mlsanityData to 7 Oct 2026

Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding

arXiv 2208.00281 ↗First posted 30 Jul 2022cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

This paper proposes a 4D backbone for long-term point cloud video understanding. A typical way to capture spatial-temporal context is using 4Dconv or transformer without hierarchy. However, those methods are neither effective nor efficient enough due to camera motion, scene changes, sampling patterns, and the complexity of 4D data. To address those issues, we leverage the primitive plane as a mid-level representation to capture the long-term spatial-temporal context in 4D point cloud videos and propose a novel hierarchical backbone named Point Primitive Transformer(PPTr), which is mainly composed of intra-primitive point transformers and primitive transformers. Extensive experiments show that PPTr outperforms the previous state of the arts on different tasks.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 30 Jul 2022.

Builds on

31 of 44 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2016Layer Normalizationcited by 5,579
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2021ViViT: A Video Vision Transformercited by 1,610
19 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
  3. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  4. 2020PCT: Point cloud transformercited by 730
  5. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  6. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  7. 2017Submanifold Sparse Convolutional Networkscited by 223
  8. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  9. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  10. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  11. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 90
  12. 20173D-PRNN: Generating Shape Primitives with Recurrent Neural Networkscited by 77
  13. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  14. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  15. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 50
  16. 20203DV: 3D Dynamic Voxel for Action Recognition in Depth Videocited by 41
  17. 2021HPNet: Deep Primitive Segmentation Using Hybrid Representationscited by 35
  18. 2015Rank Pooling for Action Recognitioncited by 29
  19. 2018Parsing Geometry Using Structure-Aware Shape Templatescited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 7; 2025: 6; 2026: 10.

35 papers.

Sort:

By area:

  1. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  2. 2023An Outlook into the Future of Egocentric Visioncited by 84
  3. 2022Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learningcited by 30
  4. 2023Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecastingcited by 27
  5. 2023PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videoscited by 22
  6. 2023Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videoscited by 19
  7. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 17
  8. 2023Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videoscited by 16
  9. 2024GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitationcited by 14
  10. 2023X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-modal Knowledge Transfercited by 12
  11. 2024VG4D: Vision-Language Model Goes 4D Video Recognitioncited by 11
  12. 2024MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Modelscited by 11
23 more
  1. 2023Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequencecited by 6
  2. 2024CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understandingcited by 6
  3. 2026Diffusion Masked Pretraining for Dynamic Point Cloudcited by 6
  4. 2023Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learningcited by 5
  5. 2023NSM4D: Neural Scene Model Based Online 4D Point Cloud Sequence Understandingcited by 5
  6. 2026Tri-Efficient Transfer Learning for Point Cloud Videoscited by 5
  7. 2024A Unified Framework for Human-centric Point Cloud Video Understandingcited by 3
  8. 2025Uni4D: A Unified Self-Supervised Learning Framework for Point Cloud Videoscited by 3
  9. 2023DPMix: Mixture of Depth and Point Cloud Video Experts for 4D Action Segmentationcited by 2
  10. 2024SPiKE: 3D Human Pose from Point Cloud Sequencescited by 2
  11. 2025Content-Distortion High-Order Interaction for Blind Image Quality Assessmentcited by 2
  12. 2023Point Cloud Video Anomaly Detection Based on Point Spatio-Temporal Auto-Encodercited by 1
  13. 2025Quality assessment of 3D human animation: Subjective and objective evaluationcited by 1
  14. 2025DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understandingcited by 1
  15. 2025PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applicationscited by 1
  16. 2026STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understandingcited by 1
  17. 2026SRENet: Spectral Re-Entry Network for Point Cloud Action Recognitioncited by 1
  18. 2026Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learningcited by 1
  19. 20254DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threadscited by 0
  20. 2026GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representationcited by 0
  21. 2026Paving the Way for Point Cloud Video Representation Learning Using A PDE Modelcited by 0
  22. 2026Joint-Embedding Prediction of Masked Point Tubes for Self-Supervised Learning on 4D Point Cloud Videoscited by 0
  23. 2026Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understandingcited by 0