VSE_Pytorch
VSE_Pytorch copied to clipboard
linxd5
Pytorch implementation of the image-sentence embedding method described in "Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"
I've started a project inspired by this one, feel free to check it out: https://github.com/josharnoldjosh/Image-Caption-Joint-Embedding
Hello, This project looks very useful, except the code does not run with the examples. There are many errors such as with the Xavier Initialization and even `tools_.py` being named...
This paper's main contributions is propose a decoded modal named SC-NLM. In your code, only image-sentence embedding space is show without SC-NLM structure. Maybe you just realize the embedding space?
