Text-to-image models offer a new level of creative flexibility by allowing users to guide the
image generation process through natural language. However, using these models to …

Abstract Category-Agnostic Pose Estimation (CAPE) aims to detect keypoints of an arbitrary
unseen category in images, based on several provided examples of that category. This is a …

Abstract We introduce Diff-Tracker, a novel approach for the challenging unsupervised
visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea …

Class-agnostic object counting aims to count objects of arbitrary classes with limited
information (eg., a few exemplars or the class names) provided. It requires the model to …

In-context segmentation has drawn more attention with the introduction of vision foundation
models. Most existing approaches adopt metric learning or masked image modeling to build …

Abstract We present TokenCompose a Latent Diffusion Model for text-to-image generation
that achieves enhanced consistency between user-specified text prompts and model …

Earth Observation imagery can capture rare and unusual events such as disasters and
major landscape changes whose visual appearance contrasts with the usual observations …

We present TokenCompose, a Latent Diffusion Model for text-to-image generation that
achieves enhanced consistency between user-specified text prompts and model-generated …

In this paper, we present the One-shot In-context Part Segmentation (OIParts) framework,
designed to tackle the challenges of part segmentation by leveraging visual foundation …

The Segment Anything Model (SAM) was originally designed for label-agnostic mask
generation. Does this model also possess inherent semantic understanding, of value to …