Recent advances in visual-language models have shown remarkable zero-shot text-image
matching ability that is transferable to downstream tasks such as object detection and …

This paper tackles the problem of object counting in images. Existing approaches rely on
extensive training data with point annotations for each object, making data collection labor …

Class-agnostic object counting aims to count all objects in an image with respect to example
boxes or class names aka few-shot and zero-shot counting. In this paper we propose a …

Our objective is open-world object counting in images, where the target object class is
specified by a text description. To this end, we propose CounTX, a class-agnostic, single …

Class-agnostic object counting aims to count object instances of an arbitrary class at test
time. It is challenging but also enables many potential applications. Current methods require …

Existing counting tasks are limited to the class level which don't account for fine-grained
details within the class. In real applications it often requires in-context or referring human …

Zero-Shot Object Counting~(ZSOC) aims to count referred instances of arbitrary classes in a
query image without human-annotated exemplars. To deal with ZSOC, preceding studies …

Low-shot counters estimate the number of objects corresponding to a selected category
based on only few or no exemplars annotated in the image. The current state-of-the-art …

Abstract Vision-Language models (VLMs), ie, image-text pairs of CLIP, have boosted image-
based Deep Learning (DL). Moreover, Visual-Question-Answer (VQA) tools and open …

Recently, the quality and performance of text-to-image generation significantly advanced
due to the impressive results of diffusion models. However, text-to-image diffusion models …