| V2V | Vehicle to vehicle |
| AVs | Autonomous vehicles |
| CAVs | Connected autonomous vehicles |
| TS-IFF | Two-stage intermediate-level feature fusion |
| DWLM | Dynamic weight learning mechanism |
| AFSM | Adaptive feature selection module |
| SSD | Single-shot detector |
| FPN | Feature pyramid network |
| VFE | Voxel feature encoding |
| BEV | Bird’s-eye view |
| 3D CNN | 3D convolutional neural network |
| 2D CNN | 2D convolutional neural network |
| DT | Default Towns |
| CC | Culver City |
| GT | Ground truth |
| PI | Pseudo-image |