SGG-Mvar

Cross-modal retrieval is crucial for achieving accurate and efficient information retrieval by establishing semantic correlations between heterogeneous images and text. However, traditional image-text training sets suffer from information asymmetry, which includes short lengths and limited sentence structures. This phenomenon often results in insufficient representations of essential visual information. We introduce RichDataset, which offers extensive semantic information. It includes diverse real-life image-text pairs and AI-generated content across domains such as news, entertainment, education, and posters. Compared with classic benchmarks such as Flickr30k and MS-COCO, RichDataset exhibits a novel and balanced distribution. Existing cross-modal retrieval models face challenges in extracting distinct features from the emerging data, leading to low retrieval accuracy. We propose SGG-MVAR, a comprehensive retrieval model guided by multiview scene information and semantic relationships. Leveraging a scene knowledge database, our model parses scene graphs and identifies differences in attributes and relationships. We conduct extensive experiments to evaluate our proposed dataset and model. All experimental results consistently demonstrate a significant improvement in recall for cross-modal retrieval

Computer vision · Graph · Modal · Advanced Image and Video Retrieval Techniques · Computer Science · Image Retrieval and Classification Techniques · Materials Science · Multimodal Machine Learning Applications · Artificial Intelligence · Theoretical Computer Science

• CDC

  Open Access•Zhaodi Wang, Yangyan Zeng et al.•IEEE Transactions on Computational…•2026

  Incluir item

• Principal component analysis

  Open Access•Svante Wold, Kim H Esbensen et al.•Chemometrics and Intelligent…•1987

  Incluir item

• ImageNet Large Scale Visual Recognition Challenge

  Open Access•Olga Russakovsky, Jia Deng et al.•International Journal of Computer…•2015

  Incluir item