MSC: A Marine Wildlife Dataset for Video Understanding with Grounded Segmentation and Clip-Level Captions
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 12621-12628
Abstract
No abstract availableAll Related Versions
Funding Information
- Marine Conservation Enhancement Fund (MCEF20107 and MCEF22112)
- internal grant from HKUST (R9429)
- HKUST Marine Robotics and Blue Economy Technology Grant
- Sustainable Smart Campus as a Living Lab
This publication has 16 references indexed in Scilit:
- CoralSCOP-LAT: Labeling and analyzing tool for coral reef images with dense semantic maskEcological Informatics, 2025
- Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection2024
- BioCLIP: A Vision Foundation Model for the Tree of Life2024
- Improved Baselines with Visual Instruction Tuning2024
- Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation2024
- GLaMM: Pixel Grounding Large Multimodal Model2024
- Evaluating Performance and Trends in Interactive Video Retrieval: Insights From the 12th VBS CompetitionIEEE Access, 2024
- Marine Video Kit: A New Marine Video Dataset for Content-Based Analysis and Retrieval2023
- Actor and Action Video Segmentation from a Sentence2018
- CIDEr: Consensus-based image description evaluation2015