# Describing Common Human Visual Actions in Images

Source: [Describing Common Human Visual Actions in Images](<https://www.sota2.com/research/paper/68fa61e61e209131ce9f685b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:08:28.563Z

Authors: Matteo Ruggero Ronchi, Pietro Perona

Published: 2015-06-07T00:33:23.000Z

## Abstract

Which common human actions and interactions are recognizable in monocular still images? Which involve objects and/or other people? How many is a person performing at a time? We address these questions by exploring the actions and interactions that are detectable in the images of the MS COCO dataset. We make two main contributions. First, a list of 140 common \`visual actions', obtained by analyzing the largest on-line verb lexicon currently available for English (VerbNet) and human sentences used to describe images in MS COCO. Second, a complete set of annotations for those \`visual actions', composed of subject-object and associated verb, which we call COCO-a (a for \`actions'). COCO-a is larger than existing action datasets in terms of number of actions and instances of these actions, and is unique because it is data-driven, rather than experimenter-biased. Other unique features are that it is exhaustive, and that all subjects and objects are localized. A statistical analysis of the accuracy of our annotations and of each action, interaction and subject-object combination is provided.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1506.02203>)

[PDF](<https://arxiv.org/pdf/1506.02203.pdf>)