Stronger interaction brings better performance: fine-grained alignment between different modalities for MNER
- 28 October 2025
- journal article
- research article
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (16) , 1-26
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (No.62171043, 62202061, No.62171043, 62202061, No.62171043, 62202061, No.62171043, 62202061)
- Natural Science Foundation of Beijing (No.4232025, No.4232025, No.4232025, No.4232025)
- Central Leading Local Project ”Fujian Mental Health Human-Computer Interaction Technology Research Center” (No.2020L3024, No.2020L3024, No.2020L3024, No.2020L3024)
- R&D Program of Beijing Municipal Education commission (No.KM202311232003, KM202311232002, No.KM202311232003, KM202311232002, No.KM202311232003, KM202311232002, No.KM202311232003, KM202311232002)
This publication has 37 references indexed in Scilit:
- Contrastive learning-based place descriptor representation for cross-modality place recognitionInformation Fusion, 2025
- ICKA: An instruction construction and Knowledge Alignment framework for Multimodal Named Entity RecognitionExpert Systems with Applications, 2024
- Dynamic attention augmented graph network for video accident anticipationPattern Recognition, 2023
- Automatic Generation of 3D Scene Animation Based on Dynamic Knowledge Graphs and Contextual EncodingInternational Journal of Computer Vision, 2023
- Exploring Simple Siamese Representation Learning2021
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- A Fast and Accurate One-Stage Approach to Visual Grounding2019
- Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition2019
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- Deep Residual Learning for Image Recognition2016