Research map / Detection and segmentation / Tracking
Know Your Surroundings: Exploiting Scene Information for Object Tracking
Goutam Bhat, Martin Danelljan, Luc Van Gool, Radu Timofte
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 scene information (state propagation and reliability) to appearance model (ablation) | DiMP-50 · NFS + OTB-100 | AUC: 65.1 -> 66.4 | Improved |
| add scene information (ablation) | DiMP-50 · NFS + OTB-100 | OP0.5: 81.9 -> 83.5 | Improved |
| add state propagation module (ablation) | tracker with scene states · NFS + OTB-100 | AUC: 64.9 -> 66.4 | Improved |
| add propagation reliability score (ablation) | tracker · NFS + OTB-100 | AUC: 66.1 -> 66.4 | Improved |
| add appearance model (ablation) | scene-only tracker · NFS + OTB-100 | AUC: 49.2 -> 66.4 | Improved |
| scene states without propagation vs appearance only (ablation) | DiMP-50 · NFS + OTB-100 | AUC: 65.1 -> 64.9 | Hurt |
| add scene information | DiMP-50 · VOT2018 | EAO: 0.440 -> 0.462 | Improved |
| add scene information | DiMP-50 · GOT-10k test | AO: 61.1 -> 63.6 | Improved |
| add scene information | DiMP-50 · TrackingNet test | AUC: 74.0 -> 74.0 | No clear effect |
| add scene information | DiMP-50 · NFS | AUC: 63.5 | Improved |
| add scene information | DiMP-50 · OTB-100 | AUC | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ATOM — ATOM: Accurate Tracking by Overlap Maximization (CVPR 2019) · better on 2 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
- Beyond Local Search: Tracking Objects Everywhere With Instance-Specific Proposals (CVPR 2016 · similarity 0.90)
- Object Tracking using Spatio-Temporal Networks for Future Prediction Location (ECCV 2020 · similarity 0.89)
- A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking (IJCV 2024 · similarity 0.89)
- Robust Visual Tracking via Hierarchical Convolutional Features (TPAMI 2018 · similarity 0.89)
- A Distractor-Aware Memory for Visual Object Tracking with SAM2 (CVPR 2025 · similarity 0.89)
- TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (NeurIPS 2024 · 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.
