paper-with-me

Papers

PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences

2022-05-27 · ICLR 2021 1 · Hehe Fan, Xin Yu, Yuhang Ding, Yi Yang, Mohan Kankanhalli

Point cloud sequences are irregular and unordered in the spatial dimension while exhibiting regularities and order in the temporal dimension. Therefore, existing grid based convolutions for conventional video processing cannot be directly applied to spatio-temporal modeling of raw point cloud sequences. In this paper, we propose a point spatio-temporal (PST) convolution to achieve informative representations of point cloud sequences. The proposed PST convolution first disentangles space and time in point cloud sequences. Then, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension. Furthermore, we incorporate the proposed PST convolution into a deep network, namely PSTNet, to extract features of point cloud sequences in a hierarchical manner. Extensive experiments on widely-used 3D action recognition and 4D semantic segmentation datasets demonstrate the effectiveness of PSTNet to model point cloud sequences.

📄 PDF Abstract BibTeX arXiv:2205.13713

Code (1)

hehefan/Point-Spatio-Temporal-Convolution 공식 구현 pytorch

Tasks

3D Action RecognitionAction RecognitionSemantic Segmentation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learning

2025-04-23 · Fengchun Liu, Tong Zhang, Chunying Zhang

In recent years, a large number of works have introduced Convolutional Neural Networks (CNNs) into image steganography, which transform traditional steganography methods such as hand-crafted features and prior knowledge …

Image SteganographySSIMSteganalysis

Anchor-Based Spatio-Temporal Attention 3D Convolutional Networks for Dynamic 3D Point Cloud Sequences

2020-12-20 · Guangming Wang, Muyao Chen, Hanwen Liu, Yehui Yang 외

With the rapid development of measurement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, …

Action RecognitionAutonomous DrivingSemantic Segmentation

STARK: Spatio-Temporal Attention for Representation of Keypoints for Continuous Sign Language Recognition

2026-03-17 · Suvajit Patra, Soumitra Samanta arxiv

Continuous Sign Language Recognition (CSLR) is a crucial task for understanding the languages of deaf communities. Contemporary keypoint-based approaches typically rely on spatio-temporal encoding, where spatial interact…

Sign Language Recognition

VG4D: Vision-Language Model Goes 4D Video Recognition

2024-04-17 · Zhichao Deng, Xiangtai Li, Xia Li, Yunhai Tong 외

Understanding the real world through point cloud video is a crucial aspect of robotics and autonomous driving systems. However, prevailing methods for 4D point cloud recognition have limitations due to sensor resolution,…

Action RecognitionAutonomous DrivingLanguage ModelingLanguage Modelling+2

Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data

2018-04-24 · Joshua Owoyemi, Koichi Hashimoto

In this paper, we demonstrate an end-to-end spatiotemporal gesture learning approach for 3D point cloud data using a new gestures dataset of point clouds acquired from a 3D sensor. Nine classes of gestures were learned f…

Data AugmentationScene Understanding