TL;DR
HPCLR is a hierarchical part-aware contrastive learning framework for skeleton-based action recognition that leverages the consistency among joint, motion, and bone modalities to select more reliable positive samples, thereby contributing to more stable and informative multi-stream skeleton representations.
This work presents a novel self-supervised architecture centered on graph prototype learning that sets a new state-of-the-art on the ARMM dataset with an accuracy of 95.70%, substantiating the efficacy and transferability of prototype-guided self-supervised learning for skeleton-based action representation.
This work proposes MEMC (Masked Modeling with Efficient and Minimal Contrastive Learning), a novel framework that adopts an efficient sequential cascade strategy based on layer-grafted pretraining and introduces two CL enhancements to improve the discriminative capability of the learned representations.
FineX is introduced, which factorizes fine-grained cues into RGB appearance, pose heatmap geometry, and skeletal-graph topology and raises mean class accuracy on Gym99, Gym288, and Diving48 without textual supervision or large-scale vision-language pre-training.
Multimodal human activity recognition (HAR) benefits from complementary skeleton, inertial, and visual observations. However, many learning-based models still treat relationships among modalities, joints, and sensor variables as symmetric associations. This limits their ability to represent asymmetric information flow and can weaken the preservation of modality-specific cues during feature fusion. We propose Causality-Inspired Structure Representation Learning (CSRL), a multimodal HAR framework that uses directional dependency modeling as a structural prior for representation learning. CSRL first estimates transfer-entropy-based graphs from temporal entities, including skeleton joints and IMU sensor variables. These graphs provide asymmetric priors that guide recognition-oriented graph learning in the representation space. CSRL further combines hybrid contrastive learning with an encoder-decoder architecture to learn modality-invariant, modality-specific, and structure-aware representations in a unified framework. This design encourages cross-modal alignment while retaining local motion cues that are important for fine-grained action discrimination. Experiments on five public HAR benchmarks, including UTD-MHAD, MMAct, CZU-MHAD, NTU RGB+D, and NTU RGB+D 120, show that CSRL consistently improves accuracy, F1 score, and recall over competitive supervised and contrastive baselines. These results support TE-guided directional structure modeling as a practical and interpretable prior for multimodal action recognition.
A novel and effective representation is presented that captures action-related information in the pipeline of HAR without any extra annotation overhead beyond the existing skeleton extraction and achieves significantly higher HAR accuracy with similar compactness and efficiency as compared with the state-of-the-art skeleton-only approaches.
Skeleton-based action recognition via graph convolutional networks (GCNs) has achieved remarkable progress, yet two persistent bottlenecks limit practical deployment: (1) systematic confusion among fine-grained actions that differ primarily in hand or finger movements, which the standard 25-joint skeleton cannot disambiguate; and (2) training instability under small batch sizes caused by BatchNorm (BN) running-statistics pollution, leading to catastrophic accuracy drops during training. In this paper, we propose BPA-STGCN (Body-Part-Aware STGCN), which addresses both challenges through an integrated framework of architectural and training innovations. First, a Partition Attention (PA) module adapting the Squeeze-and-Excitation concept to anatomically defined joint groups that decomposes the 25-joint skeleton into four anatomical partitions and learns sample-specific importance weights for each partition, enabling the model to focus on the most discriminative body region for each action. Then, the information losing global average pooling is replaced by a Temporal Pyramid Pooling (TPP) module adapting the temporal-segment and pyramid-pooling concepts to skeleton feature maps that captures multi-scale temporal dynamics through segmented pooling. Moreover, we design a stability-first training protocol comprising low-momentum BN, Mixup augmentation, gradient clipping, and extended warmup. The experiments are performed on the NTU RGB+D 60 and NTU RGB+D 120 dataset, and BPA-STGCN achieves 93.7% and 90.9% accuracy. Comprehensive ablation studies reveal that the architectural innovations and the stability protocol contribute complementarily, and that BPA-STGCN achieves the best accuracy–stability trade-off among all tested configurations.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
