{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IJ3KHUHDDUWHWU47QHOR3TUXDO","short_pith_number":"pith:IJ3KHUHD","schema_version":"1.0","canonical_sha256":"4276a3d0e31d2c7b539f81dd1dce971ba543fd81d5623cee93bb9bb6213aa0d2","source":{"kind":"arxiv","id":"1611.00393","version":3},"attestation_state":"computed","paper":{"title":"Combining Multiple Cues for Visual Madlibs Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander C. Berg, Arun Mallya, Bryan Plummer, Svetlana Lazebnik, Tamara L. Berg, Tatiana Tommasi","submitted_at":"2016-11-01T21:09:16Z","abstract_excerpt":"This paper presents an approach for answering fill-in-the-blank multiple choice questions from the Visual Madlibs dataset. Instead of generic and commonly used representations trained on the ImageNet classification task, our approach employs a combination of networks trained for specialized tasks such as scene recognition, person activity classification, and attribute prediction. We also present a method for localizing phrases from candidate answers in order to provide spatial support for feature extraction. We map each of these features, together with candidate answers, to a joint embedding s"},"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":"1611.00393","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-01T21:09:16Z","cross_cats_sorted":[],"title_canon_sha256":"ebb995cc91ff15d25cf754b2e4c07ddfdd573cae56ea7b7ef21a26c8322a02b8","abstract_canon_sha256":"59c589cbee5caf43b33ebed564cd3af89a95a2a0eaa393a3b60446764a6e3bb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:04.582286Z","signature_b64":"Nl7PziUV2LhneEthIVReH7+gmz+BIgtFjCp2e2UHg5kgspGejldSdzH83PiMvHMucMlI3T+sT/cx6PIk1X25Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4276a3d0e31d2c7b539f81dd1dce971ba543fd81d5623cee93bb9bb6213aa0d2","last_reissued_at":"2026-05-18T00:24:04.581831Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:04.581831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining Multiple Cues for Visual Madlibs Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander C. Berg, Arun Mallya, Bryan Plummer, Svetlana Lazebnik, Tamara L. Berg, Tatiana Tommasi","submitted_at":"2016-11-01T21:09:16Z","abstract_excerpt":"This paper presents an approach for answering fill-in-the-blank multiple choice questions from the Visual Madlibs dataset. Instead of generic and commonly used representations trained on the ImageNet classification task, our approach employs a combination of networks trained for specialized tasks such as scene recognition, person activity classification, and attribute prediction. We also present a method for localizing phrases from candidate answers in order to provide spatial support for feature extraction. We map each of these features, together with candidate answers, to a joint embedding s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00393","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1611.00393","created_at":"2026-05-18T00:24:04.581908+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00393v3","created_at":"2026-05-18T00:24:04.581908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00393","created_at":"2026-05-18T00:24:04.581908+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJ3KHUHDDUWH","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJ3KHUHDDUWHWU47","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJ3KHUHD","created_at":"2026-05-18T12:30:22.444734+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/IJ3KHUHDDUWHWU47QHOR3TUXDO","json":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO.json","graph_json":"https://pith.science/api/pith-number/IJ3KHUHDDUWHWU47QHOR3TUXDO/graph.json","events_json":"https://pith.science/api/pith-number/IJ3KHUHDDUWHWU47QHOR3TUXDO/events.json","paper":"https://pith.science/paper/IJ3KHUHD"},"agent_actions":{"view_html":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO","download_json":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO.json","view_paper":"https://pith.science/paper/IJ3KHUHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00393&json=true","fetch_graph":"https://pith.science/api/pith-number/IJ3KHUHDDUWHWU47QHOR3TUXDO/graph.json","fetch_events":"https://pith.science/api/pith-number/IJ3KHUHDDUWHWU47QHOR3TUXDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO/action/storage_attestation","attest_author":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO/action/author_attestation","sign_citation":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO/action/citation_signature","submit_replication":"https://pith.science/pith/IJ3KHUHDDUWHWU47QHOR3TUXDO/action/replication_record"}},"created_at":"2026-05-18T00:24:04.581908+00:00","updated_at":"2026-05-18T00:24:04.581908+00:00"}