Research map / Multi-agent systems and games / Human-AI and goal-conditioned
DATA: Domain-And-Time Alignment for High-Quality Feature Fusion in Collaborative Perception
Chengchang Tian, Jianwei Ma, Yan Huang, Zhanye Chen, Honghao Wei, Hui Zhang, Wei Hong
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 IFAM (ablation) | DATA baseline · DAIR-V2X-C | AP70: 59.91 -> 63.61 | Improved |
| Add IFAM (ablation) | DATA baseline · DAIR-V2X-C | AP50: 76.80 -> 77.02 | Improved |
| Add OD (observability-constrained discriminator) (ablation) | DATA baseline · DAIR-V2X-C | AP50: 76.80 -> 78.52 | Improved |
| Add PHD (proximal-region hierarchical downsampling) (ablation) | DATA baseline · DAIR-V2X-C | AP70: 59.91 -> 62.16 | Improved |
| Add PHD, OD and IFAM together (ablation) | DATA baseline · DAIR-V2X-C | AP50: 76.80 -> 79.94 | Improved |
| Add PHD, OD and IFAM together (ablation) | DATA baseline · DAIR-V2X-C | AP70: 59.91 -> 65.48 | Improved |
| Add PTAM temporal alignment (ablation) | DATA · DAIR-V2X-C (300 ms delay) | AP50: 71.65 -> 77.81 | Improved |
| Use two-stage PTAM instead of first stage only (ablation) | PTAM · DAIR-V2X-C (300 ms delay) | AP50: 76.80 -> 77.81 | Improved |
| Use multi-window supervision (l=16) instead of whole-map supervision (ablation) | PTAM two-stage · DAIR-V2X-C (300 ms delay) | AP50: 77.14 -> 77.81 | Improved |
| Reduce window size from 16 to 4 (ablation) | PTAM two-stage · DAIR-V2X-C (300 ms delay) | AP50: 77.81 -> 76.64 | Hurt |
| Set PHD distance threshold to 50 m instead of 10 m (ablation) | PHD · DAIR-V2X-C | AP50: 79.33 -> 79.94 | Improved |
| Raise PHD distance threshold from 50 m to 90 m (ablation) | PHD · DAIR-V2X-C | AP50: 79.94 -> 78.69 | Hurt |
Closest papers by meaning
- NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception (NeurIPS 2025 · similarity 0.87)
- RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (CVPR 2025 · similarity 0.87)
- What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception (AAAI 2024 · similarity 0.86)
- RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling (NeurIPS 2024 · similarity 0.85)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.85)
- SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation (CVPR 2025 · similarity 0.85)
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.
