Tracked Instance Search
Andreu Girbau, Ryota Hinami, Shin'ichi Satoh

TL;DR
This paper introduces tracking as a method to enhance instance search by leveraging video data, significantly improving retrieval performance when combined with traditional search techniques.
Contribution
It demonstrates how integrating tracking with instance search can substantially boost accuracy, especially when multiple instances are used, providing a versatile approach independent of specific search systems.
Findings
Performance improves from mAP 0.447 to 0.511 with tracking for a single example.
Using four instances increases mAP from 0.647 to 0.704.
Tracking enhances system robustness and effectiveness.
Abstract
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 = 0.511 for a single example, and from mAP = 0.647 to mAP = 0.704 for multiple (4) given examples.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Analysis and Summarization · Time Series Analysis and Forecasting · Advanced Image and Video Retrieval Techniques
