{"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/dual-attention-networks-for-visual-reference","title":"Dual Attention Networks for Visual Reference Resolution in Visual Dialog","arxiv_id":"1902.09368","date":"2019-02-25","proceeding":"IJCNLP 2019 11","authors":["Gi-Cheon Kang","Jaeseo Lim","Byoung-Tak Zhang"],"abstract":"Visual dialog (VisDial) is a task which requires an AI agent to answer a series of questions grounded in an image. Unlike in visual question answering (VQA), the series of questions should be able to capture a temporal context from a dialog history and exploit visually-grounded information. A problem called visual reference resolution involves these challenges, requiring the agent to resolve ambiguous references in a given question and find the references in a given image. In this paper, we propose Dual Attention Networks (DAN) for visual reference resolution. DAN consists of two kinds of attention networks, REFER and FIND. Specifically, REFER module learns latent relationships between a given question and a dialog history by employing a self-attention mechanism. FIND module takes image features and reference-aware representations (i.e., the output of REFER module) as input, and performs visual grounding via bottom-up attention mechanism. We qualitatively and quantitatively evaluate our model on VisDial v1.0 and v0.9 datasets, showing that DAN outperforms the previous state-of-the-art model by a significant margin.","url_abs":"https://arxiv.org/abs/1902.09368v3","url_pdf":"https://arxiv.org/pdf/1902.09368v3.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":"dual-attention-networks-for-visual-reference","repo_url":"https://github.com/gicheonkang/DAN-VisDial","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dual-attention-networks-for-visual-reference","repo_url":"https://github.com/phellonchen/DMRM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"ai-agent","task_name":"AI Agent"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-dialogue","task_name":"Visual Dialog"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-dialog-on-visdial-v09-val","task":"Visual Dialog","dataset":"VisDial v0.9 val","model":"DAN","rank_in_archive_order":2,"of":18,"metrics":{"MRR":"66.38","Mean Rank":"4.04","R@1":"53.33","R@10":"90.38","R@5":"82.42"},"uses_additional_data":false},{"leaderboard":"/sota/visual-dialog-on-visual-dialog-v1-0-test-std","task":"Visual Dialog","dataset":"Visual Dialog v1.0 test-std","model":"DAN","rank_in_archive_order":55,"of":80,"metrics":{"MRR (x 100)":"63.2","Mean":"4.3","NDCG (x 100)":"57.59","R@1":"49.63","R@10":"89.35","R@5":"79.75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09368"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gicheonkang/DAN-VisDial","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phellonchen/DMRM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":6},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":3,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1df9a5ffd9b38c34","entry":"pil_loader","repo":"phellonchen/DMRM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/phellonchen/DMRM/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1df9a5ffd9b38c34"}},{"code_sha256_prefix":"40ad7ca583756bff","entry":"create_glove_embedding_init","repo":"gicheonkang/DAN-VisDial","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/gicheonkang/DAN-VisDial/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40ad7ca583756bff"}},{"code_sha256_prefix":"72d5007cbbf2c295","entry":"get_gt_ranks","repo":"gicheonkang/DAN-VisDial","repo_kind":"official","path":"utils/eval_utils.py","file_url":"https://github.com/gicheonkang/DAN-VisDial/blob/HEAD/utils/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72d5007cbbf2c295"}},{"code_sha256_prefix":"8c1252eacab71602","entry":"load_folder","repo":"phellonchen/DMRM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/phellonchen/DMRM/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c1252eacab71602"}},{"code_sha256_prefix":"bf90bd27fe08f3a2","entry":"load_imageid","repo":"phellonchen/DMRM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/phellonchen/DMRM/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf90bd27fe08f3a2"}},{"code_sha256_prefix":"e90714af510bbb7f","entry":"load_imageid","repo":"gicheonkang/DAN-VisDial","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/gicheonkang/DAN-VisDial/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e90714af510bbb7f"}},{"code_sha256_prefix":"26ec77dabb4db96d","entry":"scores_to_ranks","repo":"gicheonkang/DAN-VisDial","repo_kind":"official","path":"utils/eval_utils.py","file_url":"https://github.com/gicheonkang/DAN-VisDial/blob/HEAD/utils/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26ec77dabb4db96d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}