Related papers: Beyond Gaussian Pyramid: Multi-skip Feature Stacki…

We propose a novel strategy for extracting features in supervised learning that can be used to construct a classifier which is more robust to small perturbations in the input space. Our method builds upon the idea of the information…

Deepfake technology poses a significant threat to security and social trust. Although existing detection methods have shown high performance in identifying forgeries within datasets that use the same deepfake techniques for both training…

Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often…

This paper addresses the problem of dynamic scene surface reconstruction using Gaussian Splatting (GS), aiming to recover temporally consistent geometry. While existing GS-based dynamic surface reconstruction methods can yield superior…

We introduce MIGS (Multi-Identity Gaussian Splatting), a novel method that learns a single neural representation for multiple identities, using only monocular videos. Recent 3D Gaussian Splatting (3DGS) approaches for human avatars require…

Recently, logo detection has received more and more attention for its wide applications in the multimedia field, such as intellectual property protection, product brand management, and logo duration monitoring. Unlike general object…

Modeling the evolution of high-dimensional systems from limited snapshot observations at irregular time points poses a significant challenge in quantitative biology and related fields. Traditional approaches often rely on dimensionality…

Gaussian splatting (GS) along with its extensions and variants provides outstanding performance in real-time scene rendering while meeting reduced storage demands and computational efficiency. While the selection of 2D images capturing the…

Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning…

Feature selection and instance selection are two important techniques of data processing. However, such selections have mostly been studied separately, while existing work towards the joint selection conducts feature/instance selection…

This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions…

Selecting subsets of features that differentiate between two conditions is a key task in a broad range of scientific domains. In many applications, the features of interest form clusters with similar effects on the data at hand. To recover…

Choosing which properties of the data to use as input to multivariate decision algorithms -- a.k.a. feature selection -- is an important step in solving any problem with machine learning. While there is a clear trend towards training…

Unsupervised skeleton based action recognition has achieved remarkable progress recently. Existing unsupervised learning methods suffer from severe overfitting problem, and thus small networks are used, significantly reducing the…

Feature Transformation is crucial for classic machine learning that aims to generate feature combinations to enhance the performance of downstream tasks from a data-centric perspective. Current methodologies, such as manual expert-driven…

The rapid advancement of face forgery techniques has introduced a growing variety of forgeries. Incremental Face Forgery Detection (IFFD), involving gradually adding new forgery data to fine-tune the previously trained model, has been…

With the growing application of transformer in computer vision, hybrid architecture that combine convolutional neural networks (CNNs) and transformers demonstrates competitive ability in medical image segmentation. However, direct fusion of…

In this study, a new Stacked Generalization technique called Fuzzy Stacked Generalization (FSG) is proposed to minimize the difference between N -sample and large-sample classification error of the Nearest Neighbor classifier. The proposed…

As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…

Score-based stochastic denoising models have recently been demonstrated as powerful machine learning tools for conditional and unconditional image generation. The existing methods are based on a forward stochastic process wherein the…