To create culturally inclusive vision-language models (VLMs), developing a benchmark that tests their ability to address culturally relevant questions is essential. Existing approaches typically rely on human annotators, making the process labor-intensive and creating a cognitive burden in generating diverse questions. To address this, we propose a semi-automated framework for constructing cultural VLM benchmarks, specifically targeting multiple-choice QA. This framework combines human-VLM collaboration, where VLMs generate questions based on guidelines, a small set of annotated examples, and relevant knowledge, followed by a verification process by native speakers. We demonstrate the effectiveness of this framework through the creation of K-Viscuit, a dataset focused on Korean culture. Our experiments on this dataset reveal that open-source models lag behind proprietary ones in understanding Korean culture, highlighting key areas for improvement. We also present a series of further analyses, including human evaluation, augmenting VLMs with external knowledge, and the evaluation beyond multiple-choice QA. Our dataset is available at https://huggingface.co/datasets/ddehun/k-viscuit.

Building a reliable visual question answering (VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts.

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.

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.