# Multimodal model

PP-Chart2Table is a multimodal model developed by the PaddlePaddle team, focusing on Chinese and English chart parsing and capable of efficiently converting charts into data tables.

Gemma 3 is a lightweight, advanced open model series from Google, built on the same research and technology used to create Gemini models. This model is multimodal, capable of processing both text and image inputs to generate text outputs.

Japanese CLIP model trained on OpenCLIP framework, supporting zero-shot image classification tasks

Experimental vision model combining keyword tags with long text descriptions for image prompt generation

A multimodal table detection model fine-tuned from google/paligemma-3b-mix-448, specialized in identifying table regions in images

An image caption generation model fine-tuned on the DocCI dataset based on PaliGemma-3b, capable of generating detailed descriptions of 200-350 characters with reduced hallucination

Compare2Score is a model for image quality assessment that provides a quality score for images through a specific algorithm.

CLIP model based on ViT architecture for zero-shot image classification tasks

SigLIP is a multimodal model pretrained on the WebLi dataset, utilizing an improved Sigmoid loss function, suitable for zero-shot image classification and image-text retrieval tasks.

SigLIP is a vision-language model pre-trained on the WebLi dataset, utilizing an improved sigmoid loss function to enhance performance

SigLIP is a vision-language model pretrained on the WebLi dataset, utilizing an improved sigmoid loss function, excelling in image classification and image-text retrieval tasks.

Chinese CLIP model based on Vision Transformer architecture, supporting cross-modal understanding and generation between images and text.

SigLIP is a vision-language model pretrained on the WebLi dataset, utilizing an improved Sigmoid loss function to optimize image-text matching tasks