Research map / Architectures and efficiency / CNN design
STCT: Sequentially Training Convolutional Networks for Visual Tracking
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use sequential ensemble training instead of conventional joint SGD training (ablation) | CNN-based visual tracking · OTB OPE | success AUC: 0.577 -> 0.640 | Helped |
| use sequential ensemble training instead of conventional joint SGD training (ablation) | CNN-based visual tracking · OTB OPE | precision: 0.703 -> 0.780 | Helped |
| add the convolution-with-mask layer (ablation) | STCT · OTB OPE | success AUC: 0.610 -> 0.640 | Helped |
| add the convolution-with-mask layer (ablation) | STCT · OTB OPE | precision: 0.755 -> 0.780 | Helped |
| use STCT rather than MEEM | visual tracking · OTB OPE | success AUC: 0.570 -> 0.640 | Helped |
| use STCT rather than MEEM | visual tracking · OTB TRE | success AUC: 0.564 -> 0.650 | Helped |
| use STCT rather than MEEM | visual tracking · OTB SRE | success AUC: 0.526 -> 0.577 | Helped |
Closest papers by meaning
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.91)
- Release the Power of Online-Training for Robust Visual Tracking (AAAI 2020 · similarity 0.90)
- BranchOut: Regularization for Online Ensemble Tracking With Convolutional Neural Networks (CVPR 2017 · similarity 0.88)
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking (CVPR 2019 · similarity 0.87)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.86)
- Autoregressive Sequential Pretraining for Visual Tracking (CVPR 2025 · similarity 0.85)
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.