Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of computer vision Ročník 123; číslo 1; s. 32 - 73
Hlavní autoři: Krishna, Ranjay, Zhu, Yuke, Groth, Oliver, Johnson, Justin, Hata, Kenji, Kravitz, Joshua, Chen, Stephanie, Kalantidis, Yannis, Li, Li-Jia, Shamma, David A., Bernstein, Michael S., Fei-Fei, Li
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.05.2017
Springer
Springer Nature B.V
Témata:
Analysis
Annotations
Artificial Intelligence
Carriages
Cognition & reasoning
Cognitive tasks
Computer Imaging
Computer Science
Computer simulation
Computer vision
Computers
Crowdsourcing
Datasets
Genomes
Genomics
Graph representations
Image Processing and Computer Vision
Image processing systems
Image retrieval
Language
Mathematical models
Natural language processing
Pattern Recognition
Pattern Recognition and Graphics
Questioning
Studies
Tasks
Vision
Vision systems
United States > US
Crowdsourcing
Computer vision
Relationships
Scene graph
Language
Dataset
Objects
Attributes
Question answering
Image
Knowledge
ISSN:0920-5691, 1573-1405
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked “What vehicle is the person riding?”, computers will need to identify the objects in an image as well as the relationships riding(man, carriage) and pulling(horse, carriage) to answer correctly that “the person is riding a horse-drawn carriage.” In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 108K images where each image has an average of 35 objects, 26 attributes, and 21 pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answer pairs.
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-016-0981-7