Related papers: Advancing Chart Question Answering with Robust Cha…

Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal large language models…

High-cardinality categorical features are a common characteristic of mixed-type tabular datasets. Existing generative model architectures struggle to learn the complexities of such data at scale, primarily due to the difficulty of…

Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by…

Medical Visual Question Answering (MedVQA) aims to answer medical questions according to medical images. However, the complexity of medical data leads to confounders that are difficult to observe, so bias between images and questions is…

With the development of deep learning techniques and large scale datasets, the question answering (QA) systems have been quickly improved, providing more accurate and satisfying answers. However, current QA systems either focus on the…

The remarkable growth and significant success of machine learning have expanded its applications into programming languages and program analysis. However, a key challenge in adopting the latest machine learning methods is the representation…

Vision-Language (VL) models have gained significant research focus, enabling remarkable advances in multimodal reasoning. These architectures typically comprise a vision encoder, a Large Language Model (LLM), and a projection module that…

Today, the acquisition of various behavioral log data has enabled deeper understanding of customer preferences and future behaviors in the marketing field. In particular, multimodal deep learning has achieved highly accurate predictions by…

Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or…

Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class of foundation encoders for graph-structured data, have shown…

Time series forecasting requires capturing patterns across multiple temporal scales while maintaining computational efficiency. This paper introduces AWGformer, a novel architecture that integrates adaptive wavelet decomposition with…

Recently, the Visual Question Answering (VQA) task has gained increasing attention in artificial intelligence. Existing VQA methods mainly adopt the visual attention mechanism to associate the input question with corresponding image regions…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Understanding structure-property relationships in complex materials requires integrating complementary measurements across multiple length scales. Here we propose an interpretable "multimodal" machine learning framework that unifies…

Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation and attribute recognition. Contrary to the previous works…

Data visualization in the form of charts plays a pivotal role in data analysis, offering critical insights and aiding in informed decision-making. Automatic chart understanding has witnessed significant advancements with the rise of large…

Answering semantically-complicated questions according to an image is challenging in Visual Question Answering (VQA) task. Although the image can be well represented by deep learning, the question is always simply embedded and cannot well…

Despite the improvements in perception accuracies brought about via deep learning, developing systems combining accurate visual perception with the ability to reason over the visual percepts remains extremely challenging. A particular…

Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning…

The growing reliance of machine learning models in high-stakes, highly regulated domains such as finance and insurance has created a growing tension between predictive performance, interpretability, and regulatory fairness requirements. In…