Deep hierarchical encoding model for sentence semantic matching

Lü, Wenpeng; Zhang, Xu; Lu, Huimin; Li, Fangfang

doi:10.1016/j.jvcir.2020.102794

Cited by 58 publications

(19 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the field of computer vision, single-image superresolution (SISR) is an ill-posed, low-level problem [6]- [9] that is often integrated with other industrial fields [10]- [15]. In resent years, the field of SISR has been widely used deep learning algorithms [16]- [19]. The first deep learning-based SISR algorithm was the super-resolution using convolutional neural networks (SRCNN), proposed by Dong et al [20].…”

Section: Introductionmentioning

confidence: 99%

Lightweight Feedback Convolution Neural Network for Remote Sensing Images Super-Resolution

Jin

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

There are lots of image data in the field of remote sensing, most of which have low-resolution due to the limited image sensor. The super-resolution method can effectively restore the low-resolution image to the high-resolution image. However, the existing super-resolution method has both heavy computing burden and number of parameters. For saving costs, we propose the feedback ghost residual dense network (FGRDN), which considers the feedback mechanism as the framework to attain lower features through high-level refining. Further, for feature extraction, we replace the convolution of the residual dense blocks (RDBs) with ghost modules (GMs), which can remove the redundant channels and avoid the increase of parameters along with the network depth. Finally, the spatial and channel attention module (SCM) is employed in the end of the RDB to learn more useful information from features. Compared to other SOTA lightweight algorithms, our proposed algorithm can reach convergences more rapidly with fewer parameters, and the performance of the network can be markedly enhanced on the image texture and object contour reconstruction with better peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).

show abstract

Section: Introductionmentioning

confidence: 99%

Lightweight Feedback Convolution Neural Network for Remote Sensing Images Super-Resolution

Jin

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The greater the demand and the more investment, the stronger the research on recommendation systems will certainly be. Classical recommendation methods, such as matrix factorization [12], mainly use historical user-project interaction records to simulate users' preferences for projects; There are also recommendations made through the similarity function, recommendation learning is carried out through human judgment on the similarity of objects [13], accurate similar neighbors between users or project requirements are captured according to their historical common evaluation, and then appropriate projects or items are recommended. The intelligent recommendation system [10] can make appropriate music, movies and books through different hobbies of users [14], and is widely used to realize accurate matching between users and various resources.…”

Section: Introductionmentioning

confidence: 99%

Recommendation Algorithm Based on Knowledge Graph to Propagate User Preference

Yang

Cheng

2021

Preprint

View full text Add to dashboard Cite

In recommendation algorithms, data sparsity and cold start problems are always inevitable. In order to solve such problems, researchers apply auxiliary information to recommendation algorithms to mine and obtain more potential information through users' historical records and then improve recommendation performance. This paper proposes a model ST_RippleNet, which combines knowledge graph with deep learning. In this model, users' potential interests are mined in the knowledge graph to stimulate the propagation of users' preferences on the set of knowledge entities. In the propagation of preferences, we adopt a triple-based multi-layer attention mechanism, and the distribution of users' preferences for candidate items formed by users' historical click information is used to predict the final click probability. In ST_RippleNet model, music data set is added to the original movie and book data set, and the improved loss function is applied to the model, which is optimized by RMSProp optimizer. Finally, tanh function is added to predict click probability to improve recommendation performance. Compared with the current mainstream recommendation methods, ST_RippleNet recommendation algorithm has very good performance in AUC and ACC, and has substantial improvement in movie, book and music recommendation.

show abstract

“…The research in the paper is mainly aimed at image learning algorithms based on deep learning. In recent years, convolutional neural networks (CNN) [17,18] have greatly improved the performance of semantic image classification [19][20][21][22], object detection [23][24][25][26][27], and image segmentation tasks [28,29]. Researchers have used CNN models for image inpainting tasks, but the image inpainting methods using only CNNs have low accuracy and great room for improvement in performance.…”

Section: Introductionmentioning

confidence: 99%

The image inpainting algorithm used on multi-scale generative adversarial networks and neighbourhood

Zhou

2020

Automatika

View full text Add to dashboard Cite

Various problems existed in the image inpainting algorithms, which can't meet people's requirements visually. Aiming at the defects of the existing image inpainting algorithms, such as low accuracy, poor visual consistency, and unstable training, an improved image inpainting algorithm used on a multi-scale generative adversarial network (GAN) and neighbourhood model have been proposed in the paper. The proposed algorithm mainly improves the network structure of the discriminator, and introduces a multi-scale discriminator based on the global discriminator and the local discriminator. The multi-scale discriminators were trained on images of different resolutions. Discriminators of different scales have different receptive fields, which can guide the generator to generate more global image views and finer details. Aiming at the problem of gradient disappearance or gradient explosion that often occurs in GAN training, the method of WGAN (Wasserstein GAN) has been used to simulate the sample data distribution using EM distance. The proposed model has been trained and tested on the CelebA, ImageNet, and Place2. The experimental results show that compared with the previous algorithm model, the proposed algorithm improves the accuracy of image inpainting and can generate more realistic repairing images, and it is suitable for many types of images.

show abstract

Deep hierarchical encoding model for sentence semantic matching

Cited by 58 publications

References 36 publications

Lightweight Feedback Convolution Neural Network for Remote Sensing Images Super-Resolution

Lightweight Feedback Convolution Neural Network for Remote Sensing Images Super-Resolution

Recommendation Algorithm Based on Knowledge Graph to Propagate User Preference

The image inpainting algorithm used on multi-scale generative adversarial networks and neighbourhood

Contact Info

Product

Resources

About