Year: 2025
Type: conference-paper
Abstract: This paper presents a novel framework for vision-aided unsupervised constituency parsing (VUCP), leveraging multimodal large language models (MLLMs) pre-trained on diverse image-text or video-text data.Unlike previous methods requiring explicit cross-modal alignment, our approach eliminates this need by using pre-trained models like Qwen-VL and VideoLLaVA, which seamlessly handle multimodal inputs.We introduce two multi-agent debating mechanisms-consensus-driven (CD) and round-driven (RD)-to enable cooperation between models with complementary strengths.Extensive experiments demonstrate that our approach achieves state-of-the-art performance on both image-text and video-text datasets for VUCP, improving robustness and accuracy.
Authors: Dong Zhang, Haiyan Tian, Qingying Sun, Shoushan Li
Institutions: Soochow University, Huaiyin Normal University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Awards: G1397134175, G7939979782
OpenAlex ID: W4412888612