Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
36
TIME-FREQUENCY CONVOLUTIONAL NETWORKS FOR ROBUST SPEECH RECOGNITION
"... ABSTRACT Convolutional deep neural networks (CDNNs) have consistently shown more robustness to noise and background contamination than traditional deep neural networks (DNNs). For speech recognition, CDNNs apply their convolution filters across frequency, which helps to remove cross-spectral distor ..."
Abstract
- Add to MetaCart
network (TFCNN), in which two parallel layers of convolution are performed on the input feature space: convolution across time and frequency, each using a different pooling layer. The feature maps obtained from the convolution layers are then combined and fed to a fully connected DNN. Our experimental
Deep Networks with Internal Selective Attention through Feedback Connections
"... Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers. Real brains, however, do. So does our Deep Attention Selective Network (dasNet) architecture. DasNet’s feedback structu ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers. Real brains, however, do. So does our Deep Attention Selective Network (dasNet) architecture. DasNet’s feedback
Fusion of Learned Multi-Modal Representations and Dense Trajectories for Emotional Analysis in Videos
"... Abstract-When designing a video affective content analysis algorithm, one of the most important steps is the selection of discriminative features for the effective representation of video segments. The majority of existing affective content analysis methods either use low-level audio-visual feature ..."
Abstract
- Add to MetaCart
-visual features or generate handcrafted higher level representations based on these lowlevel features. We propose in this work to use deep learning methods, in particular convolutional neural networks (CNNs), in order to automatically learn and extract mid-level representations from raw data. To this end, we
Network In Network
"... We propose a novel deep network structure called “Network In Network”(NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear acti-vation function to scan the input. Instead, we build micro ..."
Abstract
-
Cited by 11 (2 self)
- Add to MetaCart
We propose a novel deep network structure called “Network In Network”(NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear acti-vation function to scan the input. Instead, we build micro
Learning Transferable Features with Deep Adaptation Networks Mingsheng Long† ♯
"... Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. How-ever, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers w ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
with increasing domain discrepancy. Hence, it is critical to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural networks to the do-main adaptation scenario
Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
"... Deep convolutional neural networks (CNNs) are the back-bone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can signif-icantly enhance their object localization accuracy, yet dense CRF inference ..."
Abstract
- Add to MetaCart
Deep convolutional neural networks (CNNs) are the back-bone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can signif-icantly enhance their object localization accuracy, yet dense CRF inference
Network science Complex network Community detection
"... This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution and sharing with colleagues. Other uses, including reproduction and distribution, or sel ..."
Abstract
- Add to MetaCart
This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution and sharing with colleagues. Other uses, including reproduction and distribution
Matchability Prediction for Full-Search Template Matching Algorithms
"... While recent approaches have shown that it is possible to do template matching by exhaustively scanning the pa-rameter space, the resulting algorithms are still quite de-manding. In this paper we alleviate the computational load of these algorithms by proposing an efficient approach for predicting t ..."
Abstract
- Add to MetaCart
the matchability of a template, before it is actu-ally performed. This avoids large amounts of unnecessary computations. We learn the matchability of templates by using dense convolutional neural network descriptors that do not require ad-hoc criteria to characterize a template. By using deep learning descriptions
SIMULATION, DEVELOPMENT AND DEPLOYMENT OF MOBILE WIRELESS SENSOR NETWORKS FOR MIGRATORY BIRD TRACKING
, 2012
"... This thesis presents CraneTracker, a multi-modal sensing and communication system for monitoring migratory species at the continental level. By exploiting the robust and extensive cellular infrastructure across the continent, traditional mobile wireless sensor networks can be extended to enable reli ..."
Abstract
- Add to MetaCart
This thesis presents CraneTracker, a multi-modal sensing and communication system for monitoring migratory species at the continental level. By exploiting the robust and extensive cellular infrastructure across the continent, traditional mobile wireless sensor networks can be extended to enable
Results 1 - 10
of
36
