Research map / Detection and segmentation / Tracking
Visual Tracking via Spatially Aligned Correlation Filters Network
Mengdan Zhang, Qiang Wang, Junliang Xing, Jin Gao, Peixi Peng, Weiming Hu, Steve Maybank
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 |
|---|---|---|---|
| train SAM on ILSVRC2015 instead of GOTURN's ALOV300++ (SAM alone vs GOTURN) (ablation) | stage-1 alignment network · VOT2015 | EAO: 0.203 -> 0.158 | Hurt |
| train CF module on SAM-aligned augmented samples (CF-Aug) instead of canonical samples (ablation) | DCFNet · VOT2015 | EAO: 0.217 -> 0.225 | Improved |
| add SAM coarse localization to DCFNet (ablation) | DCFNet · VOT2015 | EAO: 0.217 -> 0.280 | Improved |
| add SAM to DCFNet (ablation) | DCFNet · VOT2015 | robustness (failures): 1.68 -> 1.19 | Improved |
| learn CF module coupled to SAM (SACF(D)-iter1) instead of direct SAM-DCFNet combination (ablation) | SAM-DCFNet · VOT2015 | EAO: 0.280 -> 0.287 | Improved |
| add end-to-end fine-tuning of SAM and CF module (ablation) | SACF(D)-iter1 · VOT2015 | EAO: 0.287 -> 0.324 | Improved |
| add end-to-end fine-tuning of SAM and CF module (ablation) | SACF(D)-iter1 · OTB2013 | AUC: 0.648 -> 0.664 | Improved |
| add end-to-end fine-tuning of SAM and CF module (ablation) | SACF(D)-iter1 · OTB2015 | AUC: 0.612 -> 0.633 | Improved |
| add SAM to continuous CF tracker ECO | ECO · VOT2015 | EAO: 0.326 -> 0.343 | Improved |
| add SAM to continuous CF tracker ECO | ECO · VOT2015 | robustness (failures): 1.29 -> 1.07 | Improved |
| add SAM to continuous CF tracker ECO | ECO · OTB2015 | AUC: 0.688 -> 0.693 | Improved |
| add SAM to continuous CF tracker ECO | ECO · VOT2016 | EAO: 0.353 -> 0.380 | Improved |
Closest papers by meaning
- Robust Estimation of Similarity Transformation for Visual Object Tracking (AAAI 2019 · similarity 0.91)
- Correlation-Aware Deep Tracking (CVPR 2022 · similarity 0.90)
- End-To-End Representation Learning for Correlation Filter Based Tracking (CVPR 2017 · similarity 0.90)
- Structural Correlation Filter for Robust Visual Tracking (CVPR 2016 · similarity 0.90)
- Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking (IJCV 2018 · similarity 0.89)
- Attentional Correlation Filter Network for Adaptive Visual Tracking (CVPR 2017 · similarity 0.89)
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.
