore, we leverage a temporal spike error objective to unlock a flexible early-exit mechanism for continuous IMU streams. Evaluated across seven diverse datasets, PAS-Net achieves state-of-the-art accuracy while replacing dense operations with sparse 0.1 pJ integer accumulations. Crucially, its confidence-driven early-exit capability drastically reduces dynamic energy consumption by up to 98\%. PAS-Net establishes a robust, ultra-low-power neuromorphic standard for always-on wearable sensing. The source code and pre-trained models are publicly available at https://github.com/zhengnaichuan2022/PAS-Net.git.

Zepeng Sun, Naichuan Zheng, Hailun Xia et al.

Temporal Action Detection (TAD) in untrimmed videos is currently dominated by Transformer-based architectures. While high-performing, their quadratic computational complexity and substantial parameter redundancy limit deployment in resource-constrained environments. In this paper, we propose LiquidTAD, a novel parameter-efficient framework that replaces cumbersome self-attention layers with parallelized ActionLiquid blocks. Unlike traditional Liquid Neural Networks (LNNs) that suffer from sequential execution bottlenecks, LiquidTAD leverages a closed-form continuous-time (CfC) formulation, allowing the model to be reformulated as a parallelizable operator while preserving the intrinsic physical prior of continuous-time dynamics. This architecture captures complex temporal dependencies with $O(N)$ linear complexity and adaptively modulates temporal sensitivity through learned time-constants ($τ$), providing a robust mechanism for handling varying action durations. To the best of our knowledge, this work is the first to introduce a parallelized LNN-based architecture to the TAD domain. Experimental results on the THUMOS-14 dataset demonstrate that LiquidTAD achieves a highly competitive Average mAP of 69.46\% with only 10.82M parameters -- a 63\% reduction compared to the ActionFormer baseline. Further evaluations on ActivityNet-1.3 and Ego4D benchmarks confirm that LiquidTAD achieves an optimal accuracy-efficiency trade-off and exhibits superior robustness to temporal sampling variations, advancing the Pareto frontier of modern TAD frameworks.

Naichuan Zheng, Yuchen Du, Hailun Xia et al.

For multimodal skeleton-based action recognition, Graph Convolutional Networks (GCNs) are effective models. Still, their reliance on floating-point computations leads to high energy consumption, limiting their applicability in battery-powered devices. While energy-efficient, Spiking Neural Networks (SNNs) struggle to model skeleton dynamics, leading to suboptimal solutions. We propose Signal-SGN (Spiking Graph Convolutional Network), which utilizes the temporal dimension of skeleton sequences as the spike time steps and represents features as multi-dimensional discrete stochastic signals for temporal-frequency domain feature extraction. It combines the 1D Spiking Graph Convolution (1D-SGC) module and the Frequency Spiking Convolution (FSC) module to extract features from the skeleton represented as spiking form. Additionally, the Multi-Scale Wavelet Transform Feature Fusion (MWTF) module is proposed to extract dynamic spiking features and capture frequency-specific characteristics, enhancing classification performance. Experiments across three large-scale datasets reveal Signal-SGN exceeding state-of-the-art SNN-based methods in accuracy and computational efficiency while attaining comparable performance with GCN methods and significantly reducing theoretical energy consumption.

Naichuan Zheng, Hailun Xia, Zepeng Sun et al.

Skeleton-based action recognition is crucial for multimedia applications but heavily relies on power-hungry Artificial Neural Networks (ANNs), limiting their deployment on resource-constrained edge devices. Spiking Neural Networks (SNNs) provide an energy-efficient alternative; however, existing spiking models for skeleton data often compromise the intrinsic sparsity of SNNs by resorting to dense matrix aggregations, heavy multimodal fusion modules, or non-sparse frequency domain transformations. Furthermore, they severely suffer from the short-term amnesia of spiking neurons. In this paper, we propose the Spiking State-Space Topology Transformer (S3T-Former), which, to the best of our knowledge, is the first purely spike-driven Transformer architecture specifically designed for energy-efficient skeleton action recognition. Rather than relying on heavy fusion overhead, we formulate a Multi-Stream Anatomical Spiking Embedding (M-ASE) that acts as a generalized kinematic differential operator, elegantly transforming multimodal skeleton features into heterogeneous, highly sparse event streams. To achieve true topological and temporal sparsity, we introduce Lateral Spiking Topology Routing (LSTR) for on-demand conditional spike propagation, and a Spiking State-Space (S3) Engine to systematically capture long-range temporal dynamics without non-sparse spectral workarounds. Extensive experiments on multiple large-scale datasets demonstrate that S3T-Former achieves highly competitive accuracy while theoretically reducing energy consumption compared to classic ANNs, establishing a new state-of-the-art for energy-efficient neuromorphic action recognition.

Zeyu Liang, Hailun Xia, Naichuan Zheng

While human action recognition has witnessed notable achievements, multimodal methods fusing RGB and skeleton modalities still suffer from their inherent heterogeneity and fail to fully exploit the complementary potential between them. In this paper, we propose PAN, the first human-centric graph representation learning framework for multimodal action recognition, in which token embeddings of RGB patches containing human joints are represented as spatiotemporal graphs. The human-centric graph modeling paradigm suppresses the redundancy in RGB frames and aligns well with skeleton-based methods, thus enabling a more effective and semantically coherent fusion of multimodal features. Since the sampling of token embeddings heavily relies on 2D skeletal data, we further propose attention-based post calibration to reduce the dependency on high-quality skeletal data at a minimal cost interms of model performance. To explore the potential of PAN in integrating with skeleton-based methods, we present two variants: PAN-Ensemble, which employs dual-path graph convolution networks followed by late fusion, and PAN-Unified, which performs unified graph representation learning within a single network. On three widely used multimodal action recognition datasets, both PAN-Ensemble and PAN-Unified achieve state-of-the-art (SOTA) performance in their respective settings of multimodal fusion: separate and unified modeling, respectively.

