{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DIJL72J34BEET6OPLHDYVBMNCJ","short_pith_number":"pith:DIJL72J3","schema_version":"1.0","canonical_sha256":"1a12bfe93be04849f9cf59c78a858d1250c2048b698ecd3a7e0a02edec8684bf","source":{"kind":"arxiv","id":"1909.02097","version":1},"attestation_state":"computed","paper":{"title":"Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Pang, Piyush Sharma, Radu Soricut, Soravit Changpinyo","submitted_at":"2019-09-04T20:37:30Z","abstract_excerpt":"Object detection plays an important role in current solutions to vision and language tasks like image captioning and visual question answering. However, popular models like Faster R-CNN rely on a costly process of annotating ground-truths for both the bounding boxes and their corresponding semantic labels, making it less amenable as a primitive task for transfer learning. In this paper, we examine the effect of decoupling box proposal and featurization for down-stream tasks. The key insight is that this allows us to leverage a large amount of labeled annotations that were previously unavailabl"},"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":"1909.02097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T20:37:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c7445efb75dc285dc7d2b7c4a09496d757244a8e5ba66514ebdcc192336c2451","abstract_canon_sha256":"6cc8a475dc0922d125b7620be7af2437690c7679ded94faa4e869439e47ccc68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:30.320499Z","signature_b64":"YvPM9PvLeV18vs5DjASIi0lnu/BlYFMlp7EK9wXeixIWccUDCrHFFq1vg29QGRs95qDVhsclWTWGBr65f/7FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a12bfe93be04849f9cf59c78a858d1250c2048b698ecd3a7e0a02edec8684bf","last_reissued_at":"2026-07-05T00:02:30.320090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:30.320090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Pang, Piyush Sharma, Radu Soricut, Soravit Changpinyo","submitted_at":"2019-09-04T20:37:30Z","abstract_excerpt":"Object detection plays an important role in current solutions to vision and language tasks like image captioning and visual question answering. However, popular models like Faster R-CNN rely on a costly process of annotating ground-truths for both the bounding boxes and their corresponding semantic labels, making it less amenable as a primitive task for transfer learning. In this paper, we examine the effect of decoupling box proposal and featurization for down-stream tasks. The key insight is that this allows us to leverage a large amount of labeled annotations that were previously unavailabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02097","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/1909.02097/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":"1909.02097","created_at":"2026-07-05T00:02:30.320142+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02097v1","created_at":"2026-07-05T00:02:30.320142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02097","created_at":"2026-07-05T00:02:30.320142+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIJL72J34BEE","created_at":"2026-07-05T00:02:30.320142+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIJL72J34BEET6OP","created_at":"2026-07-05T00:02:30.320142+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIJL72J3","created_at":"2026-07-05T00:02:30.320142+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/DIJL72J34BEET6OPLHDYVBMNCJ","json":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ.json","graph_json":"https://pith.science/api/pith-number/DIJL72J34BEET6OPLHDYVBMNCJ/graph.json","events_json":"https://pith.science/api/pith-number/DIJL72J34BEET6OPLHDYVBMNCJ/events.json","paper":"https://pith.science/paper/DIJL72J3"},"agent_actions":{"view_html":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ","download_json":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ.json","view_paper":"https://pith.science/paper/DIJL72J3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02097&json=true","fetch_graph":"https://pith.science/api/pith-number/DIJL72J34BEET6OPLHDYVBMNCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DIJL72J34BEET6OPLHDYVBMNCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ/action/storage_attestation","attest_author":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ/action/author_attestation","sign_citation":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ/action/citation_signature","submit_replication":"https://pith.science/pith/DIJL72J34BEET6OPLHDYVBMNCJ/action/replication_record"}},"created_at":"2026-07-05T00:02:30.320142+00:00","updated_at":"2026-07-05T00:02:30.320142+00:00"}