| DL | Deep Learning |
| CNN | Convolutional Neural Network |
| 3DOR | 3D Object Recognition |
| 3DPR | 3D Place Recognition |
| RoI | Region of Interest |
| R-CNN | Region-based Convolutional Neural Network |
| SSD | Single Shot MultiBox Detector |
| YOLO | You Only Look Once |
| PC | Point Cloud |
| AVOD | Aggregate View Object Detection |
| PG-Net | Proposal Generation network |
| PE-Net | Parameter Estimation network (PE-Net) |
| KITTI | Karlsruhe Institute of Technology and Toyota Technological Institute |
| HKUST | Hong Kong University of Science and Technology |
| KAIST | Korea Advanced Institute of Science and Technology |
| NYUD2 | New York University Dataset version 2 |
| NCLT | The University of Michigan North Campus Long-Term Vision |
| DDD17 | DAVIS Driving Dataset 2017 |
| sGD | Stochastic Gradient Descent |
| BBox | Bounding Box |
| ADV | Autonomous Driving Vehicle |
| GS3D | 3D Guidance and using the Surface feature |
| SS3D | Single-Stage Monocular 3D |
| M3DSSD | Monocular 3D Single Stage object Detector |
| SRCNN | Stereo Recurrent Convolutional Neural Network |
| NMS | Non-Maximum Suppression |
| FV | Front-View |
| BEV | Bird’s-Eye View |
| SegVNet | Segmentation-based Voxel Network |
| VFE | Voxel Feature Encoder |
| LidarMTL | Lidar-based multi-task learning network |
| IPOD | Intensive Point-based Object Detector for Point Cloud |
| FVNet | Front-View proposal generation Network |
| DPointNet | Density-oriented Point Network |
| GCNN | Graph Convolutional Neural Network |
| RGNet | Relation Graph Network |
| HGNet | Hierarchical Graph Network |
| S-AT GCN | Spatial Attention Graph Convolution |
| MV3D | Multi-view 3D Network |
| MS-CNN | Multi Scale Convolutional Neural Network |
| S-AT | Spatial-Attention |
| BEVLFVC | Bird’s Eye View LIDAR point cloud and Front View Camera image |
| MVX-Net | Multimodal Voxelnet for 3d object detection |
| NetVLAD | Network for Vector of Locally Aggregated Descriptors |
| DGCNN | Dynamic graph Convolutional Neural Network |
| AUC | Area Under Curve |
| AP | Average Precision |
| LPD-Net | Large-scale Place Description |