DeepAI AI Chat
Log In Sign Up

Scene Graph Generation with Geometric Context

by   Vishal Kumar, et al.
Indian Institute of Information Technology, Allahabad, India

Scene Graph Generation has gained much attention in computer vision research with the growing demand in image understanding projects like visual question answering, image captioning, self-driving cars, crowd behavior analysis, activity recognition, and more. Scene graph, a visually grounded graphical structure of an image, immensely helps to simplify the image understanding tasks. In this work, we introduced a post-processing algorithm called Geometric Context to understand the visual scenes better geometrically. We use this post-processing algorithm to add and refine the geometric relationships between object pairs to a prior model. We exploit this context by calculating the direction and distance between object pairs. We use Knowledge Embedded Routing Network (KERN) as our baseline model, extend the work with our algorithm, and show comparable results on the recent state-of-the-art algorithms.


Rethinking Visual Relationships for High-level Image Understanding

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

Are scene graphs good enough to improve Image Captioning?

Many top-performing image captioning models rely solely on object featur...

Assisting Scene Graph Generation with Self-Supervision

Research in scene graph generation has quickly gained traction in the pa...

Graph Neural Networks in Vision-Language Image Understanding: A Survey

2D image understanding is a complex problem within Computer Vision, but ...

Generating Triples with Adversarial Networks for Scene Graph Construction

Driven by successes in deep learning, computer vision research has begun...

TPsgtR: Neural-Symbolic Tensor Product Scene-Graph-Triplet Representation for Image Captioning

Image captioning can be improved if the structure of the graphical repre...