IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Nov 12, 2021
Spatial redundancy commonly exists in the learned representations of convolutional neural networks (CNNs), leading to unnecessary computation on high-resolution features. In this paper, we propose a novel Spatially Adaptive feature Refinement (SAR) a...
Nature communications
Nov 9, 2021
In order to better understand how the brain perceives faces, it is important to know what objective drives learning in the ventral visual stream. To answer this question, we model neural responses to faces in the macaque inferotemporal (IT) cortex wi...
Scientific reports
Nov 3, 2021
Environmental sound classification is one of the important issues in the audio recognition field. Compared with structured sounds such as speech and music, the time-frequency structure of environmental sounds is more complicated. In order to learn ti...
Neural networks : the official journal of the International Neural Network Society
Oct 29, 2021
Integrating multi-scale predictions has become a mainstream paradigm in edge detection. However, most existing methods mainly focus on effective feature extraction and multi-scale feature fusion while ignoring the low learning capacity in fine-level ...
Neural networks : the official journal of the International Neural Network Society
Oct 28, 2021
Although significant progress has been made in synthesizing high-quality and visually realistic face images by unconditional Generative Adversarial Networks (GANs), there is still a lack of control over the generation process in order to achieve sema...
Sensors (Basel, Switzerland)
Oct 27, 2021
Feature Pyramid Network (FPN) is used as the neck of current popular object detection networks. Research has shown that the structure of FPN has some defects. In addition to the loss of information caused by the reduction of the channel number, the f...
Journal of biomedical informatics
Oct 23, 2021
The current mode of use of Electronic Health Records (EHR) elicits text redundancy. Clinicians often populate new documents by duplicating existing notes, then updating accordingly. Data duplication can lead to propagation of errors, inconsistencies ...
Sensors (Basel, Switzerland)
Oct 21, 2021
Sky and ground are two essential semantic components in computer vision, robotics, and remote sensing. The sky and ground segmentation has become increasingly popular. This research proposes a sky and ground segmentation framework for the rover navig...
Sensors (Basel, Switzerland)
Oct 19, 2021
The stage and duration of hypertension are connected to the occurrence of Hypertensive Retinopathy (HR) of eye disease. Currently, a few computerized systems have been developed to recognize HR by using only two stages. It is difficult to define spec...
Sensors (Basel, Switzerland)
Oct 12, 2021
Based on the openness and accessibility of user data, personality recognition is widely used in personalized recommendation, intelligent medicine, natural language processing, and so on. Existing approaches usually adopt a single deep learning mechan...