scholarly journals Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption

2020 ◽  
Vol 34 (05) ◽  
pp. 9571-9578 ◽  
Author(s):  
Wei Zhang ◽  
Yue Ying ◽  
Pan Lu ◽  
Hongyuan Zha
Keyword(s):  
State Of The Art ◽  
Natural Extension ◽  
Target Image ◽  
Short Term ◽  
Image Representations ◽  
High Level ◽  
Image Descriptions ◽  
Shed Light ◽  
Image Caption

Personalized image caption, a natural extension of the standard image caption task, requires to generate brief image descriptions tailored for users' writing style and traits, and is more practical to meet users' real demands. Only a few recent studies shed light on this crucial task and learn static user representations to capture their long-term literal-preference. However, it is insufficient to achieve satisfactory performance due to the intrinsic existence of not only long-term user literal-preference, but also short-term literal-preference which is associated with users' recent states. To bridge this gap, we develop a novel multimodal hierarchical transformer network (MHTN) for personalized image caption in this paper. It learns short-term user literal-preference based on users' recent captions through a short-term user encoder at the low level. And at the high level, the multimodal encoder integrates target image representations with short-term literal-preference, as well as long-term literal-preference learned from user IDs. These two encoders enjoy the advantages of the powerful transformer networks. Extensive experiments on two real datasets show the effectiveness of considering two types of user literal-preference simultaneously and better performance over the state-of-the-art models.

From Users’ Intentions to IF-THEN Rules in the Internet of Things

2021 ◽  
Vol 39 (4) ◽  
pp. 1-33
Author(s):  
Fulvio Corno ◽  
Luigi De Russis ◽  
Alberto Monge Roffarello
Keyword(s):  
Internet Of Things ◽  
Smart Devices ◽  
The Internet ◽  
Short Term ◽  
Real World Data ◽  
Original Intention ◽  
Recommendation Accuracy ◽  
High Level ◽  
The Internet Of Things

In the Internet of Things era, users are willing to personalize the joint behavior of their connected entities, i.e., smart devices and online service, by means of trigger-action rules such as “IF the entrance Nest security camera detects a movement, THEN blink the Philips Hue lamp in the kitchen.” Unfortunately, the spread of new supported technologies makes the number of possible combinations between triggers and actions continuously growing, thus motivating the need of assisting users in discovering new rules and functionality, e.g., through recommendation techniques. To this end, we present , a semantic Conversational Search and Recommendation (CSR) system able to suggest pertinent IF-THEN rules that can be easily deployed in different contexts starting from an abstract user’s need. By exploiting a conversational agent, the user can communicate her current personalization intention by specifying a set of functionality at a high level, e.g., to decrease the temperature of a room when she left it. Stemming from this input, implements a semantic recommendation process that takes into account ( a ) the current user’s intention , ( b ) the connected entities owned by the user, and ( c ) the user’s long-term preferences revealed by her profile. If not satisfied with the suggestions, then the user can converse with the system to provide further feedback, i.e., a short-term preference , thus allowing to provide refined recommendations that better align with the original intention. We evaluate by running different offline experiments with simulated users and real-world data. First, we test the recommendation process in different configurations, and we show that recommendation accuracy and similarity with target items increase as the interaction between the algorithm and the user proceeds. Then, we compare with other similar baseline recommender systems. Results are promising and demonstrate the effectiveness of in recommending IF-THEN rules that satisfy the current personalization intention of the user.

scholarly journals A Framework for Property Developers to Survive in a Recession

10.29007/cfr2 ◽  
2018 ◽  
Author(s):  
Zunoon Parambath ◽  
Nilupa Udawatta
Keyword(s):  
Survival Strategies ◽  
Economic Activities ◽  
Short Term ◽  
Property Development ◽  
Market Shares ◽  
Negative Impacts ◽  
Set Up ◽  
High Level ◽  
Property Developers

