paper-with-me

Papers

Web-Scale Multimodal Summarization using CLIP-Based Semantic Alignment

2026-02-16 · Mounvik K, N Harshit arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.14889

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models

2026-05-12 · Maham Nazir, Muhammad Aqeel, Richong Zhang, Francesco Setti arxiv

Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features trained for object classification, which represent visual concepts as …

Video Summarization

CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment

2025-08-08 · Shengzhu Yang, Jiawei Du, Shuai Lu, Weihang Zhang 외 arxiv

Large-scale natural image-text datasets, especially those automatically collected from the web, often suffer from loose semantic alignment due to weak supervision, while medical datasets tend to have high cross-modal cor…

Contrastive Learning

Set-CLIP: Exploring Aligned Semantic From Low-Alignment Multimodal Data Through A Distribution View

2024-06-09 · Zijia Song, Zelin Zang, Yelin Wang, Guozheng Yang 외

Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances. However, in many specialized fields, it is struggling to obtain sufficient alignment data for trai…

Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment

2022-10-10 · JieLin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt 외

Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding. It plays an essential role in real-world applications, i.e., automatically generating cover images and titl…

Articlesmultimodal interaction

FoCLIP: A Feature-Space Misalignment Framework for CLIP-Based Image Manipulation and Detection

2025-11-10 · Yulin Chen, Zeyuan Wang, Tianyuan Yu, Yingmei Wei 외 arxiv

The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment metric. However, such a CLIP-based metric is vulnerable for its delicate multi…

Image Quality AssessmentImage Manipulation