High‐level feature aggregation for fine‐grained architectural floor plan retrieval

Person re-identification (ReID) plays a significant role in video surveillance analysis. In the real world, due to illumination, occlusion, and deformation, pedestrian features extraction is the key to person ReID. Considering the shortcomings of existing methods in pedestrian features extraction, a method based on attention mechanism and context information fusion is proposed. A lightweight attention module is introduced into ResNet50 backbone network equipped with a small number of network parameters, which enhance the significant characteristics of person and suppress irrelevant information. Aiming at the problem of person context information loss due to the over depth of the network, a context information fusion module is designed to sample the shallow feature map of pedestrians and cascade with the high-level feature map. In order to improve the robustness, the model is trained by combining the loss of margin sample mining with the loss function of cross entropy. Experiments are carried out on datasets Market1501 and DukeMTMC-reID, our method achieves rank-1 accuracy of 95.9% on the Market1501 dataset, and 90.1% on the DukeMTMC-reID dataset, outperforming the current mainstream method in case of only using global feature.

Download Full-text

Deep AI Enabled Ubiquitous Wireless Sensing

ACM Computing Surveys ◽

10.1145/3436729 ◽

2021 ◽

Vol 54 (2) ◽

pp. 1-35

Author(s):

Chenning Li ◽

Zhichao Cao ◽

Yunhao Liu

Keyword(s):

Great Success ◽

Wireless Sensing ◽

Ubiquitous Sensing ◽

Sensing Systems ◽

The Status ◽

Sensing Model ◽

High Level ◽

Traditional Approaches ◽

The Internet Of Things ◽

High Level Feature

With the development of the Internet of Things (IoT), many kinds of wireless signals (e.g., Wi-Fi, LoRa, RFID) are filling our living and working spaces nowadays. Beyond communication, wireless signals can sense the status of surrounding objects, known as wireless sensing , with their reflection, scattering, and refraction while propagating in space. In the last decade, many sophisticated wireless sensing techniques and systems were widely studied for various applications (e.g., gesture recognition, localization, and object imaging). Recently, deep Artificial Intelligence (AI), also known as Deep Learning (DL), has shown great success in computer vision. And some works have initially proved that deep AI can benefit wireless sensing as well, leading to a brand-new step toward ubiquitous sensing. In this survey, we focus on the evolution of wireless sensing enhanced by deep AI techniques. We first present a general workflow of Wireless Sensing Systems (WSSs) which consists of signal pre-processing, high-level feature, and sensing model formulation. For each module, existing deep AI-based techniques are summarized, further compared with traditional approaches. Then, we provide a view of issues and challenges induced by combining deep AI and wireless sensing together. Finally, we discuss the future trends of deep AI to enable ubiquitous wireless sensing.

Download Full-text

A challenge for historical research: Making data FAIR using a collaborative ontology management environment (OntoME)

Semantic Web ◽

10.3233/sw-200416 ◽

2020 ◽

pp. 1-16

Author(s):

Francesco Beretta

Keyword(s):

Semantic Analysis ◽

Historical Research ◽

Data Modelling ◽

Fine Grained ◽

Fair Principles ◽

Active Research ◽

New Research ◽

High Level ◽

Conceptual Data ◽

Ontology Management

This paper addresses the issue of interoperability of data generated by historical research and heritage institutions in order to make them re-usable for new research agendas according to the FAIR principles. After introducing the symogih.org project’s ontology, it proposes a description of the essential aspects of the process of historical knowledge production. It then develops an epistemological and semantic analysis of conceptual data modelling applied to factual historical information, based on the foundational ontologies Constructive Descriptions and Situations and DOLCE, and discusses the reasons for adopting the CIDOC CRM as a core ontology for the field of historical research, but extending it with some relevant, missing high-level classes. Finally, it shows how collaborative data modelling carried out in the ontology management environment OntoME makes it possible to elaborate a communal fine-grained and adaptive ontology of the domain, provided an active research community engages in this process. With this in mind, the Data for history consortium was founded in 2017 and promotes the adoption of a shared conceptualization in the field of historical research.

