| Paper | Code | mAP | ModelName | ReleaseDate |
|---|---|---|---|---|
| Improving Token-based Object Detection with Video | 91.14 | P2S-VID | 2025-06-27 | |
| Video Sparse Transformer With Attention-Guided Memory for Video Object Detection | ✓ Link | 90.39 | VSTAM | 2022-06-17 |
| Improving Token-based Object Detection with Video | 88.62 | P2S | 2025-06-27 | |
| FFAVOD: Feature Fusion Architecture for Video Object Detection | ✓ Link | 88.10 | FFAVOD-SpotNet with U-Net | 2021-09-15 |
| SpotNet: Self-Attention Multi-Task Network for Object Detection | ✓ Link | 86.8 | SpotNet | 2020-02-13 |
| Objects as Points | ✓ Link | 83.48 | CenterNet | 2019-04-16 |
| RN-VID: A Feature Fusion Architecture for Video Object Detection | ✓ Link | 70.57 | RN-VID | 2020-03-24 |
| R-FCN: Object Detection via Region-based Fully Convolutional Networks | ✓ Link | 69.87 | R-FCN | 2016-05-20 |
| Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | ✓ Link | 58.45 | Faster R-CNN | 2015-06-04 |
| YOLO9000: Better, Faster, Stronger | ✓ Link | 57.72 | YOLOv2 | 2016-12-25 |
| 3D-DETNet: a Single Stage Video-Based Vehicle Detector | 53.30 | 3D-DETNet | 2018-01-05 |