SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1708.04320 · 2017

Situation Recognition with Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We address the problem of recognizing situations in images. Given an image, the task is to predict the most salient verb (action), and fill its semantic roles such as who is performing the action, what is the source and target of the action, etc. Different verbs have different roles (e.g. attacking has weapon), and each role can take on many possible values (nouns). We propose a model based on Graph Neural Networks that allows us to efficiently capture joint dependencies between roles using neural networks defined on a graph. Experiments with different graph connectivities show that our approach that propagates information between roles significantly outperforms existing work, as well as multiple baselines. We obtain roughly 3-5% improvement over previous work in predicting the full situation. We also provide a thorough qualitative analysis of our model and influence of different roles in the verbs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1708.04320")
get_code_for_paper("1708.04320")
have("1708.04320")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1708.04320.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1708.04320.svg)](https://syntology.ai/paper/1708.04320)

Connect an agent — have() is free.