Abstract Model stealing (MS) involves querying and observing the output of a machine
learning model to steal its capabilities. The quality of queried data is crucial yet obtaining a …

Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names
of object classes during testing, without the need for manual annotations. However, a critical …

Few-shot object counting has garnered significant attention for its practicality as it aims to
count target objects in a query image based on given exemplars without additional training …

Domain shift significantly hinders crowd counting performance in unseen domains. Domain
adaptation methods tackle this issue using target domain images but falter when acquiring …

Object localization is a hot issue in computer vision area, which aims to identify and
determine the precise location of specific objects from image or video. Most existing object …

Low-shot object counters estimate the number of objects in an image using few or no
annotated exemplars. Objects are localized by matching them to prototypes, which are …

The newly proposed Generalized Referring Expression Segmentation (GRES) amplifies the
formulation of classic RES by involving multiple/non-target scenarios. Recent approaches …

The multi-volume set of LNCS books with volume numbers 15059 up to 15147 constitutes
the refereed proceedings of the 18th European Conference on Computer Vision, ECCV …

Most successful few-shot counting methods are adapted from density-based counters. They
are trained to fit a unit Gaussian over the area of each target object using the L2 loss. This …