Pets vs. vace evaluation programs: A comparative study

摘要: There are numerous distributed efforts on performance evaluation of computer vision algorithms. Information exchange between programs can expedite achievement of the common goals of such projects. As a step towards this, this paper presents a qualitative comparison of the VACE and the PETS programs, the synergy of which, we believe, will have a signi cant impact on the progress of research in the vision community. The comparison is based on the vital aspects of an evaluation project–the framework, the tasks, performance metrics and ground truth data.