Research map / Label-efficient and robust learning / Recognition and long-tail
V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting
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 |
|---|---|---|---|
| Add vehicle-infrastructure point-cloud fusion | Point-cloud 3D tracking · SPD, 200 ms latency | MOTA: 39.31 -> 51.27 | Helped |
| Use middle fusion instead of early fusion | VIC3D Tracking · SPD, 0 ms latency | MOTA: 56.03 vs. 54.75 | Hurt |
| Use middle fusion instead of early fusion | VIC3D Tracking · SPD, 0 ms latency | BPS: 1.3×10^7 vs. 6.2×10^5 | Helped |
| Add feature-flow prediction and transmit feature flow | FF-Tracking · SPD, 200 ms latency | MOTA: 48.38 -> 52.26 | Helped |
| Increase latency from 0 ms to 200 ms while using feature-flow alignment | FF-Tracking · SPD | MOTA: 54.75 -> 52.26 | Hurt |
| Add real-time infrastructure trajectories | TNT · TFD cooperative-view validation | minADE: 12.01 -> 8.27 | Helped |
| Add real-time infrastructure trajectories | HiVT · TFD cooperative-view validation | minADE: 1.55 -> 1.27 | Helped |
| Pretrain on infrastructure trajectories, then fine-tune | TNT · TFD cooperative-view validation | minADE: 12.01 -> 4.36 | Helped |
| Pretrain on infrastructure trajectories, then fine-tune | HiVT · TFD cooperative-view validation | minADE: 1.55 -> 1.52 | Helped |
Closest papers by meaning
- Learning Cooperative Trajectory Representations for Motion Forecasting (NeurIPS 2024 · similarity 0.91)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (NeurIPS 2025 · similarity 0.90)
- V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception (NeurIPS 2025 · similarity 0.88)
- End-to-End Autonomous Driving Through V2X Cooperation (AAAI 2025 · similarity 0.88)
- DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving (AAAI 2024 · similarity 0.87)
- SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving (CVPR 2025 · 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.