Search
Search Results
-
Health and Mobility in the Post-pandemic Scenario. An Analysis of the Adaptation of Sustainable Urban Mobility Plans in Key Contexts of Italy
The combination of concerns about the Covid-19 pandemic and structural problems relating to social injustice, climate change, and public health... -
Adapting on Long-Tail Domains by High Quality Self-training for Object Detection
Domain shift is a critical challenge when we deploy object detectors to real world applications. Due to the data distribution misalignment between... -
Transfer Learning for On-Orbit Ship Segmentation
With the adoption of edge AI processors for space, on-orbit inference on EO data has become a possibility. This enables a range of new applications... -
-
Generalizable person re-identification with part-based multi-scale network
Supervised person re-identification (Re-ID) has advanced significantly, but it suffers from the performance drop when the pretrained models are...
-
Discriminative Feature Adaptation via Conditional Mean Discrepancy for Cross-Domain Text Classification
This paper concerns the problem of Unsupervised Domain Adaptation (UDA) in text classification, aiming to transfer the knowledge from a source domain... -
Impact of Morphology Variations on Evolved Neural Controllers for Modular Robots
Modular robots, in particular those in which the modules are physically interchangeable, are suitable to be evolved because they allow for many... -
Person re-identification based on human semantic parsing and message passing
As an effective method to assist intelligent management of public areas, person re-identification (re-ID) technology has been developed rapidly in...
-
A compact wrist rehabilitation robot with accurate force/stiffness control and misalignment adaptation
Robots have been demonstrated to assist the rehabilitation of patients with upper or lower limb disabilities. To make exoskeleton robots more...
-
A multi-branch attention and alignment network for person re-identification
Person re-identification plays a critical role in video surveillance and has a variety of applications. However, the body misalignment caused by...
-
Improved Design Closure of Compact Microwave Circuits by Means of Performance Requirement Adaptation
Numerical optimization procedures have been widely used in the design of microwave components and systems. Most often, optimization algorithms are... -
Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
The development of deep networks has enabled state-of-the-art performance to be achieved in many application domains at the cost of a large amount of... -
Analysing Strategic Misalignment in Public Administration
Problems concerning strategic alignment can manifest in several aspects and perspectives of an organisation. This paper presents public... -
AHT: A Novel Aggregation Hyper-transformer for Few-Shot Object Detection
Few-shot object detection aims to detect novel objects with few annotated examples and this task has been extensively investigated by... -
Deep Learning for Automatic Strain Quantification in Arrhythmogenic Right Ventricular Cardiomyopathy
Quantification of cardiac motion with cine Cardiac Magnetic Resonance Imaging (CMRI) is an integral part of arrhythmogenic right ventricular... -
GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Human View Synthesis
Novel view synthesis (NVS) of multi-human scenes imposes challenges due to the complex inter-human occlusions. Layered representations handle the... -
Object detection based on semi-supervised domain adaptation for imbalanced domain resources
On specified scenarios, models trained on specific datasets (source domain) can generalize well to novel scenes (target domain) via knowledge...
-
Minimum Class Confusion for Versatile Domain Adaptation
There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as... -
Multi-camera person re-identification using spatiotemporal context modeling
Person re-identification (ReID) aims at identifying a person of interest (POI) across multiple non-overlap** cameras. The POI can be either in an...
-
Domain Adaptive Nuclei Instance Segmentation and Classification via Category-Aware Feature Alignment and Pseudo-Labelling
Unsupervised domain adaptation (UDA) methods have been broadly utilized to improve the models’ adaptation ability in general computer vision....