Download Full-text

One-IPC high-level simulation of microthreaded many-core architectures

The International Journal of High Performance Computing Applications ◽

10.1177/1094342015584495 ◽

2016 ◽

Vol 31 (2) ◽

pp. 152-162 ◽

Cited By ~ 3

Author(s):

Irfan Uddin

Keyword(s):

Design Space Exploration ◽

Instruction Set ◽

Efficient Design ◽

Simulation Framework ◽

Fine Grained ◽

Detailed Simulation ◽

High Level ◽

Many Core ◽

The Cost ◽

Multiple Clusters

The microthreaded many-core architecture is comprised of multiple clusters of fine-grained multi-threaded cores. The management of concurrency is supported in the instruction set architecture of the cores and the computational work in application is asynchronously delegated to different clusters of cores, where the cluster is allocated dynamically. Computer architects are always interested in analyzing the complex interaction amongst the dynamically allocated resources. Generally a detailed simulation with a cycle-accurate simulation of the execution time is used. However, the cycle-accurate simulator for the microthreaded architecture executes at the rate of 100,000 instructions per second, divided over the number of simulated cores. This means that the evaluation of a complex application executing on a contemporary multi-core machine can be very slow. To perform efficient design space exploration we present a co-simulation environment, where the detailed execution of instructions in the pipeline of microthreaded cores and the interactions amongst the hardware components are abstracted. We present the evaluation of the high-level simulation framework against the cycle-accurate simulation framework. The results show that the high-level simulator is faster and less complicated than the cycle-accurate simulator but with the cost of losing accuracy.

Download Full-text

Insulators Recognition Based on Enhancement of High-Level Feature with Improved Attention Method

10.1109/phm-nanjing52125.2021.9613029 ◽

2021 ◽

Author(s):

Yixiao Li ◽

Honghao Liu ◽

Huan Wang ◽

Zhiliang Liu

Keyword(s):

High Level ◽

High Level Feature

Download Full-text

Shape-Based Floor Plan Retrieval Using Parse Tree Matching

10.23919/mva51890.2021.9511363 ◽

2021 ◽

Author(s):

Philip K. Lee ◽

Bjorn Stenger

Keyword(s):

Parse Tree ◽

Floor Plan ◽

Plan Retrieval

Download Full-text

Stories as Technology: Past, Present, and Future

Seeds of Science ◽

10.53975/wlv3-sr8m ◽

2021 ◽

Author(s):

Roger’s Bacon ◽

Sergey Samsonau ◽

Dario Krpan ◽

◽

Keyword(s):

Social Cognitive ◽

Fine Grained ◽

Good Story ◽

High Level ◽

Future Technologies

What is it about a good story that causes it to have life-changing effects on one person and not another? I wonder if future technologies will enable us to develop the type of truly deep and fine-grained understanding of stories as social, cognitive, and emotional technologies that might allow us to answer this question with a high-level of precision.

Download Full-text

Entity Type Recognition for Heterogeneous Semantic Graphs

AI Magazine ◽

10.1609/aimag.v36i1.2569 ◽

2015 ◽

Vol 36 (1) ◽

pp. 75-86 ◽

Cited By ~ 4

Author(s):

Jennifer Sleeman ◽

Tim Finin ◽

Anupam Joshi

Keyword(s):

Machine Learning ◽

Background Knowledge ◽

Knowledge Bases ◽

Heterogeneous Data ◽

Unstructured Data ◽

Supervised Machine Learning ◽

Coreference Resolution ◽

Multiple Sources ◽

Fine Grained ◽

High Level

We describe an approach for identifying fine-grained entity types in heterogeneous data graphs that is effective for unstructured data or when the underlying ontologies or semantic schemas are unknown. Identifying fine-grained entity types, rather than a few high-level types, supports coreference resolution in heterogeneous graphs by reducing the number of possible coreference relations that must be considered. Big data problems that involve integrating data from multiple sources can benefit from our approach when the datas ontologies are unknown, inaccessible or semantically trivial. For such cases, we use supervised machine learning to map entity attributes and relations to a known set of attributes and relations from appropriate background knowledge bases to predict instance entity types. We evaluated this approach in experiments on data from DBpedia, Freebase, and Arnetminer using DBpedia as the background knowledge base.

Download Full-text

Explaining continuous improvement

10.1093/oso/9780198852261.003.0010 ◽

2021 ◽

pp. 197-210

Author(s):

John Toner ◽

Barbara Gail Montero ◽

Aidan Moran

Keyword(s):

Continuous Improvement ◽

Focused Attention ◽

Fine Grained ◽

Skill Maintenance ◽

And Performance ◽

Situational Demands ◽

High Level ◽

Conscious Processes ◽

Automated Procedures

The final chapter synthesizes the arguments presented over the course of the book by suggesting that skill execution continues to be governed by conscious processes even after performers have attained a high level of expertise. It argues that skill-focused attention is necessary if experts are to eschew proceduralization and react flexibly to ‘crises’ and fine-grained changes in situational demands. In doing so, it discusses the role played by conscious control, reflection, and bodily awareness in maintaining performance proficiency. It suggests that skill maintenance and continuous improvement are underpinned by the use of both automated procedures (acknowledging that these are inherently active and flexible) and metacognitive knowledge. The chapter concludes by briefly considering how skill-focused attention needs to be applied in both training and performance contexts in order to facilitate continuous improvement.

Download Full-text