论文阅读:Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval 技术标签: 论文阅读 计算机视觉 人工智能多义词的视觉语义的嵌入式交叉检索,来自 CVPR 2019 项目地址 摘要 视觉嵌入的目标是找到一个共享的空间,在这个空间中相关的视觉和文本彼此之间比较接近。当前大多数方法都学习将实例映射到
Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared space. Unfortunately, injective embedding cannot effectively ha...
This repository contains a PyTorch implementation of the PVSE network and the MRW dataset proposed in our paperPolysemous Visual-Semantic Embedding for Cross-Modal Retrieval(CVPR 2019). The code and data are free to use foracademic purposes only. ...