Research map / Detection and segmentation / Tracking
Learning Dynamic Memory Networks for Object Tracking
Tianyu Yang, Antoni B. Chan
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 attention mechanism for the LSTM input (ablation) | MemTrack · OTB-2015 | success AUC | Improved |
| add dynamic addressable memory instead of a FIFO queue of templates (ablation) | MemTrack · OTB-2015 | success AUC | Improved |
| use soft weighted-sum reading instead of hard max-similarity reading (ablation) | MemTrack · OTB-2015 | success AUC | Improved |
| add channel-wise gated residual template learning (ablation) | MemTrack · OTB-2015 | success AUC | Improved |
| increase number of memory slots from 1 to 8 (ablation) | MemTrack · OTB-2015 | success AUC | Improved |
| increase memory slots beyond 8 (to 16) (ablation) | MemTrack · OTB-2015 | success AUC | No clear effect |
| add dynamic memory over SiamFC baseline | MemTrack vs SiamFC · OTB-2013 | precision plot: +4.9% | Improved |
| add dynamic memory over SiamFC baseline | MemTrack vs SiamFC · OTB-2013 | success plot: +5.8% | Improved |
| add dynamic memory over SiamFC baseline | MemTrack vs SiamFC · OTB-2015 | precision plot: +6.4% | Improved |
| add dynamic memory over SiamFC baseline | MemTrack vs SiamFC · OTB-2015 | success plot: +7.6% | Improved |
| add dynamic memory over SiamFC baseline on low-resolution videos | MemTrack vs SiamFC · OTB-2015 low resolution | AUC: +10.7% | Improved |
| replace linear template interpolation (SiamFC_U) with memory network | MemTrack vs SiamFC_U · OTB-2013 | success plot | Improved |
Closest papers by meaning
- Visual Tracking via Dynamic Memory Networks (TPAMI 2019 · similarity 0.98)
- STMTrack: Template-Free Visual Tracking With Space-Time Memory Networks (CVPR 2021 · similarity 0.89)
- MUTrack: A Memory-Aware Unified Representation Framework for Visual Tracking (AAAI 2026 · similarity 0.89)
- Reading Relevant Feature from Global Representation Memory for Visual Object Tracking (NeurIPS 2023 · similarity 0.88)
- GradNet: Gradient-Guided Network for Visual Object Tracking (ICCV 2019 · similarity 0.87)
- MIMTrack: In-Context Tracking via Masked Image Modeling (AAAI 2025 · similarity 0.87)
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.
