Understanding human high-level spatial memory: An ACT-R model to integrate multi-level spatial cues and strategies

2013 ◽  
Vol 3 ◽  
pp. 1-5
Author(s):  
Changkun Zhao ◽  
Jonathan H. Morgan ◽  
Frank E. Ritter
Keyword(s):  
Spatial Memory ◽  
Spatial Cues ◽  
Multi Level ◽  
High Level

scholarly journals An Efficient Module for Instance Segmentation Based on Multi-Level Features and Attention Mechanisms

2021 ◽  
Vol 11 (3) ◽  
pp. 968
Author(s):  
Yingchun Sun ◽  
Wang Gao ◽  
Shuguo Pan ◽  
Tao Zhao ◽  
Yahui Peng
Keyword(s):  
Feature Extraction ◽  
Spatial Structure ◽  
Semantic Feature ◽  
Semantic Features ◽  
Segmentation Method ◽  
Spatial Dimensions ◽  
Feature Pyramid ◽  
Multi Level ◽  
High Level ◽  
Instance Segmentation

Recently, multi-level feature networks have been extensively used in instance segmentation. However, because not all features are beneficial to instance segmentation tasks, the performance of networks cannot be adequately improved by synthesizing multi-level convolutional features indiscriminately. In order to solve the problem, an attention-based feature pyramid module (AFPM) is proposed, which integrates the attention mechanism on the basis of a multi-level feature pyramid network to efficiently and pertinently extract the high-level semantic features and low-level spatial structure features; for instance, segmentation. Firstly, we adopt a convolutional block attention module (CBAM) into feature extraction, and sequentially generate attention maps which focus on instance-related features along the channel and spatial dimensions. Secondly, we build inter-dimensional dependencies through a convolutional triplet attention module (CTAM) in lateral attention connections, which is used to propagate a helpful semantic feature map and filter redundant informative features irrelevant to instance objects. Finally, we construct branches for feature enhancement to strengthen detailed information to boost the entire feature hierarchy of the network. The experimental results on the Cityscapes dataset manifest that the proposed module outperforms other excellent methods under different evaluation metrics and effectively upgrades the performance of the instance segmentation method.

Y-Net: Dual-branch Joint Network for Semantic Segmentation

2021 ◽  
Vol 17 (4) ◽  
pp. 1-22
Author(s):  
Yizhen Chen ◽  
Haifeng Hu
Keyword(s):  
Feature Vector ◽  
State Of The Art ◽  
Computational Cost ◽  
Receptive Fields ◽  
Semantic Segmentation ◽  
Global Context ◽  
Multi Level ◽  
The One ◽  
Public Datasets ◽  
High Level

Most existing segmentation networks are built upon a “ U -shaped” encoder–decoder structure, where the multi-level features extracted by the encoder are gradually aggregated by the decoder. Although this structure has been proven to be effective in improving segmentation performance, there are two main drawbacks. On the one hand, the introduction of low-level features brings a significant increase in calculations without an obvious performance gain. On the other hand, general strategies of feature aggregation such as addition and concatenation fuse features without considering the usefulness of each feature vector, which mixes the useful information with massive noises. In this article, we abandon the traditional “ U -shaped” architecture and propose Y-Net, a dual-branch joint network for accurate semantic segmentation. Specifically, it only aggregates the high-level features with low-resolution and utilizes the global context guidance generated by the first branch to refine the second branch. The dual branches are effectively connected through a Semantic Enhancing Module, which can be regarded as the combination of spatial attention and channel attention. We also design a novel Channel-Selective Decoder (CSD) to adaptively integrate features from different receptive fields by assigning specific channelwise weights, where the weights are input-dependent. Our Y-Net is capable of breaking through the limit of singe-branch network and attaining higher performance with less computational cost than “ U -shaped” structure. The proposed CSD can better integrate useful information and suppress interference noises. Comprehensive experiments are carried out on three public datasets to evaluate the effectiveness of our method. Eventually, our Y-Net achieves state-of-the-art performance on PASCAL VOC 2012, PASCAL Person-Part, and ADE20K dataset without pre-training on extra datasets.

scholarly journals Natural Language Understanding for Multi-Level Distributed Intelligent Virtual Sensors

IoT ◽  
2020 ◽  
Vol 1 (2) ◽  
pp. 494-505
Author(s):  
Radu-Casian Mihailescu ◽  
Georgios Kyriakou ◽  
Angelos Papangelis
Keyword(s):  
Deep Learning ◽  
User Interface ◽  
Natural Language ◽  
Learning Approach ◽  
Language Understanding ◽  
Virtual Sensor ◽  
Virtual Sensors ◽  
Multi Level ◽  
High Level ◽  
User Friendly

