flickr30k 开源项目推荐（26 个）

awsaf49 /flickr-dataset

Download flickr8k, flickr30k image caption datasets

UCSB-AI /ComCLIP

NAACL 2024 论文《ComCLIP：无训练合成图像与文本匹配》的官方实现和数据集

nirajankarki5 /Flickr30k-Image-Caption-Generator-Using-Deep-Learning

A deep learning model that generates descriptions of an image.

nssharmaofficial /image-caption-generator

Image captioning model with Resnet50 encoder and LSTM decoder

Delphboy /karpathy-splits

Karpathy Splits json files for image captioning

KimRass /CLIP

PyTorch implementation of 'CLIP' (Radford et al., 2021) from scratch and training it on Flickr8k + Flickr30k

thisisankit27 /SnapSpeak

Visual Elocution Synthesis

franciszekparma /Word2Vec

From-scratch Word2Vec (skip-gram with negative sampling) fully implemented in PyTorch

Sh-31 /ImgCap

ImgCap is an image captioning model designed to automatically generate descriptive captions for images. It has two versions CNN + LSTM model and CNN + LSTM + Attention mechanism model.

RazerArdi /Knowledge-Infused-Multimodal-Retrieval-A-RAG-Based-Approach-for-Context-Aware-Image-Understanding

A modular RAG-based framework for image retrieval and context-aware generation using visual and textual queries. Combines pretrained encoders, vector search, and generative models. Evaluated on Flickr30k for captioning and retrieval tasks.

HanCai98 /Flickr30k-Dataset

Preprocess the Flickr30k dataset

adas0910 /densecap-flickr30K-entities

Processing data produced by flickr30k_entities to use as regional description for densecap model

spoluan /flickr30k-image-captioning

"Flickr30k_image_captioning" is a project or repository focused on image captioning using the Flickr30k dataset. The project aims to develop and showcase algorithms and models that generate descriptive captions for images.

harshrameshnerkar /Image-Caption-Generator

🖼️ Deep Learning Image Caption Generator powered by CNN (ResNet50), RNN/LSTM & Vision Transformer (ViT) with multi-style narrative generation and interactive Flask UI.

bikhanal /clip-openai

Implementation of CLIP from OpenAI using pretrained Image and Text Encoders.

GrainRain0203 /flickr30k-image-captioning-scst

PyTorch Flickr30k image captioning with ResNet/ConvNeXt encoders, Attention-LSTM/Transformer decoders, beam search, and CIDEr-oriented SCST.

AbdelrahmanSaadIdress /visual-attention-captioner

PyTorch image captioning: ResNet50 encoder + Bahdanau attention + LSTM decoder, trained in two stages — cross-entropy warmup then CIDEr-optimized Self-Critical Sequence Training (SCST). Outperforms Show, Attend and Tell (Xu et al., 2015) on Flickr30k. Gradio demo included.

spoortimorabad /ImageCaptioningGeneration-Using-Swin-Transformer-and-GRU-attention-Mechansim

Image captioning generation using Swin transformer and GRU attention mechanism

NafisSaleh /AI-Accessibility-Extension-For-Visually-Impaired-Users

This project aims to provide real-time visual-to-audio conversion, empowering visually impaired users by describing images through generated captions and synthesized audio. The system employs a Transformer-based image captioning model and integrates with a browser extension for seamless functionality.

TahaUser5 /image-captioning-flickr30k

Image captioning model using InceptionV3 + LSTM trained on Flickr30k dataset — generates natural language descriptions for images with BLEU-1 evaluation.