Marine Video Kit: A New Marine Video Dataset for Content-based Analysis and Retrieval

TL;DR

This paper introduces the Marine Video Kit, a new underwater video dataset designed to challenge and evaluate content-based video retrieval models in domain-specific, noisy, and challenging underwater environments.

Contribution

The paper presents the first shard of the Marine Video Kit dataset for underwater videos, along with insights and experiments highlighting the limitations of general models in this domain.

Findings

General purpose models show limitations on underwater videos

The dataset includes semantic annotations and low-level feature analysis

The dataset is used in Video Browser Showdown 2023

Abstract

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. Our dataset is used in a special session during Video Browser Showdown 2023. In addition to basic meta-data statistics, we present several insights based on low-level features as well as semantic annotations of selected keyframes. The analysis also contains experiments showing limitations of respected general purpose models for retrieval. Our dataset and code are publicly available at https://hkust-vgd.github.io/marinevideokit.