{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/mattnet-modular-attention-network-for","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","arxiv_id":"1801.08186","date":"2018-01-24","proceeding":"CVPR 2018 6","authors":["Licheng Yu","Zhe Lin","Xiaohui Shen","Jimei Yang","Xin Lu","Mohit Bansal","Tamara L. Berg"],"abstract":"In this paper, we address referring expression comprehension: localizing an\nimage region described by a natural language expression. While most recent work\ntreats expressions as a single unit, we propose to decompose them into three\nmodular components related to subject appearance, location, and relationship to\nother objects. This allows us to flexibly adapt to expressions containing\ndifferent types of information in an end-to-end framework. In our model, which\nwe call the Modular Attention Network (MAttNet), two types of attention are\nutilized: language-based attention that learns the module weights as well as\nthe word/phrase attention that each module should focus on; and visual\nattention that allows the subject and relationship modules to focus on relevant\nimage components. Module weights combine scores from all three modules\ndynamically to output an overall score. Experiments show that MAttNet\noutperforms previous state-of-art methods by a large margin on both\nbounding-box-level and pixel-level comprehension tasks. Demo and code are\nprovided.","url_abs":"http://arxiv.org/abs/1801.08186v3","url_pdf":"http://arxiv.org/pdf/1801.08186v3.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":"mattnet-modular-attention-network-for","repo_url":"https://github.com/lichengunc/MAttNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"generalized-referring-expression-segmentation","task_name":"Generalized Referring Expression Segmentation"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-referring-expression-segmentation","task":"Generalized Referring Expression Segmentation","dataset":"gRefCOCO","model":"MattNet","rank_in_archive_order":13,"of":13,"metrics":{"cIoU":"47.51","gIoU":"48.24"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","task":"Referring Expression Segmentation","dataset":"RefCOCO+ test B","model":"MattNet","rank_in_archive_order":26,"of":30,"metrics":{"Overall IoU":"40.08"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","model":"MattNet","rank_in_archive_order":26,"of":30,"metrics":{"Overall IoU":"52.39"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"MattNet","rank_in_archive_order":30,"of":33,"metrics":{"Overall IoU":"46.67"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"MattNet","rank_in_archive_order":36,"of":37,"metrics":{"Overall IoU":"56.51"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.08186","atlas_url":"https://app.syntology.ai/?focus=1801.08186","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1801.08186"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.08186\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.08186"},"call":"get_concepts_for_paper(arxiv_id=\"1801.08186\")"}],"by_repo":[{"repo":"lichengunc/MAttNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"307b5fbe8f283796f5f34b8083362ac9201944b9398544fb22124aa1a7077c8b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}