• DOI:10.1609/aaai.v33i01.330110027
• Corpus ID: 53983880

Towards Task Understanding in Visual Settings

@article{Santy2019TowardsTU,
  title={Towards Task Understanding in Visual Settings},
  author={Sebastin Santy and Wazeer Zulfikar and Rishabh Mehrotra and Emine Yilmaz},
  journal={ArXiv},
  year={2019},
  volume={abs/1811.11833}
}

• Sebastin Santy, Wazeer Zulfikar, +1 author Emine Yilmaz
• Published 28 November 2018
• Computer Science
• ArXiv

We consider the problem of understanding real world tasks depicted in visual images. While most existing image captioning methods excel in producing natural language descriptions of visual scenes involving human tasks, there is often the need for an understanding of the exact task being undertaken rather than a literal description of the scene. We leverage insights from real world task understanding systems, and propose a framework composed of convolutional neural networks, and an external hierarchical task ontology to produce task descriptions from input images. Detailed experiments highlight the efficacy of the extracted descriptions, which could potentially find their way in many applications, including image alt text generation.