In this paper we address the problem of automatic sensor composition for servicing human-interpretable high-level tasks. To this end, we introduce multi-level distributed intelligent virtual sensors (multi-level DIVS) as an overlay framework for a given mesh of physical and/or virtual sensors already deployed in the environment. The goal for multi-level DIVS is two-fold: (i) to provide a convenient way for the user to specify high-level sensing tasks; (ii) to construct the computational graph that provides the correct output given a specific sensing task. For (i) we resort to a conversational user interface, which is an intuitive and user-friendly manner in which the user can express the sensing problem, i.e., natural language queries, while for (ii) we propose a deep learning approach that establishes the correspondence between the natural language queries and their virtual sensor representation. Finally, we evaluate and demonstrate the feasibility of our approach in the context of a smart city setup.

scholarly journals Adaptive Model for Credit Card Fraud Detection

2020 ◽  
Vol 14 (03) ◽  
pp. 54
Author(s):  
Imane Sadgali ◽  
Naoual Sael ◽  
Faouzia Benabbou
Keyword(s):  
Credit Card ◽  
Fraud Detection ◽  
Machine Learning Techniques ◽  
Adaptive Model ◽  
Credit Card Fraud ◽  
New Methods ◽  
Learning Techniques ◽  
Multi Level ◽  
Set Up ◽  
High Level

<p>While the flow of banking transactions is increasing, the risk of credit card fraud is becoming greater particularly with the technological revolution that we know, fraudulent are improve and always find new methods to deal with the preventive measures that financial systems set up. Several studies have proposed predictive models for credit card fraud detection based on different machine learning techniques. In this paper, we present an adaptive approach to credit card fraud detection that exploits the performance of the techniques that have given high level of accuracy and consider the type of transaction and the client's profile. Our proposition is a multi-level framework, which encompasses the banking security aspect, the customer profile and the profile of the transaction itself.</p>

scholarly journals A new joint CTC-attention-based speech recognition model with multi-level multi-head attention

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Chu-Xiong Qin ◽  
Wen-Lin Zhang ◽  
Dan Qu
Keyword(s):  
Speech Recognition ◽  
Nonnegative Matrix Factorization ◽  
State Of The Art ◽  
Nonnegative Matrix ◽  
Attention Mechanism ◽  
Word Error Rate ◽  
Absolute Value ◽  
Multi Level ◽  
End To End ◽  
High Level

Abstract A method called joint connectionist temporal classification (CTC)-attention-based speech recognition has recently received increasing focus and has achieved impressive performance. A hybrid end-to-end architecture that adds an extra CTC loss to the attention-based model could force extra restrictions on alignments. To explore better the end-to-end models, we propose improvements to the feature extraction and attention mechanism. First, we introduce a joint model trained with nonnegative matrix factorization (NMF)-based high-level features. Then, we put forward a hybrid attention mechanism by incorporating multi-head attentions and calculating attention scores over multi-level outputs. Experiments on TIMIT indicate that the new method achieves state-of-the-art performance with our best model. Experiments on WSJ show that our method exhibits a word error rate (WER) that is only 0.2% worse in absolute value than the best referenced method, which is trained on a much larger dataset, and it beats all present end-to-end methods. Further experiments on LibriSpeech show that our method is also comparable to the state-of-the-art end-to-end system in WER.

scholarly journals Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification

2021 ◽  
Author(s):  
Haocong Rao ◽  
Shihao Xu ◽  
Xiping Hu ◽  
Jun Cheng ◽  
Bin Hu
Keyword(s):  
Superior Performance ◽  
Skeleton Graph ◽  
Graph Dynamics ◽  
Connected Body ◽  
Body Component ◽  
Multi Level ◽  
Highly Correlated ◽  
High Level ◽  
Body Joints ◽  
Relation Learning

Skeleton-based person re-identification (Re-ID) is an emerging open topic providing great value for safety-critical applications. Existing methods typically extract hand-crafted features or model skeleton dynamics from the trajectory of body joints, while they rarely explore valuable relation information contained in body structure or motion. To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID. Specifically, considering that structurally-connected body components are highly correlated in a skeleton, we first propose a multi-head structural relation layer to learn different relations of neighbor body-component nodes in graphs, which helps aggregate key correlative features for effective node representations. Second, inspired by the fact that body-component collaboration in walking usually carries recognizable patterns, we propose a cross-level collaborative relation layer to infer collaboration between different level components, so as to capture more discriminative skeleton graph features. Finally, to enhance graph dynamics encoding, we propose a novel self-supervised sparse sequential prediction task for model pre-training, which facilitates encoding high-level graph semantics for person Re-ID. MG-SCR outperforms state-of-the-art skeleton-based methods, and it achieves superior performance to many multi-modal methods that utilize extra RGB or depth features. Our codes are available at https://github.com/Kali-Hac/MG-SCR.

scholarly journals Fostering post-secondary vocational students’ critical thinking through multi-level tasks in learning environments

