Related papers: Dual affine moment invariants
The research on recognizing the most discriminative regions provides referential information for weakly supervised object localization with only image-level annotations. However, the most discriminative regions usually conceal the other…
Differential Dynamic Microscopy (DDM) analyzes traditional real-space microscope images to extract information on sample dynamics in a way akin to light scattering, by decomposing each image in a sequence into Fourier modes, and evaluating…
Differential dynamic microscopy (DDM) is increasingly used in the fields of soft matter physics and biophysics to extract the dynamics of microscopic objects across a range of wavevectors using optical microscopy. Standard DDM is limited to…
LiDAR and camera fusion techniques are promising for achieving 3D object detection in autonomous driving. Most multi-modal 3D object detection frameworks integrate semantic knowledge from 2D images into 3D LiDAR point clouds to enhance…
Time-averaged two-point currents are derived and shown to be spatially invariant within domains of local translation or inversion symmetry for arbitrary time-periodic quantum systems in one dimension. These currents are shown to provide a…
Ultrasound (US) imaging is based on the time-reversal principle, in which individual channel RF measurements are back-propagated and accumulated to form an image after applying specific delays. While this time reversal is usually…
Anomaly detection in multivariate time series has emerged as a crucial challenge in time series research, with significant research implications in various fields such as fraud detection, fault diagnosis, and system state estimation.…
We present a method for dimensionality reduction of an affine variational inequality (AVI) defined over a compact feasible region. Centered around the Johnson Lindenstrauss lemma, our method is a randomized algorithm that produces with high…
RGB-infrared person re-identification is a challenging task due to the intra-class variations and cross-modality discrepancy. Existing works mainly focus on learning modality-shared global representations by aligning image styles or feature…
In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN). By exploiting the observation that a…
Atmospheric Turbulence (AT) degrades the clarity and accuracy of surveillance imagery, posing challenges not only for visualization quality but also for object classification and scene tracking. Deep learning-based methods have been…
Recent studies reveal that deep neural network (DNN) based object detectors are vulnerable to adversarial attacks in the form of adding the perturbation to the images, leading to the wrong output of object detectors. Most current existing…
With the continuous improvements of deepfake methods, forgery messages have transitioned from single-modality to multi-modal fusion, posing new challenges for existing forgery detection algorithms. In this paper, we propose AVT2-DWF, the…
Diffusion Models achieve state-of-the-art performance in generating new samples but lack a low-dimensional latent space that encodes the data into editable features. Inversion-based methods address this by reversing the denoising…
Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge. Some theoretical studies have uncovered that DNNs have preferences for some frequency…
Establishing correspondences is a fundamental task in variety of image processing and computer vision applications. In particular, finding the correspondences between a non-linearly deformed image pair induced by different modality…
Recent advancements in neural network-based optical flow estimation often come with prohibitively high computational and memory requirements, presenting challenges in their model adaptation for mobile and low-power use cases. In this paper,…
We consider the problem of constraining diffusion model outputs with a user-supplied reference image. Our key objective is to extract multiple attributes (e.g., color, object, layout, style) from this single reference image, and then…
Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scenarios. Since data…
Uncovering the underlying ordinary differential equations (ODEs) that govern dynamic systems is crucial for advancing our understanding of complex phenomena. Traditional symbolic regression methods often struggle to capture the temporal…