{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PXQW2WNER4CP6CD7CEWSFWUAM4","short_pith_number":"pith:PXQW2WNE","schema_version":"1.0","canonical_sha256":"7de16d59a48f04ff087f112d22da806738e1118599b4d25c21af143b1a708b66","source":{"kind":"arxiv","id":"2109.11848","version":1},"attestation_state":"computed","paper":{"title":"How to find a good image-text embedding for remote sensing visual question answering?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Kellenberger, Bertrand Le Saux, Christel Chappuis, Devis Tuia, Sylvain Lobry","submitted_at":"2021-09-24T09:48:28Z","abstract_excerpt":"Visual question answering (VQA) has recently been introduced to remote sensing to make information extraction from overhead imagery more accessible to everyone. VQA considers a question (in natural language, therefore easy to formulate) about an image and aims at providing an answer through a model based on computer vision and natural language processing methods. As such, a VQA model needs to jointly consider visual and textual features, which is frequently done through a fusion step. In this work, we study three different fusion methodologies in the context of VQA for remote sensing and analy"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2109.11848","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T09:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"abcc898ed88e59ca344f0da06dfbb6450df2317a2d92724e262f80c2471da65a","abstract_canon_sha256":"6390274fb39831c91e35381a2f2d4275f2c7d92c2df88d6f8c4d26fce59204bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:08.065619Z","signature_b64":"ESS8O5SnDYPXdMZC3SsD2+5eiw1VV4nGR06tvmoOTGpgAe8y4m/Dok3oOX/ifUgBKosCFHdO9Zn2I1EoIhvLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7de16d59a48f04ff087f112d22da806738e1118599b4d25c21af143b1a708b66","last_reissued_at":"2026-07-05T03:17:08.065214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:08.065214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to find a good image-text embedding for remote sensing visual question answering?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Kellenberger, Bertrand Le Saux, Christel Chappuis, Devis Tuia, Sylvain Lobry","submitted_at":"2021-09-24T09:48:28Z","abstract_excerpt":"Visual question answering (VQA) has recently been introduced to remote sensing to make information extraction from overhead imagery more accessible to everyone. VQA considers a question (in natural language, therefore easy to formulate) about an image and aims at providing an answer through a model based on computer vision and natural language processing methods. As such, a VQA model needs to jointly consider visual and textual features, which is frequently done through a fusion step. In this work, we study three different fusion methodologies in the context of VQA for remote sensing and analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11848","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.11848/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2109.11848","created_at":"2026-07-05T03:17:08.065269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.11848v1","created_at":"2026-07-05T03:17:08.065269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11848","created_at":"2026-07-05T03:17:08.065269+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXQW2WNER4CP","created_at":"2026-07-05T03:17:08.065269+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXQW2WNER4CP6CD7","created_at":"2026-07-05T03:17:08.065269+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXQW2WNE","created_at":"2026-07-05T03:17:08.065269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4","json":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4.json","graph_json":"https://pith.science/api/pith-number/PXQW2WNER4CP6CD7CEWSFWUAM4/graph.json","events_json":"https://pith.science/api/pith-number/PXQW2WNER4CP6CD7CEWSFWUAM4/events.json","paper":"https://pith.science/paper/PXQW2WNE"},"agent_actions":{"view_html":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4","download_json":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4.json","view_paper":"https://pith.science/paper/PXQW2WNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.11848&json=true","fetch_graph":"https://pith.science/api/pith-number/PXQW2WNER4CP6CD7CEWSFWUAM4/graph.json","fetch_events":"https://pith.science/api/pith-number/PXQW2WNER4CP6CD7CEWSFWUAM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4/action/storage_attestation","attest_author":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4/action/author_attestation","sign_citation":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4/action/citation_signature","submit_replication":"https://pith.science/pith/PXQW2WNER4CP6CD7CEWSFWUAM4/action/replication_record"}},"created_at":"2026-07-05T03:17:08.065269+00:00","updated_at":"2026-07-05T03:17:08.065269+00:00"}