Game of Sketches: Deep Recurrent Models of Pictionary-Style Word Guessing

Authors

  • Ravi Kiran Sarvadevabhatla Indian Institute of Science
  • Shiv Surya Indian Institute of Science
  • Trisha Mittal Indian Institute of Science
  • R. Venkatesh Babu Indian Institute of Science

Keywords:

Pictionary, Sketches, AI, Deep Learning

Abstract

The ability of machine-based agents to play games in human-like fashion is considered a benchmark of progress in AI. In this paper, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA, an elementary version of Visual Question Answering task. Styled after Pictionary, Sketch-QA uses incrementally accumulated sketch stroke sequences as visual data. Notably, Sketch-QA involves asking a fixed question ("What object is being drawn?") and gathering open-ended guess-words from human guessers. To mimic Pictionary-style guessing, we propose a deep neural model which generates guess-words in response to temporally evolving human-drawn sketches. Our model even makes human-like mistakes while guessing, thus amplifying the human mimicry factor. We evaluate our model on the large-scale guess-word dataset generated via Sketch-QA task and compare with various baselines. We also conduct a Visual Turing Test to obtain human impressions of the guess-words generated by humans and our model. Experimental results demonstrate the promise of our approach for Pictionary and similarly themed games.

Downloads

Published

2018-04-27

How to Cite

Sarvadevabhatla, R. K., Surya, S., Mittal, T., & Babu, R. V. (2018). Game of Sketches: Deep Recurrent Models of Pictionary-Style Word Guessing. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12273