Recession is considered as a major threat to the economy as it slows down economic activities. The property development sector is extremely responsive to these economic conditions. Thus, it is crucial to understand causes, effects and strategies for property developers to survive in a recession without any ill effects. Thus, this research aimed to develop a framework for property developers to identify appropriate survival strategies in recession. A comprehensive literature review was conducted in this research to achieve the above mentioned aim. The results of this study indicated that recession prompts negative impacts on property development sector resulting in unemployment, lower demand, production and revenue, decline in resources and high level of competition. According to the results, the survival strategies were classified into short-term and long-term strategies. The short term strategies include: implementing management tactics, cut down of operating costs, keeping financing lines set up, timely repayment of debts, setting vital new objectives for the future, undertaking shorter time span developments, specialisation in favoured market, renegotiating deals and contracts. The long-term strategies include retrenchment, restructuring, investment and ambidextrous strategies. Similarly, attention should be paid to predict any changes in the economic environment that can influence property development activities and it is necessary to carefully evaluate investment activities to increase sales, profits and market shares of property developers. Preparing for a crisis is doubtlessly the ideal approach as it can facilitate both survival and growth. Thus, the property developers can implement these suggested strategies in their businesses to enhance their practices.

scholarly journals Learning from Interventions Using Hierarchical Policies for Safe Learning

2020 ◽  
Vol 34 (06) ◽  
pp. 10352-10360
Author(s):  
Jing Bi ◽  
Vikas Dhiman ◽  
Tianyou Xiao ◽  
Chenliang Xu
Keyword(s):  
Reaction Time ◽  
State Of The Art ◽  
The State ◽  
Policy Framework ◽  
Asymptotic Performance ◽  
Short Term ◽  
Learning From Demonstrations ◽  
Hierarchical Levels ◽  
Long Term Behavior

Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert's reaction time and only learns short-term behavior. We address these limitations by 1) interpolating the expert's interventions back in time, and 2) by splitting the policy into two hierarchical levels, one that generates sub-goals for the future and another that generates actions to reach those desired sub-goals. This sub-goal prediction forces the algorithm to learn long-term behavior while also being robust to the expert's reaction time. Our experiments show that LfI using sub-goals in a hierarchical policy framework trains faster and achieves better asymptotic performance than typical LfD.

scholarly journals Long-term target tracking combined with re-detection

2020 ◽  
Author(s):  
Juanjuan Wang ◽  
HaoRan Yang ◽  
Ning Xu ◽  
Chengqin Wu ◽  
ZengShun Zhao ◽  
...  
Keyword(s):  
Correlation Energy ◽  
State Of The Art ◽  
Tracking Algorithm ◽  
Correlation Filters ◽  
Short Term ◽  
Tracking Method ◽  
Tracking Tasks ◽  
Svm Model ◽  
Confidence Degree

Abstract The long-term visual tracking undergoes more challenges and is closer to realistic applications than short-term tracking. However, the performances of most existing methods have been limited in the long-term tracking tasks. In this work, we present a reliable yet simple long-term tracking method, which extends the state-of-the-art Learning Adaptive Discriminative Correlation Filters (LADCF) tracking algorithm with a re-detection component based on the SVM model. The LADCF tracking algorithm localizes the target in each frame and the re-detector is able to efficiently re-detect the target in the whole image when the tracking fails. We further introduce a robust confidence degree evaluation criterion that combines the maximum response criterion and the average peak-to correlation energy (APCE) to judge the confidence level of the predicted target. When the confidence degree is generally high, the SVM is updated accordingly. If the confidence drops sharply, the SVM re-detects the target. We perform extensive experiments on the OTB-2015 and UAV123 datasets. The experimental results demonstrate the effectiveness of our algorithm in long-term tracking.

changing landscapes, human impact on

2019 ◽  
Author(s):  
John Bintliff
Keyword(s):  
Human Impact ◽  
Land Surface ◽  
Agricultural Technology ◽  
Short Term ◽  
Rural Landscapes ◽  
Natural Factors ◽  
Classical World ◽  
Ancient Society ◽  
Shed Light

The Classical world witnessed many forms of physical landscape change due to long-term and short-term geological and climatological processes. There have also been alterations to the land surface resulting from an interaction between human impact and these natural factors. Cyclical changes in land use, agricultural technology, economy, and politics have continually transformed the rural landscapes of the Mediterranean and the wider Classical world and their mapping, in turn, can shed light on fundamental aspects of ancient society that are not always documented in Classical texts.

scholarly journals Neural Architecture Search for a Highly Efficient Network with Random Skip Connections

2020 ◽  
Vol 10 (11) ◽  
pp. 3712
Author(s):  
Dongjing Shan ◽  
Xiongwei Zhang ◽  
Wenhua Shi ◽  
Li Li
Keyword(s):  
State Of The Art ◽  
Cell Structure ◽  
Frequency Discrimination ◽  
Search Space ◽  
Short Term ◽  
Cell Parameters ◽  
Neural Architecture ◽  
Proposed Model ◽  
Initialization Scheme

