{"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/a-joint-speaker-listener-reinforcer-model-for","title":"A Joint Speaker-Listener-Reinforcer Model for Referring Expressions","arxiv_id":"1612.09542","date":"2016-12-30","proceeding":"CVPR 2017 7","authors":["Licheng Yu","Hao Tan","Mohit Bansal","Tamara L. Berg"],"abstract":"Referring expressions are natural language constructions used to identify\nparticular objects within a scene. In this paper, we propose a unified\nframework for the tasks of referring expression comprehension and generation.\nOur model is composed of three modules: speaker, listener, and reinforcer. The\nspeaker generates referring expressions, the listener comprehends referring\nexpressions, and the reinforcer introduces a reward function to guide sampling\nof more discriminative expressions. The listener-speaker modules are trained\njointly in an end-to-end learning framework, allowing the modules to be aware\nof one another during learning while also benefiting from the discriminative\nreinforcer's feedback. We demonstrate that this unified framework and training\nachieves state-of-the-art results for both comprehension and generation on\nthree referring expression datasets. Project and demo page:\nhttps://vision.cs.unc.edu/refer","url_abs":"http://arxiv.org/abs/1612.09542v2","url_pdf":"http://arxiv.org/pdf/1612.09542v2.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":"a-joint-speaker-listener-reinforcer-model-for","repo_url":"https://github.com/lichengunc/speaker_listener_reinforcer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"a-joint-speaker-listener-reinforcer-model-for","repo_url":"https://github.com/mikittt/re-SLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.09542","atlas_url":"https://app.syntology.ai/?focus=1612.09542","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}