{"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/cascaded-mutual-modulation-for-visual","title":"Cascaded Mutual Modulation for Visual Reasoning","arxiv_id":"1809.01943","date":"2018-09-06","proceeding":"EMNLP 2018 10","authors":["Yiqun Yao","Jiaming Xu","Feng Wang","Bo Xu"],"abstract":"Visual reasoning is a special visual question answering problem that is\nmulti-step and compositional by nature, and also requires intensive text-vision\ninteractions. We propose CMM: Cascaded Mutual Modulation as a novel end-to-end\nvisual reasoning model. CMM includes a multi-step comprehension process for\nboth question and image. In each step, we use a Feature-wise Linear Modulation\n(FiLM) technique to enable textual/visual pipeline to mutually control each\nother. Experiments show that CMM significantly outperforms most related models,\nand reach state-of-the-arts on two visual reasoning benchmarks: CLEVR and NLVR,\ncollected from both synthetic and natural languages. Ablation studies confirm\nthat both our multistep framework and our visual-guided language modulation are\ncritical to the task. Our code is available at\nhttps://github.com/FlamingHorizon/CMM-VR.","url_abs":"http://arxiv.org/abs/1809.01943v1","url_pdf":"http://arxiv.org/pdf/1809.01943v1.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":"cascaded-mutual-modulation-for-visual","repo_url":"https://github.com/FlamingHorizon/CMM-VR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.01943","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}