@inproceedings{35873f91b15d4e61a88e22be48176113,
title = "Visual Relationship Detection with Language prior and Softmax",
abstract = "Visual relationship detection is an intermediate image understanding task that detects two objects and classifies a predicate that explains the relationship between two objects in an image. The three components are linguistically and visually correlated (e.g. »wear» is related to »person» and »shirt», while »laptop» is related to »table» and »on») thus, the solution space is huge because there are many possible cases between them. Language and visual modules are exploited and a sophisticated spatial vector is proposed. The models in this work outperformed the state of arts without costly linguistic knowledge distillation from a large text corpus and building complex loss functions. All experiments were only evaluated on Visual Relationship Detection and Visual Genome dataset.",
keywords = "Deep learning, Image understanding, Visual relationship",
author = "Jaewon Jung and Jongyoul Park",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 3rd IEEE International Conference on Image Processing, Applications and Systems, IPAS 2018 ; Conference date: 12-12-2018 Through 14-12-2018",
year = "2018",
month = jul,
day = "2",
doi = "10.1109/IPAS.2018.8708855",
language = "English",
series = "IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "143--148",
booktitle = "IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018",
}