Research map / Detection and segmentation / Tracking
Saliency-Associated Object Tracking
Zikun Zhou, Wenjie Pei, Xin Li, Hongpeng Wang, Feng Zheng, Zhenyu He
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 pixel-to-pixel similarity maps (ablation) | base model · OTB2015 | AUC: 0.651 -> 0.687 | Improved |
| add pixel-to-pixel similarity maps (ablation) | base model · NFS30 | AUC: 0.597 -> 0.625 | Improved |
| add association modeling between matched local parts (ablation) | PPFM · OTB2015 | AUC: 0.687 -> 0.701 | Improved |
| add association modeling between matched local parts (ablation) | PPFM · NFS30 | AUC: 0.625 -> 0.641 | Improved |
| add saliency mining to select discriminative parts (ablation) | PAM · OTB2015 | AUC: 0.701 -> 0.714 | Improved |
| add saliency mining to select discriminative parts (ablation) | PAM · NFS30 | AUC: 0.641 -> 0.656 | Improved |
| add saliency mining to select discriminative parts (ablation) | PAM · OTB2015 | precision: 0.909 -> 0.926 | Improved |
| use saliency mining and association instead of depth-wise correlation (ablation) | SAOT · OTB2015 | AUC: 0.691 -> 0.714 | Improved |
| use saliency mining and association instead of pixel-to-global correlation (ablation) | SAOT · OTB2015 | AUC: 0.693 -> 0.714 | Improved |
| use saliency mining and association instead of depth-wise correlation (ablation) | SAOT · NFS30 | AUC: 0.617 -> 0.656 | Improved |
| use saliency mining and association instead of pixel-to-global correlation (ablation) | SAOT · NFS30 | AUC: 0.619 -> 0.656 | Improved |
| part-based saliency tracking instead of holistic tracking with same online filter (DiMP) | SAOT · OTB2015 | AUC: 2.8% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ATOM — ATOM: Accurate Tracking by Overlap Maximization (CVPR 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MC-HOG Correlation Tracking with Saliency Proposal (AAAI 2016 · similarity 0.87)
- Robust Visual Tracking via Hierarchical Convolutional Features (TPAMI 2018 · similarity 0.86)
- Salient Object Detection: A Discriminative Regional Feature Integration Approach (IJCV 2016 · similarity 0.86)
- Unveiling the Power of Deep Tracking (ECCV 2018 · similarity 0.86)
- TrackFlow: Multi-Object tracking with Normalizing Flows (ICCV 2023 · similarity 0.86)
- Staple: Complementary Learners for Real-Time Tracking (CVPR 2016 · 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.
