Research map / Detection and segmentation / 3D detection and driving
Perceiving, Learning, and Recognizing 3D Objects: An Approach to Cognitive Service Robots
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| proposed viewpoint entropy (coverage plus saliency) as a predictor of detection performance | next-best-view prediction · synthetic bin-picking dataset | correlation with F1: correlation coefficient 0.6644 | Helped |
| add more object categories during open-ended learning (ablation) | open-ended recognizer · Washington RGB-D, open-ended | global classification accuracy | Hurt |
| instance-based open-ended learning instead of deep network batch training | 3D category learning · Washington RGB-D | training instances needed: under 20 instances per category (17.28 avg) for ~70% accuracy vs more than 1000 | Helped |
Closest papers by meaning
- ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization (NeurIPS 2024 · similarity 0.86)
- A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning (CVPR 2025 · similarity 0.84)
- Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets (ICLR 2025 · similarity 0.84)
- Entity-Centric Reinforcement Learning for Object Manipulation from Pixels (ICLR 2024 · similarity 0.84)
- Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception (CVPR 2024 · similarity 0.83)
- I-Perceive: A Foundation Model for Vision-Language Active Perception (NeurIPS 2026 · 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.