Research map / Multi-agent systems and games / Human-AI and goal-conditioned
HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer
Hao Xiang, Runsheng Xu, Jiaqi Ma
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 HM-MLP and HM-LN (type-dependent MLP and layer norm) (ablation) | HM-ViT · OPV2V V2V-H | AP@0.7: 0.404 -> 0.420 | Improved |
| add local heterogeneous 3D graph attention (H3GAT-L) (ablation) | HM-ViT · OPV2V V2V-H | AP@0.7: 0.420 -> 0.460 | Improved |
| add global heterogeneous 3D graph attention (H3GAT-G) (ablation) | HM-ViT · OPV2V V2V-H | AP@0.7: 0.460 -> 0.515 | Improved |
| increase feature compression from 0x to 8x (ablation) | HM-ViT · OPV2V V2V-H | AP@0.7: 0.515 -> 0.513 | No clear effect |
| increase feature compression to 16x and 32x (ablation) | HM-ViT · OPV2V V2V-H | AP@0.7: 0.515 -> 0.470 (16x), 0.455 (32x) | Hurt |
| collaborate with LiDAR agents for a camera-only ego vehicle | camera agents · OPV2V camera ego | AP@0.7: 2.1% -> 53.2% | Improved |
| use late fusion with mostly camera collaborators for LiDAR ego vehicle | Late Fusion · OPV2V agent modality ratio | AP | Hurt |
| train end-to-end directly on V2V-H instead of staged single-modality then hetero fine-tuning | intermediate fusion models · OPV2V V2V-H | convergence | Hurt |
Later papers that compared with this method
3 later accepted papers report HM-ViT as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- STAMP: Scalable Task- And Model-agnostic Collaborative Perception (ICLR 2025 · better on 1 of 1 shared result)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · better on 9 of 9 shared results)
- Hetecooper: Feature Collaboration Graph for Heterogeneous Collaborative Perception (ECCV 2024 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- STAMP: Scalable Task- And Model-agnostic Collaborative Perception (ICLR 2025 · similarity 0.89)
- Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators (AAAI 2025 · similarity 0.88)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (NeurIPS 2025 · similarity 0.88)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.88)
- BEVSync: Asynchronous Data Alignment for Camera-based Vehicle-Infrastructure Cooperative Perception Under Uncertain Delays (AAAI 2025 · similarity 0.88)
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception (NeurIPS 2025 · similarity 0.88)
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.
