中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
LLM-led vision-spectral fusion: A zero-shot approach to temporal fruit image classification

文献类型：期刊论文

作者Wu, Huyu2; Jia, Bowen3,4; Yuan, Xue-Ming1,5
刊名NEURAL NETWORKS
出版日期2026-02-01
卷号194页码:10
关键词Temporally relevant images Multimodal classification Large language models Zero-shot segmentation Vision-spectral fusion
ISSN号0893-6080
DOI10.1016/j.neunet.2025.108155
英文摘要A zero-shot multimodal framework for temporal image classification is proposed, targeting automated fruit quality assessment. The approach leverages large language models for expert-level semantic description generation, which guides zero-shot object detection and segmentation through GLIP and SAM models. Visual features and spectral data are fused to capture both external appearance and internal biochemical properties of fruits. Experiments on the newly constructed Avocado Freshness Temporal-Spectral dataset-comprising daily synchronized images and spectral measurements across the full spoilage lifecycle-demonstrate reductions in mean squared error by up to 33% and mean absolute error by up to 17% compared to established baselines. These results validate the effectiveness and generalizability of the framework for temporal image analysis in smart agriculture and food quality monitoring.
资助项目Ministry of Education, Singapore[MOE-2019-T3-1-010] ; Fundamental Research Funds for the Central Universities of China[2024ZY-SXT4]
WOS研究方向Computer Science ; Neurosciences & Neurology
语种英语
WOS记录号WOS:001591693900002
出版者PERGAMON-ELSEVIER SCIENCE LTD
源URL[http://119.78.100.204/handle/2XEOYT63/41666]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Jia, Bowen
作者单位1.Natl Univ Singapore, Inst Operat Res & Analyt, Singapore City, Singapore
2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
3.Sichuan Univ, Business Sch, Chengdu, Peoples R China
4.Sichuan Huashi Centralized Procurement & E commerc, Digital Res & Dev Dept, Chengdu, Peoples R China
5.Natl Univ Singapore, Business Sch, Singapore City, Singapore
推荐引用方式
GB/T 7714		 Wu, Huyu,Jia, Bowen,Yuan, Xue-Ming. LLM-led vision-spectral fusion: A zero-shot approach to temporal fruit image classification[J]. NEURAL NETWORKS,2026,194:10.
APA Wu, Huyu,Jia, Bowen,&Yuan, Xue-Ming.(2026).LLM-led vision-spectral fusion: A zero-shot approach to temporal fruit image classification.NEURAL NETWORKS,194,10.
MLA Wu, Huyu,et al."LLM-led vision-spectral fusion: A zero-shot approach to temporal fruit image classification".NEURAL NETWORKS 194(2026):10.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。