Visual Semantic Role Labeling

TL;DR

This paper introduces Visual Semantic Role Labeling, a new task that involves detecting people performing actions and localizing objects associated with specific semantic roles, advancing beyond traditional action recognition methods.

Contribution

It defines the task of Visual Semantic Role Labeling, creates a dataset with annotated actions and object roles, and provides baseline algorithms for future research.

Findings

Annotated 16K people instances in 10K images with action and object role labels.

Provided baseline algorithms and analyzed common error modes.

Outlined directions for improving semantic understanding in visual scenes.

Abstract

In this paper we introduce the problem of Visual Semantic Role Labeling: given an image we want to detect people doing actions and localize the objects of interaction. Classical approaches to action recognition either study the task of action classification at the image or video clip level or at best produce a bounding box around the person doing the action. We believe such an output is inadequate and a complete understanding can only come when we are able to associate objects in the scene to the different semantic roles of the action. To enable progress towards this goal, we annotate a dataset of 16K people instances in 10K images with actions they are doing and associate objects in the scene with different semantic roles for each action. Finally, we provide a set of baseline algorithms for this task and analyze error modes providing directions for future work.