Research map / Detection and segmentation / CNN features
Efficient One-Stage Video Object Detection by Exploiting Temporal Consistency
Guanxiong Sun, Yang Hua, Guosheng Hu, Neil Robertson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the location prior network (ablation) | FCOS · ImageNet VID val | AP: 49.8 -> 54.1 | Improved |
| add the location prior network (ablation) | CenterNet · ImageNet VID val | AP: 49.3 -> 53.4 | Improved |
| add the location prior network (ablation) | YOLOX-M · ImageNet VID val | AP: 49.4 -> 53.3 | Improved |
| add the location prior network (ablation) | FCOS · ImageNet VID val | FPS: 25.1 -> 20.4 | Hurt |
| add the size prior network (ablation) | FCOS+LPN · ImageNet VID val | FPS: 20.4 -> 26.9 | Improved |
| add the size prior network (ablation) | FCOS+LPN · ImageNet VID val | AP: 54.1 -> 53.8 | Mixed |
| add the size prior network (ablation) | YOLOX-M+LPN · ImageNet VID val | FPS: 35.8 -> 50.5 | Improved |
| add the size prior network (ablation) | YOLOX-M+LPN · ImageNet VID val | AP: 53.3 -> 52.7 | Mixed |
| raise box adjustment ratio r from 0.5 to 0.8 (ablation) | FCOS+LPN · ImageNet VID val | AP: 53.6 -> 54.1 | Improved |
| raise box adjustment ratio r from 0.8 to 1.5 (ablation) | FCOS+LPN · ImageNet VID val | FPS: 20.4 -> 14.7 | Hurt |
| raise frame interval T from 7 to 28 (ablation) | FCOS+LPN+SPN · ImageNet VID val | AP: 53.8 -> 48.5 | Hurt |
| use attention on all pixels instead of 300 proposals (naive one-stage adaptation) | SELSA-style attention · ImageNet VID, 2 reference frames | FPS: 18.5 -> 4.6 | Hurt |
Closest papers by meaning
- Practical Video Object Detection via Feature Selection and Aggregation (IJCV 2026 · similarity 0.90)
- YOLOV: Making Still Image Object Detectors Great at Video Object Detection (AAAI 2023 · similarity 0.87)
- Learning Rich Features at High-Speed for Single-Shot Object Detection (ICCV 2019 · similarity 0.87)
- Video Object Detection via Object-level Temporal Aggregation (ECCV 2020 · similarity 0.86)
- Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection (ICCV 2019 · similarity 0.86)
- Context Enhanced Transformer for Single Image Object Detection in Video Data (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
