Tracked Instance Search
Tracked Instance Search
复制标题
DOI：
10.1109/icassp.2018.8461378
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Andreu Girbau;Ryota Hinami;S. Satoh
中科院分区：
文献类型：
--
作者：
Andreu Girbau;Ryota Hinami;S. Satoh
在这项工作中，我们建议将跟踪作为实例搜索任务的通用添加。从视频数据的角度来看，传统的实例搜索方法没有考虑到很多可以利用的信息。这项工作旨在通过跟踪和结果的适当组合，独立于实例搜索系统，提供对利用这些现有信息的见解。我们还对使用同一个人的多个独立实例（最多4个）时系统的改进进行了研究。实验结果表明，采用跟踪技术后，系统的性能有了很大的提高。对于单个示例，最佳配置从mAP = 0.447提高到mAP = 0.511，对于多个(4)给定示例，最佳配置从mAP = 0.647提高到mAP = 0.704。
In this work we propose tracking as a generic addition to the instance search task. From video data perspective, much information that can be used is not taken into account in the traditional instance search approach. This work aims to provide insights on exploiting such existing information by means of tracking and the proper combination of the results, independently of the instance search system. We also present a study on the improvement of the system when using multiple independent instances (up to 4) of the same person. Experimental results show that our system improves substantially its performance when using tracking. Best configuration improves from mAP = 0.447 to mAP = 0.511for a single example, and from mAP = 0.647 to mAP = 0.704for multiple (4) given examples.