Research map / Detection and segmentation / Tracking
Real-Time MDNet
Ilchae Jung, Jeany Son, Mooyeol Baek, Bohyung Han
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 |
|---|---|---|---|
| use RoIAlign instead of RoIPooling (ablation) | RT-MDNet · OTB2015 (pretrained on VOT-OTB) | success AUC (%): 35.4 -> 56.1 | Improved |
| add adaptive RoIAlign (ablation) | RoIAlign · OTB2015 (pretrained on VOT-OTB) | success AUC (%): 56.1 -> 59.0 | Improved |
| add dense feature map (remove pool, dilated conv3) (ablation) | RoIAlign · OTB2015 (pretrained on VOT-OTB) | success AUC (%): 56.1 -> 60.7 | Improved |
| combine adaptive RoIAlign and dense feature map (improved RoIAlign) (ablation) | RoIAlign · OTB2015 (pretrained on VOT-OTB) | precision at 20px (%): 80.4 -> 85.3 | Improved |
| add instance embedding loss to multi-domain pretraining (ablation) | Ours--BBR--IEL · OTB2015 (pretrained on ImageNet-Vid) | success AUC (%): 61.9 -> 64.1 | Improved |
| add instance embedding loss to multi-domain pretraining (ablation) | Ours--BBR--IEL · OTB2015 (pretrained on ImageNet-Vid) | precision at 20px (%): 84.2 -> 87.7 | Improved |
| add bounding box regression (ablation) | Ours--BBR · OTB2015 (pretrained on ImageNet-Vid) | success AUC (%): 64.1 -> 65.0 | Improved |
| add bounding box regression (ablation) | Ours--BBR · OTB2015 (pretrained on ImageNet-Vid) | precision at 20px (%): 87.7 -> 88.5 | Improved |
| use RT-MDNet instead of ECO-HC (real-time tracker) | real-time tracking · OTB2015 | precision at 20px (%): 85.6 -> 88.5 | Improved |
| apply instance embedding loss to original MDNet (ablation) | MDNet · OTB2015 | success/precision | Improved |
Closest papers by meaning
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.92)
- Robust Visual Tracking via Hierarchical Convolutional Features (TPAMI 2018 · similarity 0.89)
- Release the Power of Online-Training for Robust Visual Tracking (AAAI 2020 · similarity 0.89)
- Robust Object Tracking Based on Temporal and Spatial Deep Networks (ICCV 2017 · similarity 0.89)
- Deep Meta Learning for Real-Time Target-Aware Visual Tracking (ICCV 2019 · similarity 0.88)
- 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.
