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

Quang-Trung Truong1          Tuan-Anh Vu1          Tan-Sang Ha1          Jakub Lokoč2
         Yue Him Wong Tim3          Ajay Joneja1          Sai-Kit Yeung1

1Hong Kong University of Science and Technology 2FMP, Charles University, Prague, Czech Republic
3Shenzhen University

International Conference On Multimedia Modeling (MMM), 2023 (Oral Presentation)

Several examples of dataset video frames that are extracted with 1fps and their ClipCap descriptions.

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

Materials
Marine Video Kit dataset - Statistics and Videos

Some marine videos are selected from the dataset.

Triton_Dec2018

Oahu 23th July


Number of videos and video duration

Total length: 12.38 hours
Number of videos: 1374
Dive sites: 11 countries/ regions

Known-item Search Experiment
Known-item Search Experiment.=
Citation
        
    @inproceedings{MVK,
    title     = {Marine Video Kit: A New Marine Video Dataset for Content-based Analysis and Retrieval},
    author    = {Truong, Quang-Trung and Vu, Tuan-Anh and Ha, Tan-Sang and Lokoč, Jakub and Tim,
                Yue Him Wong and Joneja, Ajay and Yeung, Sai-Kit},
    publisher = {Springer},
    year      = {2023},
    booktitle = {MultiMedia Modeling - 29th International Conference, {MMM} 2023,
                Bergen, Norway, January 9-12, 2023},
    series    = {Lecture Notes in Computer Science},
}
    }
      

How to download the Dataset
If you would like to download the Marine Kit Video dataset, please fill out an agreement to the "Marine Video Kit Dataset Terms of Use" to get the download link.

Acknowledgements.
This research project is partially supported by an internal grant from HKUST (R9429), the Innovation and Technology Support Programme of the Innovation and Technology Fund (Ref: ITS/200/20FP), the Marine Conservation Enhancement Fund (MCEF20107), Charles University grant (SVV-260588), and the Innovation Team Project of Universities in Guangdong Province (No. 2020KCXTD023).
Disclaimer.
Any opinions, findings, conclusions, or recommendations expressed in this material do not necessarily reflect the views of HKLTL, CAPCO, HK Electric, and the Marine Conservation Enhancement Fund.
Discussion
Please email us at tsha [at] cse.ust.hk for any inquiries. You can also post to the discussion board below.