paper-with-me

Papers

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, Zhe Liu, Hesheng Wang

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, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets.

📄 PDF Abstract BibTeX arXiv:2012.10860

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionAutonomous DrivingSemantic Segmentation

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
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…
3D Convolution A 3D Convolution is a type of convolution where the kernel slides in 3 dimensions as opposed to 2 dimensions with 2D…

Similar Papers 제목 키워드 기반

AdaAnchor4D: Anchor-Conditioned Spatiotemporal Feature Aggregation for Monocular UAV 4D Reconstruction

2026-07-30 · Peiyi Xu, Junpeng Zhang, Guanbin Li, Ronghua Shang 외 arxiv

Monocular UAV videos provide valuable observations for dynamic reconstruction of complex urban scenes. However, such scenes exhibit pronounced spatiotemporal heterogeneity: different regions follow distinct temporal acti…

Dynamic Reconstruction

ESGCN: Edge Squeeze Attention Graph Convolutional Network for Traffic Flow Forecasting

2023-07-03 · Sangrok Lee, Ha Young Kim

Traffic forecasting is a highly challenging task owing to the dynamical spatio-temporal dependencies of traffic flows. To handle this, we focus on modeling the spatio-temporal dynamics and propose a network termed Edge S…

Time Series

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

Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition

2021-09-07 · Ruwen Bai, Min Li, Bo Meng, Fengfa Li 외

Graph convolutional networks (GCNs) have emerged as dominant methods for skeleton-based action recognition. However, they still suffer from two problems, namely, neighborhood constraints and entangled spatiotemporal feat…

Action RecognitionDisentanglementSkeleton Based Action Recognition

ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capture

2025-07-09 · Mingjin Zeng, Nan Ouyang, Wenkang Wan, Lei Ao 외

Trajectory prediction for multi-agent interaction scenarios is a crucial challenge. Most advanced methods model agent interactions by efficiently factorized attention based on the temporal and agent axes. However, this s…

Motion ForecastingTrajectory Prediction