Research map / 3D vision / Human pose estimation
Tracking People by Predicting 3D Appearance, Location and Pose
Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik
Check 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 predicted 3D appearance, location, and pose for association | PHALP · PoseTrack | IDF1: 73.4 -> 76.4 | Improved |
| use predicted 3D appearance, location, and pose for association | PHALP · MuPoTS | IDF1: 79.1 -> 81.4 | Improved |
| use predicted 3D appearance, location, and pose for association | PHALP · AVA | IDF1: 61.3 -> 62.7 | Improved |
| add 3D appearance (ablation) | PHALP · PoseTrack | IDF1: 74.9 -> 76.4 | Improved |
| add 3D pose (ablation) | PHALP · PoseTrack | IDF1: 76.2 -> 76.4 | Improved |
| add 3D location (ablation) | PHALP · PoseTrack | IDF1: 71.6 -> 76.4 | Improved |
| add nearness to the location cost (ablation) | PHALP · PoseTrack | IDF1: 74.8 -> 76.4 | Improved |
Closest papers by meaning
- Tracking People with 3D Representations (NeurIPS 2021 · similarity 0.91)
- CoMotion: Concurrent Multi-person 3D Motion (ICLR 2025 · similarity 0.88)
- Multi-View 3D Human Tracking in Crowded Scenes (AAAI 2016 · similarity 0.87)
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels (NeurIPS 2025 · similarity 0.87)
- On the Benefits of 3D Pose and Tracking for Human Action Recognition (CVPR 2023 · similarity 0.86)
- TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking (NeurIPS 2026 · similarity 0.86)
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.
