Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

UVMulti: A Large-scale Benchmark Dataset for Underwater Video-level Multi-task Learning.

Yuxin Li¹, Yuxiang Zhang¹, Zhibin Yu^2,3

¹College of Electronic Engineering, Ocean University of China, Qingdao, 266520, Shandong, China.

Scientific Data

|May 11, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Buoyancy and Stability for Submerged and Floating Bodies

Buoyancy and Stability for Submerged and Floating Bodies

In fluid mechanics, buoyancy and stability are key concepts for understanding the behavior of submerged and floating bodies. When a stationary body is fully or partially submerged in a fluid, the fluid exerts a force on the body known as the buoyant force. This force acts vertically upward through a point called the center of buoyancy, which is the center of the displaced fluid volume. According to Archimedes' principle, the magnitude of the buoyant force is equal to the weight of the fluid...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Lead-free Cs<sub>3</sub>MnCl<sub>5</sub> and CsMnCl<sub>3</sub> crystals: rapid on-chip crystallization, phase transition and fluorescence sensing applications.

Physical chemistry chemical physics : PCCP·2026

Same author

From lifespan extension to hallmark-informed gerotherapeutic prioritization: A bibliometric-guided, strategy-oriented review of anti-aging drug research.

Ageing research reviews·2026

Same author

Integrated transcriptomic analysis reveals key regulatory mechanisms of HIPK2 in osteoarthritis and identifies potential therapeutic target drugs.

Medicine·2026

Same author

An oral berberine nanocapsule platform orchestrates microbiota for potent gastric cancer chemotherapy.

Journal of nanobiotechnology·2026

Same author

Immune cell-intrinsic STING activation drives tumor ferroptosis via AA-mediated suppression of ACSL4 lactylation in colorectal cancer.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

LiteMFT: Lightweight Multi-Modal Fine-Tuning for Semantic Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Establishment of comparative transcriptome dataset related to nitrogen use efficiency in melon.

Scientific data·2026

Same journal

A chromosome-level reference genome assembly of the King Ratsnake (Elaphe carinata).

Scientific data·2026

Same journal

A six-week longitudinal dataset of wearable and self-reported stress measurements in working adults.

Scientific data·2026

Same journal

A Multi-Regional Single-nucleus Atlas of the Huntington's Disease Brain.

Scientific data·2026

Same journal

A multimodal speech-production dataset with time-aligned articulography, EEG, audio, and vocal-tract anatomy.

Scientific data·2026

Same journal

A Wearable Motion Capture Dataset for Gait Analysis Using IMUs and Shank-Mounted Egocentric Cameras.

Scientific data·2026

See all related articles

Researchers introduce UVMulti, the first large-scale underwater dataset for multi-task learning. This benchmark aids developing advanced underwater vision systems by providing diverse annotations and a novel framework.

Area of Science:

Computer Vision
Robotics
Marine Technology

Background:

Multi-task learning shows promise for underwater vision tasks.
Lack of large-scale, annotated datasets hinders underwater multi-task learning research.

Purpose of the Study:

Introduce UVMulti, the first large-scale, high-resolution underwater video benchmark for multi-task learning.
Provide a comprehensive dataset with pixel-level segmentation, image enhancement, and depth annotations.

Main Methods:

Developed UVMT-Net, a multi-task learning framework integrating various paradigms.
Implemented an adaptive task weight adjustment (AWA) strategy to optimize performance.

Main Results:

The UVMulti dataset contains 100 video sequences (87,352 frames).

Related Experiment Videos

UVMT-Net framework effectively utilizes limited annotated data for improved multi-task performance.

AWA strategy enhances main task performance while preserving auxiliary task performance.

Conclusions:

UVMulti serves as a robust benchmark for advancing underwater multi-task learning.
The proposed methods offer a viable approach for real-world underwater vision applications.