Research map / 3D vision / 3D generation
JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments
Roberto Martín-Martín, Mihir Patel, Hamid Rezatofighi, Abhijeet Shenoi, JunYoung Gwak, E. Frankel, Amir Sadeghian, Silvio Savarese
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 re-identification after long occlusions (RALO) | DeepSORT · JRDB 2D tracking | ID switches: 5296 -> 5022 | Improved |
| add RALO | JRMOT (2D) · JRDB 2D tracking | ID switches: 7719 -> 6612 | Improved |
| add RALO | Tracktor · JRDB 2D tracking | ID switches: 7026 -> 6084 | Improved |
| raise 3D AP IoU threshold from 0.3 to 0.5 | F-PointNet · JRDB 3D detection | AP: 38.21 -> 6.38 | Hurt |
| raise 3D AP IoU threshold from 0.3 to 0.5 | TANet · JRDB 3D detection | AP: 53.87 -> 4.17 | Hurt |
| use TANet instead of F-PointNet detections | AB3DMOT · JRDB 3D tracking | MOTA: 19.4 -> 26.2 | Improved |
| use TANet instead of F-PointNet detections | AB3DMOT · JRDB 3D tracking | ID switches: 6177 -> 10081 | Hurt |
| outdoor instead of indoor scenes | DeepSORT · JRDB 2D tracking | MOTA: 25.5 -> 18.5 | Hurt |
| outdoor instead of indoor scenes | Faster R-CNN · JRDB 2D detection | AP@IoU=.5: 54.1 -> 48.1646 | Hurt |
| outdoor instead of indoor scenes | TANet · JRDB 3D detection | AP@IoU=.3: 52.16 -> 59.15 | Improved |
| replace Faster R-CNN with YOLOv3 | 2D detector · JRDB 2D detection | OSPA_IoU localization: 0.260 -> 0.161 | Improved |
| replace DeepSORT with Tracktor | 2D tracker · JRDB 2D tracking | MOTA: 23.2 -> 18.1 | Hurt |
Closest papers by meaning
- RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments (CVPR 2025 · similarity 0.89)
- JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups (CVPR 2024 · similarity 0.88)
- JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments (CVPR 2024 · similarity 0.88)
- EgoGen: An Egocentric Synthetic Data Generator (CVPR 2024 · similarity 0.87)
- HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos (CVPR 2025 · similarity 0.87)
- Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models (NeurIPS 2026 · 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.
