Research map / Detection and segmentation / Tracking
Graph Convolutional 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 |
|---|---|---|---|
| Add spatial GCN part-based modeling (ablation) | SiamFC · OTB-2015 | AUC: 57.7 -> 60.2 | Helped |
| Add temporal edges and spatial-temporal GCN modeling (ablation) | S-GCN · OTB-2015 | AUC: 60.2 -> 63.5 | Helped |
| Add context GCN for adaptive feature learning (ablation) | ST-GCN · OTB-2015 | AUC: 63.5 -> 64.8 | Helped |
| Use one ST-GCN layer instead of two (ablation) | GCT · OTB-2013 | AUC: 0.670 -> 0.645 | Hurt |
| Use four ST-GCN layers instead of two (ablation) | GCT · OTB-2013 | AUC: 0.670 -> 0.665 | Hurt |
| Replace the fully connected spatial graph with an 8-nearest-neighbor graph (ablation) | GCT · OTB-2013 | AUC: 0.670 -> 0.652 | Hurt |
| Use an 8-nearest-neighbor spatial graph and four ST-GCN layers (ablation) | GCT · OTB-2013 | AUC: 0.670 -> 0.660 | Hurt |
| Use one CT-GCN layer instead of two (ablation) | GCT · OTB-2013 | AUC: 0.670 -> 0.661 | Hurt |
| Use four CT-GCN layers instead of two (ablation) | GCT · OTB-2013 | AUC: 0.670 -> 0.667 | Hurt |
| Remove CT-GCN message passing and linearly combine features using learned scores (ablation) | GCT · OTB-2013 | AUC: 0.670 -> 0.655 | Hurt |
| Use both spatial-temporal target modeling and context-guided feature adaptation (ablation) | Siamese tracking · OTB-2015 | AUC: 57.7 -> 64.8 | Helped |
Closest papers by meaning
- Graph Attention Tracking (CVPR 2021 · similarity 0.91)
- High Performance Visual Tracking With Siamese Region Proposal Network (CVPR 2018 · similarity 0.89)
- SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines (AAAI 2020 · similarity 0.89)
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking (CVPR 2019 · similarity 0.88)
- SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks (CVPR 2019 · similarity 0.88)
- GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction (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.