{"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/chatterbox-multi-round-multimodal-referring","title":"ChatterBox: Multi-round Multimodal Referring and Grounding","arxiv_id":"2401.13307","date":"2024-01-24","proceeding":null,"authors":["Yunjie Tian","Tianren Ma","Lingxi Xie","Jihao Qiu","Xi Tang","Yuan Zhang","Jianbin Jiao","Qi Tian","Qixiang Ye"],"abstract":"In this study, we establish a baseline for a new task named multimodal multi-round referring and grounding (MRG), opening up a promising direction for instance-level multimodal dialogues. We present a new benchmark and an efficient vision-language model for this purpose. The new benchmark, named CB-300K, spans challenges including multi-round dialogue, complex spatial relationships among multiple instances, and consistent reasoning, which are beyond those shown in existing benchmarks. The proposed model, named ChatterBox, utilizes a two-branch architecture to collaboratively handle vision and language tasks. By tokenizing instance regions, the language branch acquires the ability to perceive referential information. Meanwhile, ChatterBox feeds a query embedding in the vision branch to a token receiver for visual grounding. A two-stage optimization strategy is devised, making use of both CB-300K and auxiliary external data to improve the model's stability and capacity for instance-level understanding. Experiments show that ChatterBox outperforms existing models in MRG both quantitatively and qualitatively, paving a new path towards multimodal dialogue scenarios with complicated and precise interactions. Code, data, and model are available at: https://github.com/sunsmarterjie/ChatterBox.","url_abs":"https://arxiv.org/abs/2401.13307v1","url_pdf":"https://arxiv.org/pdf/2401.13307v1.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":"chatterbox-multi-round-multimodal-referring","repo_url":"https://github.com/sunsmarterjie/chatterbox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.13307","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}