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

07/30/2022
by   Hao Wen, et al.
0

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

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/19/2021

Spatial-Temporal Transformer for 3D Point Cloud Sequences

Effective learning of spatial-temporal information within a point cloud ...
research
09/01/2022

MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition

Recognizing human actions from point cloud videos has attracted tremendo...
research
08/18/2023

Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos

Recently, the community has made tremendous progress in developing effec...
research
04/04/2022

TALLFormer: Temporal Action Localization with Long-memory Transformer

Most modern approaches in temporal action localization divide this probl...
research
01/09/2023

End-to-end Unsupervised Learning of Long-Term 3D Stable objects

3D point cloud semantic classification is an important task in robotics ...
research
10/23/2022

LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers

Transformer with its underlying attention mechanism and the ability to c...
research
06/13/2023

E2E-LOAD: End-to-End Long-form Online Action Detection

Recently, there has been a growing trend toward feature-based approaches...

Please sign up or login with your details

Forgot password? Click here to reset