期刊： PATTERN RECOGNITION LETTERS, 2021; 146 ()
To improve the accuracy of multi-spectral semantic segmentation, an attention fusion network (AFNet) based on deep learning is proposed. Different fro......
期刊： PATTERN RECOGNITION LETTERS, 2021; 146 ()
When inferring sentiments, using verbal clues only is problematic because of the ambiguity. Adding related vocal and visual contexts as complements fo......
期刊： PATTERN RECOGNITION LETTERS, 2021; 147 ()
Synthesizing photographic images from given text descriptions is a challenging problem. Although current methods first synthesize an initial blurred i......
期刊： PATTERN RECOGNITION LETTERS, 2021; 148 ()
License plate number detection in drone images is a complex problem because the images are generally captured at oblique angles and pose several chall......
期刊： PATTERN RECOGNITION LETTERS, 2021; 149 ()
The automatic generation of poems from images is a classic task in natural language processing. Recently, it has gained tremendous research interest d......
期刊： PATTERN RECOGNITION LETTERS, 2021; 150 ()
Recommended technologies for the tourism system, such as the travelocity.com and visiteurope.com, have gained tremendous popularity in the past few ye......
期刊： PATTERN RECOGNITION LETTERS, 2021; 145 ()
Weakly-supervised video object localization is a challenging yet important task. The system should spatially localize the object of interest in videos......
期刊： PATTERN RECOGNITION LETTERS, 2021; 145 ()
To process data like text and speech, Natural Language Processing (NLP) is a valuable tool. As on of NLP?s upstream tasks, sequence labeling is a vita......
期刊： PATTERN RECOGNITION LETTERS, 2021; 145 ()
We present a simple end-to-end model based on deep learning to automatically decompose sketched objects into components by disentangling the visual re......
期刊： PATTERN RECOGNITION LETTERS, 2021; 148 ()
Object detection has attracted growing attention due to its extensive application prospect, in which bounding box regression is an essential component......
期刊： PATTERN RECOGNITION LETTERS, 2021; 146 ()
Deep neural networks are known to be vulnerable to adversarial attacks. The empirical analysis in our study suggests that attacks tend to induce diver......
期刊： PATTERN RECOGNITION LETTERS, 2021; 146 ()
In recent years, the number of Internet of Things (IoT) devices has increased rapidly. The Internet of Biometric Things (IoBT) can process biometrics ......
期刊： PATTERN RECOGNITION LETTERS, 2021; 145 ()
Face spoofing attacks based on 3D face images have posed a severe security risk to face recognition systems. Despite the great effort made by the tech......
期刊： PATTERN RECOGNITION LETTERS, 2021; 146 ()
Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real fa......
期刊： PATTERN RECOGNITION LETTERS, 2021; 148 ()
A B S T R A C T Support vector data description (SVDD) is a classical anomaly detection algorithm. How to develop a deep version of SVDD is one valuab......
