{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JBXQCPCPQGAR5WUOQNLHU42XYL","short_pith_number":"pith:JBXQCPCP","schema_version":"1.0","canonical_sha256":"486f013c4f81811eda8e83567a7357c2d1b5776789cda3940936506b4fdd9524","source":{"kind":"arxiv","id":"1903.11649","version":2},"attestation_state":"computed","paper":{"title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajay Divakaran, Anirban Roy, Devi Parikh, Karan Sikka, Karuna Ahuja, Samyak Datta","submitted_at":"2019-03-27T18:55:32Z","abstract_excerpt":"We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a `downstream' task to guide the process of phrase localization. Our method, as a first step, infers the latent correspondences between regions-of-interest (RoIs) and phrases in the caption and creates a discriminative image representation using these matched RoIs. In a subsequent step, this (learned) representation is aligned with the caption. Our key contribution lies in building this `caption-conditioned"},"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":"1903.11649","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T18:55:32Z","cross_cats_sorted":[],"title_canon_sha256":"be923f2e2ff6bec03dacd16e3b9fd57c7e89081cce76bf8bdaa45587854b22ca","abstract_canon_sha256":"0d0690829ad802be0653046fcf58cc50c394e2f73cd1cf3c5c5ee7fb3edc34d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:57.776023Z","signature_b64":"w6aLUqPH/GmxkDiZP6m4ltG31tq2A1xC9r5UlHZRwInUlxNFXAUOp06FSO61ea+Gq/yjk7ujM/vYMdjAnr32BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"486f013c4f81811eda8e83567a7357c2d1b5776789cda3940936506b4fdd9524","last_reissued_at":"2026-07-05T00:11:57.775532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:57.775532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajay Divakaran, Anirban Roy, Devi Parikh, Karan Sikka, Karuna Ahuja, Samyak Datta","submitted_at":"2019-03-27T18:55:32Z","abstract_excerpt":"We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a `downstream' task to guide the process of phrase localization. Our method, as a first step, infers the latent correspondences between regions-of-interest (RoIs) and phrases in the caption and creates a discriminative image representation using these matched RoIs. In a subsequent step, this (learned) representation is aligned with the caption. Our key contribution lies in building this `caption-conditioned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11649","kind":"arxiv","version":2},"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/1903.11649/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":"1903.11649","created_at":"2026-07-05T00:11:57.775586+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.11649v2","created_at":"2026-07-05T00:11:57.775586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11649","created_at":"2026-07-05T00:11:57.775586+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBXQCPCPQGAR","created_at":"2026-07-05T00:11:57.775586+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBXQCPCPQGAR5WUO","created_at":"2026-07-05T00:11:57.775586+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBXQCPCP","created_at":"2026-07-05T00:11:57.775586+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/JBXQCPCPQGAR5WUOQNLHU42XYL","json":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL.json","graph_json":"https://pith.science/api/pith-number/JBXQCPCPQGAR5WUOQNLHU42XYL/graph.json","events_json":"https://pith.science/api/pith-number/JBXQCPCPQGAR5WUOQNLHU42XYL/events.json","paper":"https://pith.science/paper/JBXQCPCP"},"agent_actions":{"view_html":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL","download_json":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL.json","view_paper":"https://pith.science/paper/JBXQCPCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.11649&json=true","fetch_graph":"https://pith.science/api/pith-number/JBXQCPCPQGAR5WUOQNLHU42XYL/graph.json","fetch_events":"https://pith.science/api/pith-number/JBXQCPCPQGAR5WUOQNLHU42XYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL/action/storage_attestation","attest_author":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL/action/author_attestation","sign_citation":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL/action/citation_signature","submit_replication":"https://pith.science/pith/JBXQCPCPQGAR5WUOQNLHU42XYL/action/replication_record"}},"created_at":"2026-07-05T00:11:57.775586+00:00","updated_at":"2026-07-05T00:11:57.775586+00:00"}