We propose a new paradigm to automatically generate training data with accurate labels at
scale using the text-toimage synthesis frameworks (eg, DALL-E, Stable Diffusion, etc.). The …

In recent years, remarkable achievements have been made in artificial intelligence tasks
and applications based on deep neural networks (DNNs), especially in the fields of vision …

Training computer vision models usually requires collecting and labeling vast amounts of
imagery under a diverse set of scene configurations and properties. This process is …

We investigate the contributions of three important features of the human visual system
(HVS)—shape, texture, and color—to object classification. We build a humanoid vision …

Person re-identification (Re-ID) in real-world scenarios suffers from various degradations,
eg, low resolution, weak lighting, and bad weather. These degradations hinders identity …

We propose a new paradigm to automatically generate training data with accurate labels at
scale using the text-to-image synthesis frameworks (eg, DALL-E, Stable Diffusion, etc.). The …

Recently, many researchers have made remarkable achievements in the field of artistic font
synthesis, with impressive glyph style and effect style in the results. However, due to less …

This paper presents a novel approach to enhance image-to-image generation by leveraging
the multimodal capabilities of the Large Language and Vision Assistant (LLaVA). We …

For decades, gait has been gathering extensive interest due to the advantage that it can be
measured from a distance without physical contact. However, for image/video-based gait …

We present juxtaform, a novel approach to the interactive summarization of large shape
collections for conceptual shape design. We conduct a formative study to ascertain design …