Feature Refinement and Filter Network for Person Re-Identification

Ning, Xin; Gong, Kun; Li, Weijun; Zhang, Liping; Bai, Xiao; Tian, Shengwei

doi:10.1109/tcsvt.2020.3043026

Cited by 217 publications

(75 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used it to remove redundant predictions through the self-attention layers of the encoder-decoder structure of the transformer. Ning et al [43] used an attention mechanism for person re-identification. To identify high value features and eliminate interference caused by background information, they designed a multibranch attention network to select valuable fine-grained features.…”

Section: Attention Mechanismmentioning

confidence: 99%

SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection

Choi

Lee

Kang

et al. 2021

Sensors

View full text Add to dashboard Cite

The development of deep learning has achieved great success in object detection, but small object detection is still a difficult and challenging task in computer vision. To address the problem, we propose an improved single-shot multibox detector (SSD) using enhanced feature map blocks (SSD-EMB). The enhanced feature map block (EMB) consists of attention stream and feature map concatenation stream. The attention stream allows the proposed model to focus on the object regions rather than background owing to channel averaging and the effectiveness of the normalization. The feature map concatenation stream provides additional semantic information to the model without degrading the detection speed. By combining the output of these two streams, the enhanced feature map, which improves the detection of a small object, is generated. Experimental results show that the proposed model has high accuracy in small object detection. The proposed model not only achieves good detection accuracy, but also has a good detection speed. The SSD-EMB achieved a mean average precision (mAP) of 80.4% on the PASCAL VOC 2007 dataset at 30 frames per second on an RTX 2080Ti graphics processing unit, an mAP of 79.9% on the VOC 2012 dataset, and an mAP of 26.6% on the MS COCO dataset.

show abstract

Section: Attention Mechanismmentioning

confidence: 99%

SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection

Choi

Lee

Kang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Due to its shallow structure, the classifier limits the learning of music features, and it is difficult to extract more effective features to represent music, which affects the accuracy of classification. In recent years, deep neural networks [9][10][11][12] have achieved good results in natural language processing, computer vision [13][14][15][16], and other research fields. e deep neural network model can automatically learn deeper features from the shallow features and can reflect the local relevance of the input data.…”

Section: Introductionmentioning

confidence: 99%

Recognition and Classification Model of Music Genres and Chinese Traditional Musical Instruments Based on Deep Neural Networks

2021

Scientific Programming

View full text Add to dashboard Cite

The teaching of ideological and political theory courses and daily ideological and political education are two important parts of education for college students. With the iterative update of information technology, the individualized development of students, and the reform and innovation of ideological and political education, higher goals and requirements have been put forward for ideological and political education. Some universities have developed new paths in the teaching model, but they have not considered the evaluation module and paid little attention to their own development. They only paid attention to the fact that it injected fresh blood into the reform of education model and ideological education but ignored the improvement of their own quality. Therefore, with these limitations, the learning effect is not satisfactory. Keeping in view these issues, this article defines the concept of deep learning and ideological and political education of college students as the starting point and then analyzes the new precise and personalized concepts, new forms of intelligent teaching and evaluation, and new models of intelligent learning that deep learning brings to college students’ ideological and political education. This is a new path of intelligent linkage with the subject, object, and mediator. It can deepen the reform of the education and teaching mode of individualization, accuracy, interactivity, and vividness of college students’ ideological and political education and improve the evaluation and management of college students’ ideological and political education. The experimental results of the study showed the effectiveness of the proposed study.

show abstract

“…e advent of the big data era and the continued advancement of artificial intelligence technology in recent years [13][14][15][16], which has been gradually applied to various fields, brings profound changes to various industries. More and more experts and scholars begin to study the neural network [17][18][19][20] and apply it to the prediction of stock and other time series. Neural network has strong self-learning ability, can deal with massive data, and can make more accurate prediction for unstable and nonlinear time series.…”

Section: Introductionmentioning

confidence: 99%

A Stock Trend Forecast Algorithm Based on Deep Neural Networks

Yan

Yang

2021

Scientific Programming

View full text Add to dashboard Cite

As a recognized complex dynamic system, the stock market has many influencing factors, such as nonstationarity, nonlinearity, high noise, and long memory. It is difficult to explain it simply through mathematical models. Therefore, the analysis and prediction of the stock market have been a very challenging job since long time. Therefore, this paper adopts an encoder-decoder model of attention mechanism, adding attention mechanism from two aspects of feature and time. Both encoder and decoder use LSTM neural network. This method solves two problems in time series prediction; the first problem is that multiple input features have different degrees of influence on the target sequence, the feature attention mechanism is used to deal with this problem, and the weights of different input features can be obtained. A more robust feature association relationship is obtained; the second problem is that the data before and after the sequence have a strong time correlation. The time attention mechanism is used to deal with this problem, and the weights at different time points can be obtained to obtain more robustness and good timing dependencies. The simulation and experimental results show that the introduction of the attention mechanism can obtain lower forecast errors, which proves the effectiveness of the model in dealing with stock forecasting problems.

show abstract

Feature Refinement and Filter Network for Person Re-Identification

Cited by 217 publications

References 66 publications

SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection

SSD-EMB: An Improved SSD Using Enhanced Feature Map Block for Object Detection

Recognition and Classification Model of Music Genres and Chinese Traditional Musical Instruments Based on Deep Neural Networks

A Stock Trend Forecast Algorithm Based on Deep Neural Networks

Contact Info

Product

Resources

About