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

by   Ranjay Krishna, et al.

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) in order 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 100K images where each image has an average of 21 objects, 18 attributes, and 18 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 answers.


page 4

page 6

page 8

page 17

page 23

page 36

page 38

page 39


Scene Graph Reasoning for Visual Question Answering

Visual question answering is concerned with answering free-form question...

Rethinking Visual Relationships for High-level Image Understanding

Relationships, as the bond of isolated entities in images, reflect the i...

Detecting Visual Relationships with Deep Relational Networks

Relationships among objects play a crucial role in image understanding. ...

Image-based Recommendations on Styles and Substitutes

Humans inevitably develop a sense of the relationships between objects, ...

MetaCLUE: Towards Comprehensive Visual Metaphors Research

Creativity is an indispensable part of human cognition and also an inher...

Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection

Despite progress in visual perception tasks such as image classification...

Automatic Understanding of Image and Video Advertisements

There is more to images than their objective physical content: for examp...

Please sign up or login with your details

Forgot password? Click here to reset