Effective analysis of unusual domain specific video collections represents an important practical problem, where state-of-the-art general purpose models still face limitations. Hence, it is desirable to design benchmark datasets that challenge novel powerful models for specific domains with additional constraints. It is important to remember that domain specific data may be noisier (e.g., endoscopic or underwater videos) and often require more experienced users for effective search. In this paper, we focus on single-shot videos taken from moving cameras in underwater environments which constitute a nontrivial challenge for research purposes. The first shard of a new Marine Video Kit dataset is presented to serve for video retrieval and other computer vision challenges. In addition to basic meta-data statistics, we present several insights and reference graphs based on low-level features as well as semantic annotations of selected keyframes. The analysis contains also experiments showing limitations of respected general purpose models for retrieval.
翻译:有效分析非同寻常域特定视频收藏是一个重要的实际问题,最先进的一般用途模型仍面临局限性,因此,最好设计基准数据集,对具有额外限制的特定领域新的强大模型提出挑战,必须记住,具体领域的具体数据可能是新颖的(例如内镜或水下视频),往往需要经验丰富的用户才能有效搜索。在本文中,我们侧重于从水下环境中移动相机拍摄的单张视频,这些视频对研究目的来说构成非技术性挑战。新的海洋视频工具包数据集的第一块碎片用于视频检索和其他计算机视觉挑战。除了基本的元数据统计外,我们还提供一些基于低级别特征的洞察力和参考图以及某些关键框架的语义说明。分析还包含一些实验,显示受尊重的一般检索模式的局限性。