This is code for Joint Multimodal Entity-Relation Extraction Based on Edge-enhanced Graph Alignment Network and Word-pair Relation Tagging (AAAI 2023)
For the scene graph, we used the method https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch, and thanks
you can get a current dataset in the following website, which is the same dataset used in the AAAI2023 paper https://drive.google.com/drive/folders/1JDWuWN1ClzJBd9FeryJu3XAj7AIC-iRB.
It is worth noting that we merged some samples and now get the V2 version. We recommend you use V2 in your work