Related papers: A simple projective setup to study optical cloakin…
Open-vocabulary object detection (OVD), detecting specific classes of objects using only their linguistic descriptions (e.g., class names) without any image samples, has garnered significant attention. However, in real-world applications,…
The synthesis of non-magnetic 2D dielectric cloaks as proper solutions of an inverse scattering problem is addressed in this paper. Adopting the relevant integral formulation governing the scattering phenomena, analytic and numerical…
In elasticity, the design of a cloaking for an inclusion or a void to leave a vibrational field unperturbed by its presence, so to achieve its invisibility, is a thoroughly analyzed, but still unchallenged, mechanical problem. The 'cloaking…
Light has many properties that vision sensors can passively measure. Colour-band separated wavelength and intensity are arguably the most commonly used for monocular 6D object pose estimation. This paper explores how complementary…
Image recognition is a classic and common task in the computer vision field, which has been widely applied in the past decade. Most existing methods in literature aim to learn discriminative features from labeled images for classification,…
Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution, which is far from reality. In this paper, we propose…
Estimating accurate 3D locations of objects from monocular images is a challenging problem because of lacking depth. Previous work shows that utilizing the object's keypoint projection constraints to estimate multiple depth candidates…
In this paper, we present the design of cylindrical and spherical electromagnetic cloaks working at visible frequencies. The cloak design is based on the employment of layered structures consisting of alternating plasmonic and non-plasmonic…
We show a design method of cloaking devices which work for target objects with arbitrary shape and material by a topology optimisation with an accurate and efficient sensitivity analysis. Most of past researches on topology optimisation of…
The design rules of transformation optics generally lead to spatially inhomogeneous and anisotropic impedance-matched magneto-dielectric material distributions for, e.g., free-space invisibility cloaks. Recently, simplified anisotropic…
Out-of-distribution (OOD) object detection is an important yet underexplored task. A reliable object detector should be able to handle OOD objects by localizing and correctly classifying them as OOD. However, a critical issue arises when…
Handling object interaction is a fundamental challenge in practical multi-object tracking, even for simple interactive effects such as one object temporarily occluding another. We formalize the problem of occlusion in tracking with two…
Human perception involves decomposing complex multi-object scenes into time-static object appearance (i.e., size, shape, color) and time-varying object motion (i.e., position, velocity, acceleration). For machines to achieve human-like…
We have designed and built a new type of CCD that we call an orthogonal transfer CCD (OTCCD), which permits parallel clocking horizontally as well as vertically. The device has been used successfully to remove image motion caused by…
Rendering objects invisible to impinging acoustic waves (cloaking) and creating acoustic illusions (holography) has been attempted using active and passive approaches. While passive methods are applicable only to narrow frequency bands,…
One-Class Classification (OCC) is a special case of multi-class classification, where data observed during training is from a single positive class. The goal of OCC is to learn a representation and/or a classifier that enables recognition…
Camouflaged Object Detection (COD) aims to identify objects that blend seamlessly into their surroundings. The inherent visual complexity of camouflaged objects, including their low contrast with the background, diverse textures, and subtle…
The ability to control electromagnetic fields, heat currents, electric currents, and other physical phenomena by coordinate transformation methods has resulted in novel functionalities, such as cloaking, field rotations, and concentration…
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built. Recent work on simple 2D and 3D datasets has shown that models…
We study object hallucination in Multimodal Large Language Models (MLLMs) and improve visual contrastive decoding (VCD) by constructing an object-aligned auxiliary view. We leverage object-centric attention in self-supervised Vision…