Research map / Detection and segmentation / Tracking
Online Object Tracking, Learning and Parsing with And-Or Graphs
Tianfu Wu, Yang Lu, Song Chun Zhu
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 online structure re-learning (AOG vs AOGFixed) (ablation) | AOGTracker · TB-100/50/CVPR2013 | success plot OPE/SRE/TRE: consistent overall improvement; AOGFixed-st slightly better on Motion-Blur and Out-of-View | Improved |
| add part configurations (AOG vs whole object template only) (ablation) | AOGTracker · TB-100/50/CVPR2013 | success plot: trackers with AOG perform better than ObjectOnly | Improved |
| add temporal DP (-st vs -s) to AOG trackers (ablation) | AOGTracker · TB-100/50/CVPR2013 | success plot: AOG-st obtains the best overall performance | Improved |
| add temporal DP to whole-object-template tracker (ablation) | ObjectOnly · TB-100/50/CVPR2013 | success plot: ObjectOnly-s slightly outperforms ObjectOnly-st | Hurt |
| AOGTracker vs best prior tracker, OPE | AOGTracker · TB-100 | success rate / precision rate gain: 13.93 / 18.06 | Improved |
| AOGTracker vs STRUCK, SRE | AOGTracker · TB-100 | success rate / precision rate gain: 11.47 / 16.79 | Improved |
| AOGTracker vs runner-up, OPE | AOGTracker · TB-CVPR2013 | success rate gain: 2.74 / 19.37 | Mixed |
| AOGTracker in low-resolution subset | AOGTracker · TB-50 LR | success rate gain: 6.65 | Mixed |
| AOGTracker in scale-variation subset | AOGTracker · TB-50 SV | success rate gain: 18.38 | Improved |
| AOGTracker on VOT2013 robustness | AOGTracker · VOT2013 | robustness: best accuracy, best overall rank, robustness slightly worse than PLT, LGT and LGTpp | Mixed |
| AOGTracker on VOT2014 | AOGTracker · VOT2014 | accuracy/robustness: comparable to other trackers | No clear effect |
Closest papers by meaning
- Tracking Without Bells and Whistles (ICCV 2019 · similarity 0.86)
- OVTrack: Open-Vocabulary Multiple Object Tracking (CVPR 2023 · similarity 0.86)
- TGFormer: Transformer with Track Query Group for Multi-Object Tracking (AAAI 2025 · similarity 0.85)
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.85)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · similarity 0.85)
- ODTrack: Online Dense Temporal Token Learning for Visual Tracking (AAAI 2024 · similarity 0.85)
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.
