{"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/kefa-a-knowledge-enhanced-and-fine-grained","title":"Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction Generation","arxiv_id":"2307.13368","date":"2023-07-25","proceeding":null,"authors":["Haitian Zeng","Xiaohan Wang","Wenguan Wang","Yi Yang"],"abstract":"We introduce a novel speaker model \\textsc{Kefa} for navigation instruction generation. The existing speaker models in Vision-and-Language Navigation suffer from the large domain gap of vision features between different environments and insufficient temporal grounding capability. To address the challenges, we propose a Knowledge Refinement Module to enhance the feature representation with external knowledge facts, and an Adaptive Temporal Alignment method to enforce fine-grained alignment between the generated instructions and the observation sequences. Moreover, we propose a new metric SPICE-D for navigation instruction evaluation, which is aware of the correctness of direction phrases. The experimental results on R2R and UrbanWalk datasets show that the proposed KEFA speaker achieves state-of-the-art instruction generation performance for both indoor and outdoor scenes.","url_abs":"https://arxiv.org/abs/2307.13368v1","url_pdf":"https://arxiv.org/pdf/2307.13368v1.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":"kefa-a-knowledge-enhanced-and-fine-grained","repo_url":"https://github.com/haitianzeng/KEFA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2307.13368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}