PyTorch source code for "Stacked Cross Attention for Image-Text Matching...
Meshed-Memory Transformer for Image Captioning. CVPR 2020
Show, Control and Tell: A Framework for Generating Controllable and Grou...
TOMM2020 Dual-Path Convolutional Image-Text Embedding :feet: https://a...
Code for "Learning the Best Pooling Strategy for Visual Semantic Embeddi...
(RSS 2018) LoST - Visual Place Recognition using Visual Semantics for Op...
PyTorch library for Visual-Semantic tasks