Web-Scale Multimodal Summarization using CLIP-Based Semantic Alignment
This work provides a configurable, deployable tool for web-scale multimodal summarization, which is incremental as it integrates existing models like CLIP and BLIP into a lightweight framework.
The paper tackles the problem of generating summaries by combining retrieved text and image data from web sources, achieving a ROC-AUC of 0.9270, an F1-score of 0.6504, and an accuracy of 96.99% on evaluation with 500 image-caption pairs.
We introduce Web-Scale Multimodal Summarization, a lightweight framework for generating summaries by combining retrieved text and image data from web sources. Given a user-defined topic, the system performs parallel web, news, and image searches. Retrieved images are ranked using a fine-tuned CLIP model to measure semantic alignment with topic and text. Optional BLIP captioning enables image-only summaries for stronger multimodal coherence.The pipeline supports features such as adjustable fetch limits, semantic filtering, summary styling, and downloading structured outputs. We expose the system via a Gradio-based API with controllable parameters and preconfigured presets.Evaluation on 500 image-caption pairs with 20:1 contrastive negatives yields a ROC-AUC of 0.9270, an F1-score of 0.6504, and an accuracy of 96.99%, demonstrating strong multimodal alignment. This work provides a configurable, deployable tool for web-scale summarization that integrates language, retrieval, and vision models in a user-extensible pipeline.