Research map / Detection and segmentation / Tracking
Robust MIL-Based Feature Template Learning for Object Tracking
Xiangyuan Lan, Pong C. Yuen, Rama Chellappa
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 |
|---|---|---|---|
| learn feature templates with contaminated-feature modeling and MIL bags instead of per-frame updating/other trackers (vs best baseline SCM) | particle-filter sparse tracker · 20-video tracking set | precision (20px): 0.751 -> 0.862 | Improved |
| same, success rate vs SCM | particle-filter sparse tracker · 20-video tracking set | success rate (AUC): 0.577 -> 0.636 | Improved |
| proposed tracker vs online MIL boosting tracker (MIL) | tracker · 20-video tracking set | average success rate: 0.52 -> 0.81 | Improved |
Closest papers by meaning
- Robust Object Modeling for Visual Tracking (ICCV 2023 · similarity 0.87)
- Learning Dynamic Memory Networks for Object Tracking (ECCV 2018 · similarity 0.84)
- Interacting Multiview Tracker (TPAMI 2016 · similarity 0.84)
- Visual Tracking via Dynamic Memory Networks (TPAMI 2019 · similarity 0.84)
- Model Uncertainty Guides Visual Object Tracking (AAAI 2021 · similarity 0.84)
- Robust Tracking via Mamba-based Context-aware Token Learning (AAAI 2025 · similarity 0.81)
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.
