mlsanityData to 7 Oct 2026

3DInAction: Understanding Human Actions in 3D Point Clouds

arXiv 2303.06346 ↗First posted 11 Mar 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose a novel method for 3D point cloud action recognition. Understanding human actions in RGB videos has been widely studied in recent years, however, its 3D point cloud counterpart remains under-explored. This is mostly due to the inherent limitation of the point cloud data modality -- lack of structure, permutation invariance, and varying number of points -- which makes it difficult to learn a spatio-temporal representation. To address this limitation, we propose the 3DinAction pipeline that first estimates patches moving in time (t-patches) as a key building block, alongside a hierarchical architecture that learns an informative spatio-temporal representation. We show that our method achieves improved performance on existing datasets, including DFAUST and IKEA ASM. Code is publicly available at https://github.com/sitzikbs/3dincaction.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 22 of its 41 references that are in the map. First posted on arXiv 11 Mar 2023.

Builds on

22 of 41 references.

References · 22

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2018SlowFast Networks for Video Recognitioncited by 1,862
  7. 2020Point Transformercited by 1,462
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  9. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  10. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  11. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  12. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
10 more
  1. 2017Learning Spatio-Temporal Representation with Pseudo-3D Residual Networkscited by 386
  2. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  3. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  4. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  5. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  6. 2020The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Posecited by 95
  7. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  8. 2021Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learningcited by 58
  9. 20203DV: 3D Dynamic Voxel for Action Recognition in Depth Videocited by 41
  10. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 4.

10 papers.

  1. 2024KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognitioncited by 3
  2. 2025Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videoscited by 3
  3. 2024On Exploring PDE Modeling for Point Cloud Video Representation Learningcited by 2
  4. 2025Content-Distortion High-Order Interaction for Blind Image Quality Assessmentcited by 2
  5. 2023MS-TCRNet: Multi-Stage Temporal Convolutional Recurrent Networks for Action Segmentation Using Sensor-Augmented Kinematicscited by 1
  6. 2026TAG-Head: Time-Aligned Graph Head for Plug-and-Play Fine-grained Action Recognitioncited by 1
  7. 2026SRENet: Spectral Re-Entry Network for Point Cloud Action Recognitioncited by 1
  8. 2025Human Action Recognition from Point Clouds over Timecited by 0
  9. 2026DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognitioncited by 0
  10. 2026Paving the Way for Point Cloud Video Representation Learning Using A PDE Modelcited by 0