Research map / Detection and segmentation / Tracking
Deep Meta Learning for Real-Time Target-Aware Visual Tracking
Janghoon Choi, Junseok Kwon, Kyoung Mu Lee
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 the meta-learner network to the matching network (ablation) | MLT · OTB-2015 | AUC: 0.564 -> 0.611 | Improved |
| use meta-learner instead of online finetuning of conv5 (ablation) | MLT · OTB-2015 | AUC: 0.523 -> 0.611 | Improved |
| add the meta-learner network to the matching network (ablation) | MLT · OTB-2013 | AUC: 0.571 -> 0.621 | Improved |
| use meta-learner instead of online finetuning of conv5 (ablation) | MLT · OTB-2013 | AUC: 0.510 -> 0.621 | Improved |
| add the meta-learner network to the matching network (ablation) | MLT · LaSOT (Protocol I) | AUC: 0.357 -> 0.368 | Improved |
| use meta-learner instead of online finetuning of conv5 (ablation) | MLT · LaSOT (Protocol I) | AUC: 0.331 -> 0.368 | Improved |
| add the meta-learner network to the matching network (ablation) | MLT · LaSOT (Protocol II) | AUC: 0.330 -> 0.345 | Improved |
| use meta-learner instead of online finetuning of conv5 (ablation) | MLT · LaSOT (Protocol II) | AUC: 0.305 -> 0.345 | Improved |
| add the meta-learner network (TC-128) (ablation) | MLT · TC-128 | AUC: 0.477 -> 0.498 | Improved |
| add the meta-learner network (UAV20L) (ablation) | MLT · UAV20L | AUC: 0.366 -> 0.435 | Improved |
| use meta-learner instead of online finetuning (TC-128) (ablation) | MLT · TC-128 | AUC: 0.419 -> 0.498 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- SINT — SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation (CVPR 2018) · better on 1 of 2 shared results
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
- Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers (ECCV 2018 · similarity 0.92)
- Target-Aware Deep Tracking (CVPR 2019 · similarity 0.92)
- Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning (AAAI 2020 · similarity 0.90)
- Learning Dynamic Siamese Network for Visual Object Tracking (ICCV 2017 · similarity 0.90)
- Robust Visual Tracking via Hierarchical Convolutional Features (TPAMI 2018 · similarity 0.89)
- Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook (TPAMI 2022 · similarity 0.88)
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.
