Related papers: ChartFormer: A Large Vision Language Model for Con…
Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar…
Recent advancements in computer vision have highlighted the scalability of Vision Transformers (ViTs) across various tasks, yet challenges remain in balancing adaptability, computational efficiency, and the ability to model higher-order…
Diffusion models have shown impressive results in text-to-image synthesis. Using massive datasets of captioned images, diffusion models learn to generate raster images of highly diverse objects and scenes. However, designers frequently use…
This paper explores the effectiveness of Multimodal Large Language models (MLLMs) as assistive technologies for visually impaired individuals. We conduct a user survey to identify adoption patterns and key challenges users face with such…
In this time when biased information, deep fakes, and propaganda proliferate, the accessibility of reliable data sources is more important than ever. National statistical institutes provide curated data that contain quantitative information…
Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token…
Visual Story-Telling is the process of forming a multi-sentence story from a set of images. Appropriately including visual variation and contextual information captured inside the input images is one of the most challenging aspects of…
The integration of visual-tactile stimulus is common while humans performing daily tasks. In contrast, using unimodal visual or tactile perception limits the perceivable dimensionality of a subject. However, it remains a challenge to…
We here propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs).…
In this paper, we present the texture reformer, a fast and universal neural-based framework for interactive texture transfer with user-specified guidance. The challenges lie in three aspects: 1) the diversity of tasks, 2) the simplicity of…
We present a novel platform for the interactive visualization of very large graphs. The platform enables the user to interact with the visualized graph in a way that is very similar to the exploration of maps at multiple levels. Our…
Learning representations in the joint domain of vision and touch can improve manipulation dexterity, robustness, and sample-complexity by exploiting mutual information and complementary cues. Here, we present Visuo-Tactile Transformers…
Data profiling plays a critical role in understanding the structure of complex datasets and supporting numerous downstream tasks, such as social media analytics and financial fraud detection. While existing research predominantly focuses on…
With the wide usage of data visualizations, a huge number of Scalable Vector Graphic (SVG)-based visualizations have been created and shared online. Accordingly, there has been an increasing interest in exploring how to retrieve…
Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights that would otherwise require a lot of cognitive and…
Fraud detection remains a challenging task due to the complex and deceptive nature of fraudulent activities. Current approaches primarily concentrate on learning only one perspective of the graph: either the topological structure of the…
Vision-Language Models (VLMs) have shown promise in generating plotting code from chart images, yet achieving structural fidelity remains challenging. Existing approaches largely rely on supervised fine-tuning, encouraging surface-level…
Visual Programming Tools (VPTs) allow users to create interactive media projects such as games and animations using visual representations of programming concepts. Although VPTs have been shown to have huge potential for teaching children…
While Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities for reasoning and self-correction at the textual level, these strengths provide minimal benefits for complex tasks centered on visual perception, such as…
Recently, the emergence of multitask deep learning models has enhanced catheterization procedures by providing tactile and visual perception data through an end-to-end architecture. This information is derived from a segmentation and force…