Yanhui Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yanhui Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Tian Bai
College of Computer Science and Technology, Ministry of Education, Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun, 130012, China
2 shared publications - Weiqi Zhang
College of Computer Science and Technology, Jilin University, Changchun, China and Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, China
2 shared publications - Zefan Zhang
College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, China
2 shared publications - Kailong Suo
College of Computer Science and Technology, Jilin University, Changchun, China and Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, China
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8537-8546
Video-Level Multimodal Relation Extraction with Event-Entity Semantic Consistency
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8537-8546
Open AccessVideo-Level Multimodal Relation Extraction with Event-Entity Semantic Consistency
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1148-1157
Caption-Aware Multimodal Relation Extraction with Mutual Information Maximization
Multimodal Relation Extraction (MRE) has achieved great improvements. However, modern MRE models are easily affected by irrelevant objects during multimodal alignment which are called error sensitivity issues. The main reason is that visual features are not fully aligned with textual features and the reasoning process may suppress redundant and noisy information at the risk of losing critical information. In light of this, we propose a Caption-Aware Multimodal Relation Extraction Network with Mutual Information Maximization (CAMIM). Specifically, we first generate detailed image captions through the Large Language Model (LLM). Then, the Caption-Aware Module (CAM) hierarchically aligns the fine-grained visual entities and textual entities for reasoning. In addition, for preserving crucial information within different modalities, we leverage a Mutual Information Maximization method to regulate the multimodal reasoning module. Experiments show that our model outperforms the state-of-the-art MRE models on the benchmark dataset MNRE. Further ablation studies prove the pluggable and effective performance of our Caption-Aware Module and Mutual Information Maximization method. Our code is available at https://github.com/zefanZhang-cn/CAMIM.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1148-1157
Open AccessCaption-Aware Multimodal Relation Extraction with Mutual Information Maximization
Multimodal Relation Extraction (MRE) has achieved great improvements. However, modern MRE models are easily affected by irrelevant objects during multimodal alignment which are called error sensitivity issues. The main reason is that visual features are not fully aligned with textual features and the reasoning process may suppress redundant and noisy information at the risk of losing critical information. In light of this, we propose a Caption-Aware Multimodal Relation Extraction Network with Mutual Information Maximization (CAMIM). Specifically, we first generate detailed image captions through the Large Language Model (LLM). Then, the Caption-Aware Module (CAM) hierarchically aligns the fine-grained visual entities and textual entities for reasoning. In addition, for preserving crucial information within different modalities, we leverage a Mutual Information Maximization method to regulate the multimodal reasoning module. Experiments show that our model outperforms the state-of-the-art MRE models on the benchmark dataset MNRE. Further ablation studies prove the pluggable and effective performance of our Caption-Aware Module and Mutual Information Maximization method. Our code is available at https://github.com/zefanZhang-cn/CAMIM.