HPBAFormer: Enhancing 3D Point Cloud Analysis With Hybrid Pooling Set Abstraction and Bypass Cross-Attention Learning
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 14866-14878
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62325602)
- Key Scientific Research Project Plan of Colleges and Universities in Henan Province (26A520039)
- Foundation of the State Key Laboratory of Robotics of China (2022-KF-22-06)
- National Key Research and Development Program project (2024YFB3311600)
- Foundation of Henan Educational Committee (25HASTIT034)
- Natural Science Foundation of Henan (232300421095)
- National Supercomputing Center
This publication has 54 references indexed in Scilit:
- FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection2022
- PCT: Point cloud transformerComputational Visual Media, 2021
- Pillar-Based Object Detection for Autonomous Driving2020
- Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution2020
- H3DNet: 3D Object Detection Using Hybrid Geometric Primitives2020
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection2018
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- 3D ShapeNets: A deep representation for volumetric shapes2015
- SUN RGB-D: A RGB-D scene understanding benchmark suite2015
- Augmented Reality Teaching and Learning2013