Scientific Paper · source-verified

Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition

Xi, Xinyu; Yang, Hua; Zhang, Shentai; Liu, Yijie; Sun, Sijin; Fu, Xiuju · 2025-03-10

This paper presents a multimodal AI framework integrating image data, textual descriptions, and classification vectors from a Multimodal Large Language Model (MLLM) to enhance maritime multi-scene recognition, achieving 98% accuracy while optimizing deployment for resource-constrained Autonomous Surface Vehicles (ASVs) in marine conservation, environmental monitoring, and disaster response.

Show citation

Xi, Xinyu; Yang, Hua; Zhang, Shentai; Liu, Yijie; Sun, Sijin; Fu, Xiuju. 2025-03-10. Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition. https://arxiv.org/abs/2503.06978v1 (AI & Environment Resource Hub; record paper-148; collection snapshot 2026-09-15).

Classification and context

Included in the original Scientific Paper collection. Labels below are metadata based suggestions. They are not verified findings, claims of effectiveness, or endorsements.

pathway

topic

lifecycle

orientation

Definitions, inclusion guidance, and examples →

Available source metadata

Author or creator
Xi, Xinyu; Yang, Hua; Zhang, Shentai; Liu, Yijie; Sun, Sijin; Fu, Xiuju
Publisher
arXiv
Publication date
2025-03-10
Date precision
day
Geographic scope
Unknown
Language
unknown
Peer review
unknown
Source status
verified
Last verified
2026-09-15T16:44:35.111Z
Snapshot import
2026-09-06
Legacy domain
Water & Oceans
Legacy subdomain
Multimodal Detection for Maritime Applications with Intelligent Maritime Robotics
journal
arXiv

Provenance and review

Source sheet: Scientific Paper · Row 152 · Original ID: paper-148.

View source spreadsheet ↗

A paper listing is not a quality assessment. Peer review and findings require source-level confirmation. Source link reachable · checked 2026-09-15. Source identity and required metadata verified. The import date is not the original date added.

Suggest a correction for this record →

Related through shared environmental topics

Ordered by the number of shared provisional topic labels. This indicates a browsing connection, not agreement between sources.

Shared topics: Cross-cutting sustainability; Water; Biodiversity and ecosystems; Oceans and coasts

Shared topics: Water; Biodiversity and ecosystems; Oceans and coasts; Transport and logistics

Shared topics: Cross-cutting sustainability; Water; Biodiversity and ecosystems; Oceans and coasts

Tool

European Digital Twin Ocean (EDITO)

Welcome to the core infrastructure of the European Digital Twin Ocean. EDITO offers cutting edge tools to develop digital twins, support science-based decision making, and ensure maximum impact for research and innovation actions across the key objectives of the EU Mission Ocean & Waters: protect biodiversity, stop marine pollution, and support a sustainable blue economy.

EDITOfree

Shared topics: Cross-cutting sustainability; Water; Biodiversity and ecosystems; Oceans and coasts

Scientific Paper · 2024-10-01

SLAGREEF: Preliminary Results on Slag-Based Artificial Reef Design

The SLAGREEF project explores the use of slag furnace residues and inert waste to 3D-print artificial reefs, aiming to protect coastal areas and restore marine ecosystems, with ongoing monitoring at the Obsea underwater observatory.

UP Commons