A Symmetric Fusion Learning Model for Detecting Visual Relations and Scene Parsing

<div>An example of predicting the semantic relationship between multiple objects from an image and parsing the scene graph: (a) an input image with bounding boxes, (b) the interactions between objects in an image, and (c) an example of parsing a scene graph.</div>

Scientific Programming

fig1

Figure 1

Figure 1: A Symmetric Fusion Learning Model for Detecting Visual Relations and Scene Parsing 