DF-MobileNetV4: A dual-scale adaptive attention and fused ConvBlock enhanced MobileNetV4 for underwater fish feeding behavior recognition
Authors:
- Bohao ZhangBZBohao Zhang
- Liang WangLWLiang Wang
- Mingbiao WuMWMingbiao Wu
- Zhuhong CheZCZhuhong Che
- Tianyou HuangTHTianyou Huang
- Shuangyin LiuSLShuangyin Liu
- Meng CuiMeng Cui
- Longqin XuLXLongqin Xu
Open Access
- 9 April 2026
- journal article
- Published by Elsevier in Information Processing in Agriculture
Abstract
No abstract availableFunding Information
- Guangzhou Municipal Science and Technology Project (2023E04J1239)
- Guangzhou Municipal Science and Technology Project (2023E04J1238)
- National Natural Science Foundation of China (62373390)
- Natural Science Foundation of Guangdong Province (2024020202)
- Natural Science Foundation of Guangdong Province (2022B1515120059)
This publication has 25 references indexed in Scilit:
- A method for fusing attention mechanism-based ResNet and improved ConvNeXt for analyzing fish feeding behaviorAquaculture International, 2025
- MobileNetV4: Universal Models for the Mobile Ecosystem2024
- Feeding intensity identification method for pond fish school using dual-label and MobileViT-SENetBiosystems Engineering, 2024
- MSIF-MobileNetV3: An improved MobileNetV3 based on multi-scale information fusion for fish feeding behavior analysisAquacultural Engineering, 2023
- A MobileNetV2-SENet-based method for identifying fish school feeding behaviorAquacultural Engineering, 2022
- Effects of Feeding Strategies on Growth Performance of F1 Gulf Coast Striped Bass Strains in Recirculating Aquaculture SystemsNorth American Journal of Aquaculture, 2022
- Fish feeding intensity quantification using machine vision and a lightweight 3D ResNet-GloRe networkAquacultural Engineering, 2022
- Automatic recognition methods of fish feeding behavior in aquaculture: A reviewAquaculture, 2020
- Evaluation of fish feeding intensity in aquaculture using a convolutional neural network and machine visionAquaculture, 2019
- Measuring feeding activity of fish in RAS using computer visionAquacultural Engineering, 2014