Multi-level factorisation net for person re-identification
X Chang, TM Hospedales… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Key to effective person re-identification (Re-ID) is modelling discriminative and view-
invariant factors of person appearance at both high and low semantic levels. Recently …
invariant factors of person appearance at both high and low semantic levels. Recently …
Learning rotation-invariant and fisher discriminative convolutional neural networks for object detection
The performance of object detection has recently been significantly improved due to the
powerful features learnt through convolutional neural networks (CNNs). Despite the …
powerful features learnt through convolutional neural networks (CNNs). Despite the …
Learning a discriminative filter bank within a CNN for fine-grained recognition
Compared to earlier multistage frameworks using CNN features, recent end-to-end deep
approaches for fine-grained recognition essentially enhance the mid-level learning …
approaches for fine-grained recognition essentially enhance the mid-level learning …
Learn to combine modalities in multimodal deep learning
Combining complementary information from multiple modalities is intuitively appealing for
improving the performance of learning-based approaches. However, it is challenging to fully …
improving the performance of learning-based approaches. However, it is challenging to fully …
Scene recognition with prototype-agnostic scene layout
Exploiting the spatial structure in scene images is a key research direction for scene
recognition. Due to the large intra-class structural diversity, building and modeling flexible …
recognition. Due to the large intra-class structural diversity, building and modeling flexible …
StackNet-DenVIS: a multi-layer perceptron stacked ensembling approach for COVID-19 detection using X-ray images
The highly contagious nature of Coronavirus disease 2019 (Covid-19) resulted in a global
pandemic. Due to the relatively slow and taxing nature of conventional testing for Covid-19 …
pandemic. Due to the relatively slow and taxing nature of conventional testing for Covid-19 …
[HTML][HTML] Length of stay prediction for hospital management using domain adaptation
LNW Momo, N Moorosi, EO Nsoesie… - … Applications of Artificial …, 2024 - Elsevier
Anticipating inpatient length of stay (LoS) can be of crucial aid for efficient hospital
management, admissions planning, resource allocation and care quality improvement …
management, admissions planning, resource allocation and care quality improvement …
Deep learning to combat phishing
With the tremendous increase in our dependence on online services for daily needs, cyber
threats and related crime have also increased at an alarming rate. Phishing is one of the …
threats and related crime have also increased at an alarming rate. Phishing is one of the …
Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery
Satellite imagery is being leveraged for many societally critical tasks across climate,
economics, and public health. Yet, because of heterogeneity in landscapes (eg how a road …
economics, and public health. Yet, because of heterogeneity in landscapes (eg how a road …
Feature preserving GAN and multi-scale feature enhancement for domain adaption person re-identification
The performance of person Re-identification (Re-ID) model depends much on its training
dataset, and drops significantly when the detector is applied to a new scene due to the large …
dataset, and drops significantly when the detector is applied to a new scene due to the large …