Soft Semantic Representation for Cross-Domain Face Recognition

2021 ◽  
Vol 16 ◽  
pp. 346-360
Author(s):  
Chunlei Peng ◽  
Nannan Wang ◽  
Jie Li ◽  
Xinbo Gao
2018 ◽  
Vol 9 ◽  
Author(s):  
Anna Krasotkina ◽  
Antonia Götz ◽  
Barbara Höhle ◽  
Gudrun Schwarzer

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 50452-50464 ◽  
Author(s):  
Han Byeol Bae ◽  
Taejae Jeon ◽  
Yongju Lee ◽  
Sungjun Jang ◽  
Sangyoun Lee

2020 ◽  
Vol 28 (10) ◽  
pp. 2311-2322
Author(s):  
Yue MING ◽  
◽  
Shao-Ying WANG ◽  
Chun-Xiao FAN ◽  
Jiang-Wan ZHOU

Author(s):  
A. U. Usmani ◽  
M. Jadidi ◽  
G. Sohn

Abstract. Establishing semantic interoperability between BIM and GIS is vital for geospatial information exchange. Semantic web have a natural ability to provide seamless semantic representation and integration among the heterogeneous domains like BIM and GIS through employing ontology. Ontology models can be defined (or generated) using domain-data representations and further aligned across other ontologies by the semantic similarity of their entities - introducing cross-domain ontologies to achieve interoperability of heterogeneous information. However, due to extensive semantic features and complex alignment (mapping) relations between BIM and GIS data formats, many approaches are far from generating semantically-rich ontologies and perform effective alignment to address geospatial interoperability. This study highlights the fundamental perspectives to be addressed for BIM and GIS interoperability and proposes a comprehensive conceptual framework for automatic ontology generation followed by ontology alignment of open-standards for BIM and GIS data formats. It presents an approach based on transformation patterns to automatically generate ontology models, and semantic-based and structure-based alignment techniques to form cross-domain ontology. Proposed two-phase framework provides ontology model generation for input XML schemas (i.e. of IFC and CityGML formats), and illustrates alignment technique to potentially develop a cross-domain ontology. The study concludes anticipated results of cross-domain ontology can provides future perspectives in knowledge-discovery applications and seamless information exchange for BIM and GIS.


1988 ◽  
Vol 40 (3) ◽  
pp. 561-580 ◽  
Author(s):  
Andrew W. Young ◽  
Deborah Hellawell ◽  
Edward H. F. De Haan

Cross-domain semantic priming of person recognition (from face primes to name targets at 500msecs SOA) is investigated in normal subjects and a brain-injured patient (PH) with a very severe impairment of overt face recognition ability. Experiment 1 demonstrates equivalent semantic priming effects for normal subjects from face primes to name targets (cross-domain priming) and from name primes to name targets (within-domain priming). Experiment 2 demonstrates cross-domain semantic priming effects from face primes that PH cannot recognize overtly. Experiment 3 shows that cross-domain semantic priming effects can be found for normal subjects when target names are repeated across all conditions. This (repeated targets) method is then used in Experiment 4 to establish that PH shows equivalent semantic priming to normal subjects from face primes which he is very poor at identifying overtly and from name primes which he can identify overtly. These findings demonstrate that automatic aspects of face recognition can remain intact even when all sense of overt recognition has been lost.


IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 97503-97515 ◽  
Author(s):  
Dongdong Zheng ◽  
Kaibing Zhang ◽  
Jian Lu ◽  
Junfeng Jing ◽  
Zenggang Xiong

2021 ◽  
Author(s):  
Masoud Faraki ◽  
Xiang Yu ◽  
Yi-Hsuan Tsai ◽  
Yumin Suh ◽  
Manmohan Chandraker

2021 ◽  
Vol 336 ◽  
pp. 06007
Author(s):  
Yuying Shao ◽  
Lin Cao ◽  
Changwu Chen ◽  
Kangning Du

Because of the large modal difference between sketch image and optical image, and the problem that traditional deep learning methods are easy to overfit in the case of a small amount of training data, the Cross Domain Meta-Network for sketch face recognition method is proposed. This method first designs a meta-learning training strategy to solve the small sample problem, and then proposes entropy average loss and cross domain adaptive loss to reduce the modal difference between the sketch domain and the optical domain. The experimental results on UoM-SGFS and PRIP-VSGC sketch face data sets show that this method and other sketch face recognition methods.


Sign in / Sign up

Export Citation Format

Share Document