This work investigates the potential of seam carving as a feature pooling technique within Convolutional Neural Networks (CNNs) for image classification tasks. We propose replacing the traditional max pooling layer with a seam carving operation. Our...
Feb 6, 2026 · Rock, in geology, naturally occurring and coherent aggregate of one or more minerals. Such aggregates constitute the basic unit of which the solid Earth is composed and typically form …
Python implementation of KNN and DTW classification algorithm (⭐ 790)
Head pose estimation is a crucial problem for many tasks, such as driver attention, fatigue detection, and human behaviour analysis. It is well known that neural networks are better at handling classification problems than regression problems. It is...
This project implements a Squeeze-and-Excitation Residual Network (SE-ResNet) to solve a fine-grained classification problem on 32 × 32 images. It addresses signal-to-noise challenges in low-resolution data. (⭐ 0)
Convolutional Neural Networks (CNNs) have revolutionized image classification by extracting spatial features and enabling state-of-the-art accuracy in vision-based tasks. The squeeze and excitation network proposed module gathers channelwise represen...
We construct an infinite sequence of projectively flat manifolds by using castling transformations of prehomogeneous vector spaces. We also give a classification of manifolds equipped with a flat projective structure obtained by a finite number of ca...
Squad Main team Equipa B U23 You are here Home Football Main team Squad Squad Results Classification Calendar Trophies Goalkeeper 1 Rui Silva 12 João Virgínia 41 ...
This paper addresses the difficult problem of finding an optimal neural architecture design for a given image classification task. We propose a method that aggregates two main results of the previous state-of-the-art in neural architecture search. Th...
Thoracic disease detection from chest radiographs using deep learning methods has been an active area of research in the last decade. Most previous methods attempt to focus on the diseased organs of the image by identifying spatial regions responsibl...
Extracting fashion attributes from images of people wearing clothing/fashion accessories is a very hard multi-class classification problem. Most often, even catalogues of fashion do not have all the fine-grained attributes tagged due to prohibitive c...
A picture is worth a thousand words. Albeit a cliché, for the fashion industry, an image of a clothing piece allows one to perceive its category (e.g., dress), sub-category (e.g., day dress) and properties (e.g., white colour with floral patterns)....
Aeacus Rhadamanthus Four Princes of devils in the elements: Samael: Fire Azrael: Water Azazel: Air Mahazael: Earth Four Princes of spirits, upon the four
Finding a set of nested partitions of a dataset is useful to uncover relevant structure at different scales, and is often dealt with a data-dependent methodology. In this paper, we introduce a general two-step methodology for model-based hierarchical...
We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions. In this setting, every time before the learner observes a sample, the adversary decides whether to corrupt the la...
Open source software is a rapidly evolving center for distributed work, and understanding the characteristics of this work across its different contexts is vital for informing policy, economics, and the design of enabling software. The steep increase...
Data streams are often defined as large amounts of data flowing continuously at high speed. Moreover, these data are likely subject to changes in data distribution, known as concept drift. Given all the reasons mentioned above, learning from streams...
Machine learning models that aim to predict dementia onset usually follow the classification methodology ignoring the time until an event happens. This study presents an alternative, using survival analysis within the context of machine learning tech...
The autonomous automotive industry is one of the largest and most conventional projects worldwide, with many technology companies effectively designing and orienting their products towards automobile safety and accuracy. These products are performing...
We propose a Concentrated Document Topic Model(CDTM) for unsupervised text classification, which is able to produce a concentrated and sparse document topic distribution. In particular, an exponential entropy penalty is imposed on the document topic...