mlsanityData to 14 Oct 2026

Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding

arXiv 2608.30279 ↗First posted 31 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Point cloud video representation learning is crucial for 3D dynamic scene understanding. In this paper, we propose MoSaiC, a novel Motion-Saliency Complementary masked modeling framework for self-supervised point cloud video representation learning. MoSaiC couples three components: Curriculum Motion-Saliency Masking (CMSM), which guides the masking process toward motion-salient tokens under a curriculum schedule; Normal-Flow Motion (NFM) modeling, which supervises the local rigid rotation of each token in the Lie algebra so(3) as an explicit geometric motion target; and Cross-view Token Consistency Prediction (CTCP), which enforces consistency between two complementary masked views at the token level. Together, these components allow MoSaiC to effectively capture both appearance and motion dynamics. Extensive experiments on multiple downstream tasks, including action recognition, temporal action segmentation, and point-level semantic segmentation, demonstrate the effectiveness of our approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

31 of 43 references.

References · 31

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  6. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  7. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  8. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  9. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  10. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 327
  11. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  12. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
19 more
  1. 2019MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequencescited by 117
  2. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  3. 2022Point Primitive Transformer for Long-Term 4D Point Cloud Video Understandingcited by 35
  4. 2022Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learningcited by 30
  5. 2022No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfacescited by 25
  6. 2023PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videoscited by 22
  7. 2026Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoringcited by 21
  8. 2023Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videoscited by 19
  9. 2026PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoningcited by 19
  10. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 18
  11. 2025PointDico: Contrastive 3D Representation Learning Guided by Diffusion Modelscited by 11
  12. 2026PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learningcited by 10
  13. 2026CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registrationcited by 9
  14. 2026Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Modelscited by 6
  15. 2026Diffusion Masked Pretraining for Dynamic Point Cloudcited by 6
  16. 2026Tri-Efficient Transfer Learning for Point Cloud Videoscited by 6
  17. 2026Parameter-Efficient Fine-Tuning for Spiking Point Cloud Modelscited by 3
  18. 2026GaussFusion: Towards Multimodal 3D Gaussian Pretrainingcited by 2
  19. 2026SpikingMOT: A Spike-Driven Multi-Object Trackercited by 2

Built on by

Not cited yet.