{"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/exploring-models-and-data-for-image-question","title":"Exploring Models and Data for Image Question Answering","arxiv_id":"1505.02074","date":"2015-05-08","proceeding":"NeurIPS 2015 12","authors":["Mengye Ren","Ryan Kiros","Richard Zemel"],"abstract":"This work aims to address the problem of image-based question-answering (QA)\nwith new models and datasets. In our work, we propose to use neural networks\nand visual semantic embeddings, without intermediate stages such as object\ndetection and image segmentation, to predict answers to simple questions about\nimages. Our model performs 1.8 times better than the only published results on\nan existing image QA dataset. We also present a question generation algorithm\nthat converts image descriptions, which are widely available, into QA form. We\nused this algorithm to produce an order-of-magnitude larger dataset, with more\nevenly distributed answers. A suite of baseline results on this new dataset are\nalso presented.","url_abs":"http://arxiv.org/abs/1505.02074v4","url_pdf":"http://arxiv.org/pdf/1505.02074v4.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":"exploring-models-and-data-for-image-question","repo_url":"https://github.com/renmengye/imageqa-public","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploring-models-and-data-for-image-question","repo_url":"https://github.com/abhigoyal1997/CS-763-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploring-models-and-data-for-image-question","repo_url":"https://github.com/moh833/VQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"question-generation","task_name":"Question Generation"},{"task_slug":"question-generation","task_name":"Question-Generation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"coco-qa","name":"COCO-QA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-sutd-trafficqa","task":"Video Question Answering","dataset":"SUTD-TrafficQA","model":"VIS+LST","rank_in_archive_order":6,"of":6,"metrics":{"1/2":"54.25","1/4":"29.91"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.02074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.02074"}},"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/moh833/VQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abhigoyal1997/CS-763-Project","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/renmengye/imageqa-public","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"f3406c3db2da10b5","entry":"preprocess","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f3406c3db2da10b5"}},{"code_sha256_prefix":"1877d63c9e9a8d2e","entry":"sort_batch","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1877d63c9e9a8d2e"}},{"code_sha256_prefix":"aa7a1a62f175dab8","entry":"parseInputFile","repo":"renmengye/imageqa-public","repo_kind":"official","path":"src/imageqa_adhoc.py","file_url":"https://github.com/renmengye/imageqa-public/blob/HEAD/src/imageqa_adhoc.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":"aa7a1a62f175dab8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}