Results 21 to 30 of about 1,432,491 (277)
Semi-Supervised Multi-Channel Speaker Diarization With Cross-Channel Attention
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2023 Most neural speaker diarization systems rely on sufficient manual training data labels, which are hard to collect under real-world scenarios. This paper proposes a semi-supervised speaker diarization system to utilize large-scale multi-channel training data by generating pseudo-labels for unlabeled data.
Wu, Shilong +6 more
openaire +2 more sources
Separable Attention Capsule Network for Signal Classification
IEEE Access, 2020 In this paper, a new Separable Attention Capsule Network (SACN) is proposed for signal classification. SACN is a light-weight network composed of multi-channel separable convolution layer, attention module and classification layer.
Shaoqing Liu +4 more
doaj +1 more source
Multi-Scale Feature Channel Attention Generative Adversarial Network for Face Sketch Synthesis
IEEE Access, 2020 Face sketch synthesis for photos is an applied research topic and it is critical for criminal investigation. However, sketch synthesis remains some challenges because of the blur and artifacts in the generated face sketches. To mitigate these problems in
Jieying Zheng +4 more
doaj +1 more source
Leida xuebao, 2021 Deep-learning technology has enabled remarkable results for ship detection in SAR images. However, in view of the complex and changeable backgrounds of SAR ship images, how to accurately and efficiently extract target features and improve detection ...
Xueke ZHOU, Chang LIU, Bin ZHOU
doaj +1 more source
Saliency Based Control in Random Feature Networks [PDF]
, 2014 The ability to rapidly focus attention and react to salient environmental features enables animals to move agiley through their habitats. To replicate this kind of high-performance control of movement in synthetic systems, we propose a new approach to ...
Baillieul, John, Kong, Zhaodan
core +1 more source
IEEE Access, 2020 Constrained image splicing detection and localization (CISDL) is a newly formulated image forensics task and plays an important role in verifying the generating process of a forged image.
Yaqi Liu, Xianfeng Zhao
doaj +1 more source
Gradient-Guided and Multi-Scale Feature Network for Image Super-Resolution
Applied Sciences, 2022 Recently, deep-learning-based image super-resolution methods have made remarkable progress. However, most of these methods do not fully exploit the structural feature of the input image, as well as the intermediate features from the intermediate layers ...
Jian Chen +3 more
doaj +1 more source
Multi-channel feature fusion attention Dehazing network
PLOS ONE, 2023 Haze is a typical weather phenomena that has a significant negative impact on transportation safety, particularly in the port, highways, and airport runway areas. A multi-scale U-shaped dehazing network is proposed in this research, which is based on our multi-channel feature fusion attention structure.
Changjun Zou, Hangbin Xu, Lintao Ye
openaire +2 more sources
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023 Target detection is a critical task in interpreting aerial images. Small target detection, such as vehicles, is challenging. Different lighting conditions affect the accuracy of vehicle detection.
Yuanfeng Wu +4 more
doaj +1 more source
Generalized Bregman Divergence and Gradient of Mutual Information for Vector Poisson Channels [PDF]
, 2013 We investigate connections between information-theoretic and estimation-theoretic quantities in vector Poisson channel models. In particular, we generalize the gradient of mutual information with respect to key system parameters from the scalar to the ...
Carin, L, IEEE, Rodrigues, M, Wang, L
core +2 more sources