Research map / Video / Video segmentation and tracking
Mutual Enhancement for Detection of Multiple Logos in Sports Videos
Yuan Liao, Xiaoqing Lu, Chengcui Zhang, Yongtao Wang, Zhi Tang
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 homogeneous sibling promotion (rho) to Fast-RCNN (ablation) | FRCN · FlickrLogos-32 | recall: 0.69 -> 0.76 | Improved |
| add homogeneous sibling promotion (rho) to Fast-RCNN (ablation) | FRCN · FlickrLogos-32 | precision: 0.8 -> 0.73 | Hurt |
| add homogeneous sibling promotion (rho) to Fast-RCNN (ablation) | FRCN · FlickrLogos-32 | F1: 0.74 -> 0.74 | No clear effect |
| add color consistency (lambda) to promotion (ablation) | FRCN+rho · FlickrLogos-32 | precision: 0.73 -> 0.77 | Improved |
| add color consistency (lambda) to promotion (ablation) | FRCN+rho · FlickrLogos-32 | F1: 0.74 -> 0.76 | Improved |
| add inhomogeneous exclusion to promotion and color consistency (ablation) | FRCN+rho+lambda · FlickrLogos-32 | precision: 0.77 -> 0.81 | Improved |
| add inhomogeneous exclusion to promotion and color consistency (ablation) | FRCN+rho+lambda · FlickrLogos-32 | F1: 0.76 -> 0.79 | Improved |
| add re-ranking to Fast-RCNN (ablation) | FRCN · Tennis video logo dataset | F1: 0.583 -> 0.603 | Improved |
| add frame propagation to Fast-RCNN alone (ablation) | FRCN · Tennis video logo dataset | F1: 0.583 -> 0.581 | No clear effect |
| add frame propagation to Fast-RCNN with re-ranking (ablation) | FRCN+re-ranking · Tennis video logo dataset | F1: 0.603 -> 0.616 | Improved |
| replace Fast-RCNN with proposed mutual enhancement re-ranking | FRCN · FlickrLogos-27 | F1: 0.586 -> 0.626 | Improved |
| replace Fast-RCNN with proposed mutual enhancement re-ranking | FRCN · Own logo dataset | F1: 0.736 -> 0.780 | Improved |
Closest papers by meaning
- Large-Scale Logo Detection (TPAMI 2025 · similarity 0.83)
- LOGO: A Long-Form Video Dataset for Group Action Quality Assessment (CVPR 2023 · similarity 0.82)
- ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis (AAAI 2024 · similarity 0.81)
- Towards Universal Soccer Video Understanding (CVPR 2025 · similarity 0.81)
- SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos (CVPR 2024 · similarity 0.81)
- Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance (CVPR 2025 · similarity 0.81)
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.
