{"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/hierarchical-question-image-co-attention-for","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","arxiv_id":"1606.00061","date":"2016-05-31","proceeding":"NeurIPS 2016 12","authors":["Jiasen Lu","Jianwei Yang","Dhruv Batra","Devi Parikh"],"abstract":"A number of recent works have proposed attention models for Visual Question\nAnswering (VQA) that generate spatial maps highlighting image regions relevant\nto answering the question. In this paper, we argue that in addition to modeling\n\"where to look\" or visual attention, it is equally important to model \"what\nwords to listen to\" or question attention. We present a novel co-attention\nmodel for VQA that jointly reasons about image and question attention. In\naddition, our model reasons about the question (and consequently the image via\nthe co-attention mechanism) in a hierarchical fashion via a novel 1-dimensional\nconvolution neural networks (CNN). Our model improves the state-of-the-art on\nthe VQA dataset from 60.3% to 60.5%, and from 61.6% to 63.3% on the COCO-QA\ndataset. By using ResNet, the performance is further improved to 62.1% for VQA\nand 65.4% for COCO-QA.","url_abs":"http://arxiv.org/abs/1606.00061v5","url_pdf":"http://arxiv.org/pdf/1606.00061v5.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":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/jiasenlu/HieCoAttenVQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/Rabahjamal/Visual-Question-Answering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/SkyOL5/VQA-CoAttention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/WillSuen/VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/arya46/VQA_HieCoAtt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/karunraju/VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/miohana/vqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/phisad/keras-hicoatt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"hierarchical-question-image-co-attention-for","repo_url":"https://github.com/ritvikshrivastava/ADL_VQA_Tensorflow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"visual-dialogue","task_name":"Visual Dialog"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-dialog-on-visdial-v09-val","task":"Visual Dialog","dataset":"VisDial v0.9 val","model":"HieCoAtt-QI","rank_in_archive_order":9,"of":18,"metrics":{"MRR":"57.88","Mean Rank":"5.84","R@1":"43.51","R@10":"83.96","R@5":"74.49"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual-1","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 1.0 multiple choice","model":"HQI+ResNet","rank_in_archive_order":7,"of":10,"metrics":{"Percentage correct":"66.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-coco-visual-4","task":"Visual Question Answering (VQA)","dataset":"COCO Visual Question Answering (VQA) real images 1.0 open ended","model":"HQI+ResNet","rank_in_archive_order":6,"of":14,"metrics":{"Percentage correct":"62.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v1-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v1 test-dev","model":"HieCoAtt (ResNet)","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"61.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v1-test-std","task":"Visual Question Answering (VQA)","dataset":"VQA v1 test-std","model":"HieCoAtt (ResNet)","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"62.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.00061","atlas_url":"https://app.syntology.ai/?focus=1606.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.00061"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/karunraju/VQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WillSuen/VQA","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phisad/keras-hicoatt","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiasenlu/HieCoAttenVQA","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ritvikshrivastava/ADL_VQA_Tensorflow2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/miohana/vqa","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SkyOL5/VQA-CoAttention","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arya46/VQA_HieCoAtt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Rabahjamal/Visual-Question-Answering","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"repositories":3}},"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":1,"samples":[{"code_sha256_prefix":"8f94f0e75a42bcfa","entry":"collate_lines","repo":"karunraju/VQA","repo_kind":"listed","path":"coatt/coattention_experiment_runner.py","file_url":"https://github.com/karunraju/VQA/blob/HEAD/coatt/coattention_experiment_runner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f94f0e75a42bcfa"}},{"code_sha256_prefix":"841acde4f63da42b","entry":"build_model","repo":"arya46/VQA_HieCoAtt","repo_kind":"listed","path":"models/arch.py","file_url":"https://github.com/arya46/VQA_HieCoAtt/blob/HEAD/models/arch.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":"841acde4f63da42b"}},{"code_sha256_prefix":"89d2b73b092fedd6","entry":"image_feature_extractor","repo":"arya46/VQA_HieCoAtt","repo_kind":"listed","path":"utils/helper_functions.py","file_url":"https://github.com/arya46/VQA_HieCoAtt/blob/HEAD/utils/helper_functions.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":"89d2b73b092fedd6"}},{"code_sha256_prefix":"ab1d505a48053f78","entry":"image_feature_extractor","repo":"miohana/vqa","repo_kind":"listed","path":"utils/helper_functions.py","file_url":"https://github.com/miohana/vqa/blob/HEAD/utils/helper_functions.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":"ab1d505a48053f78"}},{"code_sha256_prefix":"7d9a7d3d8353ba1a","entry":"predict_answers","repo":"arya46/VQA_HieCoAtt","repo_kind":"listed","path":"utils/helper_functions.py","file_url":"https://github.com/arya46/VQA_HieCoAtt/blob/HEAD/utils/helper_functions.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":"7d9a7d3d8353ba1a"}},{"code_sha256_prefix":"4a692c10164ea21a","entry":"predict_function","repo":"arya46/VQA_HieCoAtt","repo_kind":"listed","path":"utils/load_pickles.py","file_url":"https://github.com/arya46/VQA_HieCoAtt/blob/HEAD/utils/load_pickles.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":"4a692c10164ea21a"}},{"code_sha256_prefix":"fe06a6a886106510","entry":"process_sentence","repo":"arya46/VQA_HieCoAtt","repo_kind":"listed","path":"utils/helper_functions.py","file_url":"https://github.com/arya46/VQA_HieCoAtt/blob/HEAD/utils/helper_functions.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":"fe06a6a886106510"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}