Naichuan Zheng, Hailun Xia

Multimodal human action recognition based on RGB and skeleton data fusion, while effective, is constrained by significant limitations such as high computational complexity, excessive memory consumption, and substantial energy demands, particularly when implemented with Artificial Neural Networks (ANN). These limitations restrict its applicability in resource-constrained scenarios. To address these challenges, we propose a novel Spiking Neural Network (SNN)-driven framework for multimodal human action recognition, utilizing event camera and skeleton data. Our framework is centered on two key innovations: (1) a novel multimodal SNN architecture that employs distinct backbone networks for each modality-an SNN-based Mamba for event camera data and a Spiking Graph Convolutional Network (SGN) for skeleton data-combined with a spiking semantic extraction module to capture deep semantic representations; and (2) a pioneering SNN-based discretized information bottleneck mechanism for modality fusion, which effectively balances the preservation of modality-specific semantics with efficient information compression. To validate our approach, we propose a novel method for constructing a multimodal dataset that integrates event camera and skeleton data, enabling comprehensive evaluation. Extensive experiments demonstrate that our method achieves superior performance in both recognition accuracy and energy efficiency, offering a promising solution for practical applications.

Naichuan Zheng, Hailun Xia, Zeyu Liang et al.

In recent years, multimodal Graph Convolutional Networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. The reliance on high-energy-consuming continuous floating-point operations inherent in GCN-based methods poses significant challenges for deployment in energy-constrained, battery-powered edge devices. To address these limitations, MK-SGN, a Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation, is proposed to leverage the energy efficiency of Spiking Neural Networks (SNNs) for skeleton-based action recognition for the first time. By integrating the energy-saving properties of SNNs with the graph representation capabilities of GCNs, MK-SGN achieves significant reductions in energy consumption while maintaining competitive recognition accuracy. Firstly, we formulate a Spiking Multimodal Fusion (SMF) module to effectively fuse multimodal skeleton data represented as spike-form features. Secondly, we propose the Self-Attention Spiking Graph Convolution (SA-SGC) module and the Spiking Temporal Convolution (STC) module, to capture spatial relationships and temporal dynamics of spike-form features. Finally, we propose an integrated knowledge distillation strategy to transfer information from the multimodal GCN to the SGN, incorporating both intermediate-layer distillation and soft-label distillation to enhance the performance of the SGN. MK-SGN exhibits substantial advantages, surpassing state-of-the-art GCN frameworks in energy efficiency and outperforming state-of-the-art SNN frameworks in recognition accuracy. The proposed method achieves a remarkable reduction in energy consumption, exceeding 98\% compared to conventional GCN-based approaches. This research establishes a robust baseline for developing high-performance, energy-efficient SNN-based models for skeleton-based action recognition

Zeyu Liang, Hailun Xia, Naichuan Zheng et al.

Skeleton-based action recognition has achieved remarkable performance with the development of graph convolutional networks (GCNs). However, most of these methods tend to construct complex topology learning mechanisms while neglecting the inherent symmetry of the human body. Additionally, the use of temporal convolutions with certain fixed receptive fields limits their capacity to effectively capture dependencies in time sequences. To address the issues, we (1) propose a novel Topological Symmetry Enhanced Graph Convolution (TSE-GC) to enable distinct topology learning across different channel partitions while incorporating topological symmetry awareness and (2) construct a Multi-Branch Deformable Temporal Convolution (MBDTC) for skeleton-based action recognition. The proposed TSE-GC emphasizes the inherent symmetry of the human body while enabling efficient learning of dynamic topologies. Meanwhile, the design of MBDTC introduces the concept of deformable modeling, leading to more flexible receptive fields and stronger modeling capacity of temporal dependencies. Combining TSE-GC with MBDTC, our final model, TSE-GCN, achieves competitive performance with fewer parameters compared with state-of-the-art methods on three large datasets, NTU RGB+D, NTU RGB+D 120, and NW-UCLA. On the cross-subject and cross-set evaluations of NTU RGB+D 120, the accuracies of our model reach 90.0\% and 91.1\%, with 1.1M parameters and 1.38 GFLOPS for one stream.

Rui Zhang, Zheng Zhu, Peng Li et al.

Human pose estimation has witnessed a significant advance thanks to the development of deep learning. Recent human pose estimation approaches tend to directly predict the location heatmaps, which causes quantization errors and inevitably deteriorates the performance within the reduced network output. Aim at solving it, we revisit the heatmap-offset aggregation method and propose the Offset-guided Network (OGN) with an intuitive but effective fusion strategy for both two-stages pose estimation and Mask R-CNN. For two-stages pose estimation, a greedy box generation strategy is also proposed to keep more necessary candidates while performing person detection. For mask R-CNN, ratio-consistent is adopted to improve the generalization ability of the network. State-of-the-art results on COCO and PoseTrack dataset verify the effectiveness of our offset-guided pose estimation and tracking.