Analysis of Image Captioning Models
-
Updated
Aug 6, 2017 - Python
Analysis of Image Captioning Models
Augment the MS COCO training set while training NIC
We aim to generate realistic images from text descriptions using GAN architecture. The network that we have designed is used for image generation for two datasets: MSCOCO and CUBS.
A Clone version from Original SegCaps source code with enhancements on MS COCO dataset.
An easy implementation of FPN (https://arxiv.org/pdf/1612.03144.pdf) in PyTorch.
A demo for mapping class labels from ImageNet to COCO.
The pytorch implementation on “Fine-Grained Image Captioning with Global-Local Discriminative Objective”
Object-Detection API using MSCOCO dataset & using customized dataset from tensorflow
An easy implementation of Faster R-CNN (https://arxiv.org/pdf/1506.01497.pdf) in PyTorch.
Code Repository for "A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video" [Pattern Recognition, Elsevier 2020]
Image caption generation using GRU-based attention mechanism
Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval [ECCV 2020]
MS COCO captions in Arabic
Caption generation from images using topics as additional guiding inputs.
Using LSTM or Transformer to solve Image Captioning in Pytorch
A simple Python API (built on top of TensorFlow) for neural image captioning with MSCOCO data.
A python based tool for looking things up in coco
Convert segmentation binary mask images to COCO JSON format.
NLP - descriptive statistics of COCO annotations via Python COCO-API
Add a description, image, and links to the mscoco-dataset topic page so that developers can more easily learn about it.
To associate your repository with the mscoco-dataset topic, visit your repo's landing page and select "manage topics."