Semantic Image Retrieval via Active Grounding of Visual Situations

Quinn, Max H.; Conser, Erik; Witte, Jordan M.; Mitchell, Melanie

doi:10.48550/arxiv.1711.00088

Search citation statements

Order By: Relevance

Paper Sections

Select...

Semantic Image Retrieval1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2018

Publication Types

Select...

Book1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A common approach to retrieve images with semantic structure through the learning is to train deep models on images with joint labels of several classes which form complex concepts and learn a relationship model that represents the expected spatial relationships among the relevant objects for retrieval of instances of visual situations [10]. For example, if we have labels for person and bicycle with corresponding relation we can train model to a new concept -cyclist.…”

Section: Semantic Image Retrievalmentioning

confidence: 99%

Semantic Image Retrieval by Uniting Deep Neural Networks and Cognitive Architectures

Potapov

Zhdanov

Scherbakov

et al. 2018

Artificial General Intelligence

View full text Add to dashboard Cite

Image and video retrieval by their semantic content has been an important and challenging task for years, because it ultimately requires bridging the symbolic/subsymbolic gap. Recent successes in deep learning enabled detection of objects belonging to many classes greatly outperforming traditional computer vision techniques. However, deep learning solutions capable of executing retrieval queries are still not available. We propose a hybrid solution consisting of a deep neural network for object detection and a cognitive architecture for query execution. Specifically, we use YOLOv2 and OpenCog. Queries allowing the retrieval of video frames containing objects of specified classes and specified spatial arrangement are implemented.

show abstract

Section: Semantic Image Retrievalmentioning

confidence: 99%