Research map / Video / Video segmentation and tracking
AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting
Artur Xarles, Sergio Escalera, Thomas B. Moeslund, Albert Clapés
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 high-res RoI branch to low-res branch (ablation) | AdaSpot-s · Tennis (AdaSpot-s ablation) | mAP@0f: 71.18 -> 73.30 | Improved |
| add high-res RoI branch to low-res branch (ablation) | AdaSpot-s · SN-BAS (AdaSpot-s ablation) | mAP@0.5s: 47.98 -> 53.02 | Improved |
| use replicate padding instead of zero-padding (ablation) | AdaSpot-s · Tennis (AdaSpot-s ablation) | mAP@0f: 72.15 -> 73.30 | Improved |
| use replicate padding instead of zero-padding (ablation) | AdaSpot-s · SN-BAS (AdaSpot-s ablation) | mAP@0.5s: 51.01 -> 53.02 | Improved |
| add spatio-temporal smoothing to saliency (ablation) | AdaSpot-s · Tennis (AdaSpot-s ablation) | mAP@0f: 71.67 -> 73.30 | Improved |
| add spatio-temporal smoothing to saliency (ablation) | AdaSpot-s · SN-BAS (AdaSpot-s ablation) | mAP@0.5s: 49.99 -> 53.02 | Improved |
| use adaptive RoI scale instead of fixed crop (ablation) | AdaSpot-s · Tennis (AdaSpot-s ablation) | mAP@0f: 72.81 -> 73.30 | Improved |
| use adaptive RoI scale instead of fixed crop (ablation) | AdaSpot-s · SN-BAS (AdaSpot-s ablation) | mAP@0.5s: 53.02 -> 51.71 | Hurt |
| add high-res auxiliary loss Lh (ablation) | AdaSpot-s · Tennis (AdaSpot-s ablation) | mAP@0f: 71.18 -> 73.30 | Improved |
| add low-res auxiliary loss Ll (ablation) | AdaSpot-s · Tennis (AdaSpot-s ablation) | mAP@0f: 72.81 -> 73.30 | Improved |
| add both auxiliary losses (ablation) | AdaSpot-s · SN-BAS (AdaSpot-s ablation) | mAP@0.5s: 49.22 -> 53.02 | Improved |
| use AdaSpot-b instead of E2E-Spot 800MF | AdaSpot-b · SN-BAS | mAP@0.5s: 54.49 -> 56.24 | Improved |
Closest papers by meaning
- "Spotting Temporally Precise, Fine-Grained Events in Video" (ECCV 2022 · similarity 0.88)
- A Context-Aware Loss Function for Action Spotting in Soccer Videos (CVPR 2020 · similarity 0.88)
- Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance (CVPR 2025 · similarity 0.87)
- Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation (AAAI 2026 · similarity 0.86)
- Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization (ECCV 2018 · similarity 0.86)
- AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition (ECCV 2022 · 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.
