Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text
Christopher Clark, Jordi Salvador, Dustin Schwenk, Derrick Bonafilia, Mark Yatskar, Eric Kolve, Alvaro Herrasti, Jonghyun Choi, Sachin Mehta, Sam Skjonsberg, Carissa Schoenick, Aaron Sarnat
Abstract
Communicating with humans is challenging for AIs because it requires a shared understanding of the world, complex semantics (e.g., metaphors or analogies), and at times multimodal gestures (e.g., pointing with a finger, or an arrow in a diagram). We investigate these challenges in the context of Iconary, a collaborative game of drawing and guessing based on Pictionary, that poses a novel challenge for the research community. In Iconary, a Guesser tries to identify a phrase that a Drawer is drawing by composing icons, and the Drawer iteratively revises the drawing to help the Guesser in response. This back-and-forth often uses canonical scenes, visual metaphor, or icon compositions to express challenging words, making it an ideal test for mixing language and visual/symbolic communication in AI. We propose models to play Iconary and train them on over 55,000 games between human players. Our models are skillful players and are able to employ world knowledge in language models to play with words unseen during training. Elite human players outperform our models, particularly at the drawing task, leaving an important gap for future research to address. We release our dataset, code, and evaluation setup as a challenge to the community at github.com/allenai/iconary. Annotations 18.5%, 22.0% A noun is drawn by composing multiple icons, such as drawing 'sprinkler' with a spray bottle, drop, and fountain icons. Composition 47.5%, 64.0% Arrows, crosses, checkmarks, or circles guide interpretation, such as an arrow to indicate a part or crosses to specify incorrect options. Repurposing 22.5%, 32.0% An icon is used to represent an object different than its intended meaning, such as a scarf for 'scabbard', or box + ring for 'boxing ring'. Verb Scene 25.0%, 44.5% Multiple icons are arranged in a scene to indicate the verb. Verb Icon 41.0%, 25.5% A single icon is used to indicate the verb, such as hammer for 'building' or eyes for 'reading'. Verb Arrows 22.0%, 25.5% The verb is indicated by using arrows to show motion.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers2
- DrawMon: A Distributed System for Detection of Atypical Sketch Content in Concurrent Pictionary GamesNikhil Bansal, Kartik Gupta, Kiruthika Kannan, Sivani Pentapati et al.ACM MM 2022 · 1 citation
- Sketchtopia: A Dataset and Foundational Agents for Benchmarking Asynchronous Multimodal Communication with Iconic FeedbackMohd Hozaifa Khan, Ravi Kiran SarvadevabhatlaCVPR 2025
Builds on3
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal TransformersJaemin Cho, Jiasen Lu, Dustin Schwenk, Hannaneh Hajishirzi et al.EMNLP 2020 · 80 citations
- PowerTransformer: Unsupervised Controllable Revision for Biased Language CorrectionXinyao Ma, Maarten Sap, Hannah Rashkin, Yejin ChoiEMNLP 2020 · 50 citations
Related papers
- Emergent Communication of GeneralizationsJesse Mu, Noah D. GoodmanNeurIPS 2021 · 60 citations
- More Victories, Less Cooperation: Assessing Cicero's Diplomacy PlayWichayaporn Wongkamjan, Feng Gu, Yanze Wang, Ulf Hermjakob et al.ACL 2024
- Emergent Graphical Conventions in a Visual Communication GameShuwen Qiu, Sirui Xie, Lifeng Fan, Tao Gao et al.NeurIPS 2022 · 18 citations
- Iconix: Controlling Semantics and Style in Progressive Icon Grids GenerationZhida Sun, Xiaodong Wang, Zhenyao Zhang, Min Lu et al.CHI 2026 · 1 citation
- Unicode Analogies: An Anti-Objectivist Visual Reasoning ChallengeSteven Spratley, Krista A. Ehinger, Tim MillerCVPR 2023