Regarding the sequence learning of neural networks, there exists a problem of how to capture long-term dependencies and alleviate the gradient vanishing phenomenon. To manage this problem, we proposed a neural network with random connections via a scheme of a neural architecture search. First, a dense network was designed and trained to construct a search space, and then another network was generated by random sampling in the space, whose skip connections could transmit information directly over multiple periods and capture long-term dependencies more efficiently. Moreover, we devised a novel cell structure that required less memory and computational power than the structures of long short-term memories (LSTMs), and finally, we performed a special initialization scheme on the cell parameters, which could permit unhindered gradient propagation on the time axis at the beginning of training. In the experiments, we evaluated four sequential tasks: adding, copying, frequency discrimination, and image classification; we also adopted several state-of-the-art methods for comparison. The experimental results demonstrated that our proposed model achieved the best performance.

Growing without Pains? Explaining Liberal Democrat MPs' Behaviour

2009 ◽  
Vol 11 (2) ◽  
pp. 259-279 ◽  
Author(s):  
Matt Cole
Keyword(s):  
Group Composition ◽  
National Party ◽  
Short Term ◽  
Contextual Data ◽  
Liberal Democrats ◽  
Composition Structure ◽  
High Level ◽  
Over Time

Recent academic studies and wider commentary on the behaviour of Liberal Democrat MPs have recognised their relatively high level of cohesiveness on whipped votes when compared to that of Labour and the Conservatives, and to the Liberal Democrats' own reputation; but while this trend continues, few studies have focused upon its causes. This article uses the MPs' voting records, personal papers, interviews and wider contextual data to chart the extent of that unity over time, and to explore its origins, including group composition, structure, patronage, relations with the extra-parliamentary party and other parties as well as national party image. It finds the key to this unity in a combination of medium and long-term features of the Liberal and Liberal Democrat group of MPs, rather than a short-term singular determinant.

scholarly journals Methodology of making organizational and technological decisions at the stage of operational management of construction operations based on the forecasting system

2021 ◽  
Vol 2131 (2) ◽  
pp. 022114
Author(s):  
L Zelentsov ◽  
L Mailyan ◽  
D Pirko
Keyword(s):  
Software Package ◽  
Complex Dynamic ◽  
Short Term ◽  
Current Management ◽  
Construction Operations ◽  
Construction Products ◽  
Forecasting System ◽  
High Level ◽  
Cost Parameters

Abstract The article discusses the issues of forecasting two key parameters of an investment and construction project: time and cost, while the building company is considered as a complex dynamic system. Taking into account the long-term nature of the creation of construction products and, as a consequence, the high level of work in progress, the need to use forecasting models is justified, both at short-term planning intervals (week, month) and at longer intervals (quarter, year). The article examines the formalized forecasting methods, gives a characteristic of the methods most widely used in practice. These methods include forecasting based on ARIMA models. DSTU has developed a pilot software package for an intelligent construction management system, which includes a software package for forecasting the time and cost parameters of a construction object at the stages of operational and current management.

scholarly journals Plasticity versus stability across the human cortical visual connectome

2019 ◽  
Author(s):  
Koen V. Haak ◽  
Christian F. Beckmann
Keyword(s):  
Visual Processing ◽  
Hierarchical Level ◽  
Recent Theory ◽  
Short Term ◽  
Visual Hierarchy ◽  
Short Term Adaptation ◽  
High Level ◽  
Open Question ◽  
The Brain

AbstractWhether and how the balance between plasticity and stability varies across the brain is an important open question. Within a processing hierarchy, it is thought that plasticity is increased at higher levels of cortical processing, but direct quantitative comparisons between low- and high-level plasticity have not been made so far. Here, we addressed this issue for the human cortical visual system. By quantifying plasticity as the complement of the heritability of functional connectivity, we demonstrate a non-monotonic relationship between plasticity and hierarchical level, such that plasticity decreases from early to mid-level cortex, and then increases further of the visual hierarchy. This non-monotonic relationship argues against recent theory that the balance between plasticity and stability is governed by the costs of the “coding-catastrophe”, and can be explained by a concurrent decline of short-term adaptation and rise of long-term plasticity up the visual processing hierarchy.

Sign in / Sign up

Export Citation Format

Share Document