SCOOT: Self-supervised Centric Open-set Object Tracking
文献类型：会议论文
| 作者 | Li W(李巍)1,2; Meng WL(孟维亮)1,2 ; Li BW(李博文)1,2; Zhang JG(张吉光)1,2; Zhang XP(张晓鹏)1,2
|
| 出版日期 | 2023-12 |
| 会议日期 | 2023-12-12-2023-12-15 |
| 会议地点 | Sydney, Australia |
| 英文摘要 | We propose a novel and comprehensive general-purpose object tracking system named Self-supervised Centric Open-set Object Tracking or ‘SCOOT’. Our SCOOT encompasses a self-supervised appearance model, a fusion module for combining textual and visual features, and an object association algorithm based on reconstruction and observation. Through this system, we unlock new possibilities for enhancing the capability ofopen-set object tracking with the aid of language cues in real-world scenarios. |
| 语种 | 英语 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57146]  |
| 专题 | 模式识别国家重点实验室_三维可视计算 |
| 通讯作者 | Meng WL(孟维亮); Zhang JG(张吉光) |
| 作者单位 | 1.Univ. of CAS 2.MAIS, CASIA |
| 推荐引用方式 GB/T 7714 | Li W,Meng WL,Li BW,et al. SCOOT: Self-supervised Centric Open-set Object Tracking[C]. 见:. Sydney, Australia. 2023-12-12-2023-12-15. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。