Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is considered as a challenging problem since i) no supervision is given to the reasoning process and ii) high-order semantics of multi-hop knowledge facts need to be captured. In this paper, we introduce a concept of hypergraph to encode high-level semantics of a question and a knowledge base, and to learn high-order associations between them. The proposed model, Hypergraph Transformer, constructs a question hypergraph and a query-aware knowledge hypergraph, and infers an answer by encoding inter-associations between two hypergraphs and intra-associations in both hypergraph itself. Extensive experiments on two knowledge-based visual QA and two knowledge-based textual QA demonstrate the effectiveness of our method, especially for multi-hop reasoning problem. Our source code is available at https://github.com/yujungheo/kbvqa-public.

In this work, we propose the application of abstract meaning representation (AMR) based semantic parsing models to parse textual descriptions of a visual scene into scene graphs, which is the first work to the best of our knowledge. Previous works examined scene graph parsing from textual descriptions using dependency parsing and left the AMR parsing approach as future work since sophisticated methods are required to apply AMR. Hence, we use pre-trained AMR parsing models to parse the region descriptions of visual scenes (i.e. images) into AMR graphs and pre-trained language models (PLM), BART and T5, to parse AMR graphs into scene graphs. The experimental results show that our approach explicitly captures high-level semantics from textual descriptions of visual scenes, such as objects, attributes of objects, and relationships between objects. Our textual scene graph parsing approach outperforms the previous state-of-the-art results by 9.3% in the SPICE metric score.

Recent GAN-based text-to-image generation models have advanced that they can generate photo-realistic images matching semantically with descriptions. However, research on multi-lingual text-to-image generation has not been carried out yet much. There are two problems when constructing a multilingual text-to-image generation model: 1) language imbalance issue in text-to-image paired datasets and 2) generating images that have the same meaning but are semantically inconsistent with each other in texts expressed in different languages. To this end, we propose a Language-agnostic Semantic Consistent Generative Adversarial Network (LaSC-GAN) for text-to-image generation, which can generate semantically consistent images via language-agnostic text encoder and Siamese mechanism. Experiments on relatively low-resource language text-image datasets show that the model has comparable generation quality as images generated by high-resource language text, and generates semantically consistent images for texts with the same meaning even in different languages.

Scene graph is a graph representation that explicitly represents high-level semantic knowledge of an image such as objects, attributes of objects and relationships between objects. Various tasks have been proposed for the scene graph, but the problem is that they have a limited vocabulary and biased information due to their own hypothesis. Therefore, results of each task are not generalizable and difficult to be applied to other down-stream tasks. In this paper, we propose Entity Synset Alignment(ESA), which is a method to create a general scene graph by aligning various semantic knowledge efficiently to solve this bias problem. The ESA uses a large-scale lexical database, WordNet and Intersection of Union (IoU) to align the object labels in multiple scene graphs/semantic knowledge. In experiment, the integrated scene graph is applied to the image-caption retrieval task as a down-stream task. We confirm that integrating multiple scene graphs helps to get better representations of images.