In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT).
Deep learning methods have been employed in gravitational-wave astronomy to accelerate the construction of surrogate waveforms for the inspiral of spin-aligned black hole binaries, among other applications.
In this paper, regularized lightweight deep convolutional neural network models, capable of effectively operating in real-time on devices with restricted computational power for high-resolution video input are proposed.
Knowledge Distillation has been established as a highly promising approach for training compact and faster models by transferring knowledge from heavyweight and powerful models.
Semantic scene segmentation plays a critical role in a wide range of robotics applications, e. g., autonomous navigation.
no code implementations • 9 Jul 2021 • Paraskevi Nousi, Styliani-Christina Fragkouli, Nikolaos Passalis, Panagiotis Iosif, Theocharis Apostolatos, George Pappas, Nikolaos Stergioulas, Anastasios Tefas
Based on this finding, we design a spiral module with learnable parameters, that is used as the first layer in a neural network, which learns to map the input space to the coefficients.
In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on relevant sources of information for the given learning objective.
The proposed method is capable of overcoming the aforementioned limitations by using an appropriate supervision scheme during the different phases of the training process, as well as by designing and training an appropriate auxiliary teacher model that acts as a proxy model capable of "explaining" the way the teacher works to the student.
To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention.
Deep Learning (DL) models can be used to tackle time series analysis tasks with great success.
However, combining existing BoF formulations with deep feature extractors pose significant challenges: the distribution of the input features is not stationary, tuning the hyper-parameters of the model can be especially difficult and the normalizations involved in the BoF model can cause significant instabilities during the training process.
The proposed method is adapted to the needs of large-scale hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI).
Universal Neural Style Transfer (NST) methods are capable of performing style transfer of arbitrary styles in a style-agnostic manner via feature transforms in (almost) real-time.
In order to visualize that data in 2D or 3D, usually Dimensionality Reduction (DR) techniques are employed.
Among the most impressive recent applications of neural decoding is the visual representation decoding, where the category of an object that a subject either sees or imagines is inferred by observing his/her brain activity.
The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems.
Forecasting the movements of stock prices is one the most challenging problems in financial markets analysis.
Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one.
Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks.
The vast majority of Dimensionality Reduction (DR) techniques rely on second-order statistics to define their optimization objective.