Research map / Detection and segmentation / Tracking
Pose-Assisted Multi-Camera Collaboration for Active Object Tracking
Jing Li, Jing Xu, Fangwei Zhong, Xiangyu Kong, Yu Qiao, Yizhou Wang
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 the pose-assisted controllers and visibility switcher instead of the strongest conventional tracker baseline | CMC-AOT · Garden | Mean Error: 24.04 -> 10.76 | Improved |
| use the pose-assisted controllers and visibility switcher instead of the strongest conventional tracker baseline | CMC-AOT · Urban City | Mean Error: 27.93 -> 8.02 | Improved |
| add pose-assisted collaboration with visibility-based switching | CMC-AOT · Garden | Success Rate: 69.06 -> 85.66 | Improved |
| add pose-assisted collaboration with visibility-based switching | CMC-AOT · Urban City | Success Rate: 68.98 -> 84.18 | Improved |
| fuse visual representations from other cameras rather than use only each camera's visual input (ablation) | CMC-AOT · Garden | Mean Error: 28.07 -> 31.81 | Hurt |
| fuse visual representations from other cameras rather than use only each camera's visual input (ablation) | CMC-AOT · Urban City | Mean Error: 34.02 -> 21.96 | Improved |
| add visual-feature fusion from other cameras instead of using only own visual input (ablation) | CMC-AOT · Garden | Success Rate: 64.57 -> 43.46 | Hurt |
| add visual-feature fusion from other cameras instead of using only own visual input (ablation) | CMC-AOT · Urban City | Success Rate: 51.99 -> 63.53 | Improved |
| add pose features through direct fusion without the proposed switcher (ablation) | CMC-AOT · Garden | Mean Error: 28.07 -> 26.80 | No clear effect |
| add pose features through direct fusion without the proposed switcher (ablation) | CMC-AOT · Urban City | Mean Error: 34.02 -> 25.56 | Improved |
| use the proposed switcher to select between vision-based and pose-based controllers instead of direct pose fusion (ablation) | CMC-AOT · Garden | Mean Error: 26.80 -> 10.76 | Improved |
| use the proposed switcher to select between vision-based and pose-based controllers instead of direct pose fusion (ablation) | CMC-AOT · Urban City | Mean Error: 25.56 -> 8.02 | Improved |
Closest papers by meaning
- RSPT: Reconstruct Surroundings and Predict Trajectory for Generalizable Active Object Tracking (AAAI 2023 · similarity 0.86)
- Towards Real-Time Multi-Object Tracking (ECCV 2020 · similarity 0.85)
- PoseTrack: Joint Multi-Person Pose Estimation and Tracking (CVPR 2017 · similarity 0.85)
- Online Multi-Object Tracking via Structural Constraint Event Aggregation (CVPR 2016 · similarity 0.85)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.84)
- Towards Generalizable Multi-Object Tracking (CVPR 2024 · similarity 0.83)
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.
