{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/enabling-my-robot-to-play-pictionary","title":"Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition","arxiv_id":"1608.03369","date":"2016-08-11","proceeding":null,"authors":["Ravi Kiran Sarvadevabhatla","Jogendra Kundu","Babu R. Venkatesh"],"abstract":"Freehand sketching is an inherently sequential process. Yet, most approaches\nfor hand-drawn sketch recognition either ignore this sequential aspect or\nexploit it in an ad-hoc manner. In our work, we propose a recurrent neural\nnetwork architecture for sketch object recognition which exploits the long-term\nsequential and structural regularities in stroke data in a scalable manner.\nSpecifically, we introduce a Gated Recurrent Unit based framework which\nleverages deep sketch features and weighted per-timestep loss to achieve\nstate-of-the-art results on a large database of freehand object sketches across\na large number of object categories. The inherently online nature of our\nframework is especially suited for on-the-fly recognition of objects as they\nare being drawn. Thus, our framework can enable interesting applications such\nas camera-equipped robots playing the popular party game Pictionary with human\nplayers and generating sparsified yet recognizable sketches of objects.","url_abs":"http://arxiv.org/abs/1608.03369v1","url_pdf":"http://arxiv.org/pdf/1608.03369v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"enabling-my-robot-to-play-pictionary","repo_url":"https://github.com/val-iisc/sketch-obj-rec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"sketch-recognition","task_name":"Sketch Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}