2021 ◽  
Vol 13 (3) ◽  
pp. 397-406
Author(s):  
Zhanar Sabyrovna Bekbayeva ◽  
Temir Tlekovich Galiyev ◽  
Nazymgul Albytova ◽  
Zhazira Meirhanovna Zhazykbayeva ◽  
Assem Bolatbekovna Mussatayeva
Keyword(s):  
Critical Thinking ◽  
Reflective Thinking ◽  
Cross Sectional Study ◽  
Vocational Students ◽  
Cross Sectional ◽  
Post Secondary ◽  
Significant Difference ◽  
Multi Level ◽  
Low Performance ◽  
High Level

In today’s labour market, being competitive requires, in addition to technical skills, several twenty-first-century career competencies, including the capacity to think critically. Although the literature on teaching methods designed for enhancing students’ reflective thinking abounds, the contribution of special tasks with varying complexity to learners’ critical thinking capacity, to our knowledge, has not been earlier investigated. Hence, the present investigation sought to investigate the effect of multi-level critical thinking activities introduced into classes on the critical thinking level of post-secondary vocational students. This cross-sectional study employed the Starkey Critical Thinking Test adapted for the Russian-speaking population in order to measure critical thinking level in a sample (n = 218) of vocational students. Results showed that among students whose classes were complemented by critical thinking tasks, almost half of subjects with low and test scores eventually shifted to a medium scoring cohort. Eleven learners who were medium scorers at the beginning gained high-level results at the end point. Meanwhile, only a small percentage of those no-treatment participants with initially low performance on the critical thinking test eventually moved into the medium level, as well as from the latter into a high achievement category. The independent two-tailed t-test revealed a significant difference between posttest scores observed in control and intervention groups. It can be therefore suggested that critical analysis of thought-provoking materials with subsequent class presentation and discussion can provide catalytic conditions for developing learners’ reflective thinking abilities. It was recommended that future studies using similar intervention should involve a larger sample and deal with qualitative data to extend the research and increase its validity.   Keywords: Education; higher-order thinking; reflective thinking; vocational students.

scholarly journals Proposed Hybrid Algorithm for Image Steganography in Text Security Using Fish Algorithm

2019 ◽  
Vol 54 (6) ◽  
Author(s):  
Ghada Mohammad Tahir Kasim Aldabagh
Keyword(s):  
Signal To Noise Ratio ◽  
Personal Data ◽  
Image Steganography ◽  
Security And Privacy ◽  
Basic Algorithm ◽  
Important Data ◽  
Suitable Alternative ◽  
Secure Data Transmission ◽  
Multi Level ◽  
High Level

The rapid growth of various technologies makes secure data transmission a very important issue. The cryptography technique is the most popular method in several security cases. The major issue is putting the security in place without disturbing the personal data. In such a case, steganography can be used as the most suitable alternative technique. Essentially, steganography is the art of hiding important data that we want to send over a channel or transmission medium. The hiding of information is made with the carrier, making the hacking of data difficult. Hiding the important data provides security and privacy at a high level. In general, there are five types of steganograph: text, audio, video, image and protocol. The carrier plays an important role in steganography. The selection of the carrier depends on the level of security. We proposed an algorithm which is useful for multi-level steganography, and is more advantageous than the standard, less significant, bit algorithm. In this paper, we used multi-level steganography. We focused on image steganography along with a fish algorithm in order to secure the text. We aimed to compare the performance of a basic algorithm to the proposed algorithm. The parameters which have been taken into consideration to compare these two algorithms are execution time and peak signal to noise ratio. We achieved the expected result which shows the applied security for the important data. We used MATLAB 10 software to get these results.

scholarly journals Multi-Level Fusion Temporal–Spatial Co-Attention for Video-Based Person Re-Identification

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1686
Author(s):  
Shengyu Pei ◽  
Xiaoping Fan
Keyword(s):  
Neural Network ◽  
Metric Learning ◽  
Auxiliary Information ◽  
Generalization Ability ◽  
Local Branch ◽  
Feature Information ◽  
Multi Level ◽  
High Level ◽  
Additional Collection ◽  
Level Fusion

A convolutional neural network can easily fall into local minima for insufficient data, and the needed training is unstable. Many current methods are used to solve these problems by adding pedestrian attributes, pedestrian postures, and other auxiliary information, but they require additional collection, which is time-consuming and laborious. Every video sequence frame has a different degree of similarity. In this paper, multi-level fusion temporal–spatial co-attention is adopted to improve person re-identification (reID). For a small dataset, the improved network can better prevent over-fitting and reduce the dataset limit. Specifically, the concept of knowledge evolution is introduced into video-based person re-identification to improve the backbone residual neural network (ResNet). The global branch, local branch, and attention branch are used in parallel for feature extraction. Three high-level features are embedded in the metric learning network to improve the network’s generalization ability and the accuracy of video-based person re-identification. Simulation experiments are implemented on small datasets PRID2011 and iLIDS-VID, and the improved network can better prevent over-fitting. Experiments are also implemented on MARS and DukeMTMC-VideoReID, and the proposed method can be used to extract more feature information and improve the network’s generalization ability. The results show that our method achieves better performance. The model achieves 90.15% Rank1 and 81.91% mAP on MARS.

Sign in / Sign up

Export Citation Format

Share Document