{"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/earthvqa-towards-queryable-earth-via","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","arxiv_id":"2312.12222","date":"2023-12-19","proceeding":null,"authors":["Junjue Wang","Zhuo Zheng","Zihang Chen","Ailong Ma","Yanfei Zhong"],"abstract":"Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoning. Based on city planning needs, we develop a multi-modal multi-task VQA dataset (EarthVQA) to advance relational reasoning-based judging, counting, and comprehensive analysis. The EarthVQA dataset contains 6000 images, corresponding semantic masks, and 208,593 QA pairs with urban and rural governance requirements embedded. As objects are the basis for complex relational reasoning, we propose a Semantic OBject Awareness framework (SOBA) to advance VQA in an object-centric way. To preserve refined spatial locations and semantics, SOBA leverages a segmentation network for object semantics generation. The object-guided attention aggregates object interior features via pseudo masks, and bidirectional cross-attention further models object external relations hierarchically. To optimize object counting, we propose a numerical difference loss that dynamically adds difference penalties, unifying the classification and regression tasks. Experimental results show that SOBA outperforms both advanced general and remote sensing methods. We believe this dataset and framework provide a strong benchmark for Earth vision's complex analysis. The project page is at https://Junjue-Wang.github.io/homepage/EarthVQA.","url_abs":"https://arxiv.org/abs/2312.12222v1","url_pdf":"https://arxiv.org/pdf/2312.12222v1.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":"earthvqa-towards-queryable-earth-via","repo_url":"https://github.com/Junjue-Wang/EarthVQA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"},{"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":[{"slug":"earthvqa","name":"EarthVQA","full_name":"A multi-modal multi-task VQA dataset for remote sensing"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-earthvqa","task":"Visual Question Answering","dataset":"EarthVQA","model":"SOBA","rank_in_archive_order":1,"of":1,"metrics":{"Overall Accuracy":"78.14"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.12222","atlas_url":"https://app.syntology.ai/?focus=2312.12222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12222"}},"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/Junjue-Wang/EarthVQA","reach":{"status":"ok"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"6ec207a34e2ddbe3","entry":"conv_with_kaiming_uniform","repo":"Junjue-Wang/EarthVQA","repo_kind":"official","path":"module/seg_base.py","file_url":"https://github.com/Junjue-Wang/EarthVQA/blob/HEAD/module/seg_base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ec207a34e2ddbe3"}},{"code_sha256_prefix":"4133a26ae05f4dd9","entry":"cross_entropy_loss","repo":"Junjue-Wang/EarthVQA","repo_kind":"official","path":"module/loss.py","file_url":"https://github.com/Junjue-Wang/EarthVQA/blob/HEAD/module/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4133a26ae05f4dd9"}},{"code_sha256_prefix":"f9f989173c2cfffe","entry":"ohem_cross_entropy","repo":"Junjue-Wang/EarthVQA","repo_kind":"official","path":"module/loss.py","file_url":"https://github.com/Junjue-Wang/EarthVQA/blob/HEAD/module/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9f989173c2cfffe"}},{"code_sha256_prefix":"8b71e70e06f0cfbd","entry":"positionalencoding1d","repo":"Junjue-Wang/EarthVQA","repo_kind":"official","path":"module/position_emb.py","file_url":"https://github.com/Junjue-Wang/EarthVQA/blob/HEAD/module/position_emb.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8b71e70e06f0cfbd"}},{"code_sha256_prefix":"37d52453adf46f82","entry":"positionalencoding2d","repo":"Junjue-Wang/EarthVQA","repo_kind":"official","path":"module/position_emb.py","file_url":"https://github.com/Junjue-Wang/EarthVQA/blob/HEAD/module/position_emb.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37d52453adf46f82"}},{"code_sha256_prefix":"c3ab88bb5ff98da6","entry":"som","repo":"Junjue-Wang/EarthVQA","repo_kind":"official","path":"module/loss.py","file_url":"https://github.com/Junjue-Wang/EarthVQA/blob/HEAD/module/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3ab88bb5ff98da6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}