mlsanityData to 14 Oct 2026

KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition

arXiv 2409.09444 ↗First posted 14 Sep 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Point cloud sequence-based 3D action recognition has achieved impressive performance and efficiency. However, existing point cloud sequence modeling methods cannot adequately balance the precision of limb micro-movements with the integrity of posture macro-structure, leading to the loss of crucial information cues in action inference. To overcome this limitation, we introduce D-Hyperpoint, a novel data type generated through a D-Hyperpoint Embedding module. D-Hyperpoint encapsulates both regional-momentary motion and global-static posture, effectively summarizing the unit human action at each moment. In addition, we present a D-Hyperpoint KANsMixer module, which is recursively applied to nested groupings of D-Hyperpoints to learn the action discrimination information and creatively integrates Kolmogorov-Arnold Networks (KAN) to enhance spatio-temporal interaction within D-Hyperpoints. Finally, we propose KAN-HyperpointNet, a spatio-temporal decoupled network architecture for 3D action recognition. Extensive experiments on two public datasets: MSR Action3D and NTU-RGB+D 60, demonstrate the state-of-the-art performance of our method.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 14 Sep 2024.

Builds on

28 of 38 references.

References · 28

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  6. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  7. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  8. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  9. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  10. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 118
  11. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  12. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 49
16 more
  1. 20203DV: 3D Dynamic Voxel for Action Recognition in Depth Videocited by 41
  2. 2022Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentationscited by 31
  3. 2018Learning with privileged information via adversarial discriminative modality distillationcited by 30
  4. 2022Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learningcited by 30
  5. 2023Part Aware Contrastive Learning for Self-Supervised Action Recognitioncited by 21
  6. 2021ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpointscited by 20
  7. 2023Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videoscited by 19
  8. 2018Action Recognition for Depth Video using Multi-view Dynamic Imagescited by 18
  9. 2021Recognizing Actions in Videos from Unseen Viewpointscited by 18
  10. 2023Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videoscited by 16
  11. 20203DFCNN: Real-Time Action Recognition using 3D Deep Neural Networks with Raw Depth Informationcited by 13
  12. 2024MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Modelscited by 11
  13. 20233DInAction: Understanding Human Actions in 3D Point Cloudscited by 10
  14. 2021Real-time 3D human action recognition based on Hyperpoint sequencecited by 9
  15. 2020Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networkscited by 8
  16. 2023Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awarenesscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understandingcited by 1
  2. 2026SRENet: Spectral Re-Entry Network for Point Cloud Action Recognitioncited by 1
  3. 2026Paving the Way for Point Cloud Video Representation Learning Using A PDE Modelcited by 0