Method Detail: SeqMLPReg-VLSOT
Back to Leaderboard| Benchmark: | VLSOT |
|---|---|
| Short name: | SeqMLPReg-VLSOT |
| Long name: | A Linear-Regression Based Sequence Baseline |
| Description: | 通过数据模型预测数据，读取json数据；预测每个视频帧中车辆的长宽高和空间坐标（共 6 个数值），frame0~frame29 中提取出每一帧的长、宽、高、x、y、z 这 6 个数据；再把这段长度不固定的序列压缩成一个固定长度的特征向量，得到预测值，按要求格式输出txt文件。 |
| Reference: | N/A |
| Last submitted: | September 19, 2026 |
| Published: | September 18, 2026 at 14:59:51 |
| Submissions: | 2 |
| Project page / code: | https://github.com/23008239/SeqMLPReg |
| Open source: | No |
Benchmark performance
| Submission Date | SR@0.5 (↑) | SR@0.7 (↑) | AOR (↑) | PR@1.0 (↑) | ACE (↓) | PR@0.5 (↑) |
|---|---|---|---|---|---|---|
| 2026-09-19 01:30 | - | - | - | - | - | - |
| 2026-09-18 15:31 | - | - | - | - | - | - |