Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps
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 |
|---|---|---|---|
| Use spatial confidence maps to select sparse, informative features and guide message fusion | Where2comm · OPV2V | AP@0.50: 39.82 -> 47.14 | Helped |
| Use spatial confidence maps to select sparse, informative features and guide message fusion | Where2comm · DAIR-V2X | AP@0.50: 56.01 -> 63.76 | Helped |
| Use spatial confidence maps to select sparse, informative features and guide message fusion | Where2comm · V2X-Sim2.0 | AP@0.50: 80.80 -> 83.77 | Helped |
| Apply Gaussian filtering during critical-area selection (ablation) | Where2comm · Reported selection-matrix ablation | detection performance | Helped |
| Add multi-head attention to fusion (ablation) | Where2comm fusion · OPV2V | AP@0.50: 34.96 -> 38.75 | Helped |
| Add multi-head attention to fusion (ablation) | Where2comm fusion · CoPerception-UAVs | AP@0.50: 63.48 -> 63.99 | Helped |
| Add multi-head attention to fusion (ablation) | Where2comm fusion · V2X-Sim | AP@0.50: 51.2 -> 57.3 | Helped |
| Add sensor positional encoding (ablation) | Where2comm fusion with MHA · OPV2V | AP@0.50: 38.75 -> 39.82 | Helped |
| Add sensor positional encoding (ablation) | Where2comm fusion with MHA · CoPerception-UAVs | AP@0.50: 63.99 -> 64.34 | Helped |
| Add sensor positional encoding (ablation) | Where2comm fusion with MHA · V2X-Sim | AP@0.50: 57.3 -> 59.1 | Helped |
| Add spatial confidence map as a fusion prior (ablation) | Where2comm fusion with MHA and SPE · OPV2V | AP@0.50: 39.82 -> 47.30 | Helped |
| Add spatial confidence map as a fusion prior (ablation) | Where2comm fusion with MHA and SPE · CoPerception-UAVs | AP@0.50: 64.34 -> 64.83 | Helped |
Closest papers by meaning
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.88)
- CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization (CVPR 2025 · similarity 0.88)
- RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (CVPR 2025 · similarity 0.88)
- What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception (AAAI 2024 · similarity 0.88)
- Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism (NeurIPS 2025 · similarity 0.87)
- AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning (AAAI 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.