captioning-images 开源项目推荐（198 个）

peteanderson80 /bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

TheShadow29 /awesome-grounding

awesome grounding: A curated list of research papers in visual grounding

aimagelab /meshed-memory-transformer

[CVPR 2020] Meshed-Memory Transformer for Image Captioning

optas /artemis

Learning to ground explanations of affect for visual art.

dabasajay /Image-Caption-Generator

A neural network to generate captions for an image using CNN and RNN with BEAM Search.

aimagelab /show-control-and-tell

[CVPR 2019] Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions

anuragmishracse /caption_generator

A modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.

peteanderson80 /Up-Down-Captioner

Automatic image captioning model based on Caffe, using features from bottom-up attention.

amanchadha /stanford-cs231n-assignments-2020

This repository contains my solutions to the assignments for Stanford's CS231n "Convolutional Neural Networks for Visual Recognition" (Spring 2020).

InternScience /OmniCaptioner

Official Repository of OmniCaptioner

vinitshahdeo /Hashtagify

📸 Generates hashtags for Instagram posts. Upload your photo and it will suggest the relevant #hashtags for you. 🏷️

peteanderson80 /SPICE

Semantic Propositional Image Caption Evaluation

neural-nuts /image-caption-generator

[DEPRECATED] A Neural Network based generative model for captioning images using Tensorflow

Pikselkroken /pixlstash

Desktop image library for photographers and creators. Search by content, face or the text in a picture, get help from local AI models to tag and organise your images. Connect ComfyUI to generate and edit pictures, and AI-toolkit to train LoRAs. Also runs as a headless server.

mitvis /vistext

VisText is a benchmark dataset for semantically rich chart captioning.

vavo /lora-pilot

From dataset to trained LoRA to finished image or video. One browser workspace for your models, datasets, training, and generation. LoRA Pilot supports 50+ training model groups, with ComfyUI, Kohya, AI Toolkit, and Diffusion Pipe included. Run on your own GPU or RunPod, and connect AI agents through MCP.

SiliconeShojo /TagForge

Advanced AI tagging and prompt generation studio.

harsh19 /spot-the-diff

EMNLP 2018. Learning to Describe Differences Between Pairs of Similar Images. Harsh Jhamtani, Taylor Berg-Kirkpatrick.

aimagelab /pacscore

[CVPR 2023 & IJCV 2025] Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

Nenotriple /img-txt_viewer

Windows工具，用于并排图片与文本浏览、手动标题/标签编辑以及批量数据集操作。 非常适合LoRA和机器学习数据集准备，完全离线，私密且易于使用。