{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LA7DXHTLFMQLWMAVHEORKHVI4S","short_pith_number":"pith:LA7DXHTL","schema_version":"1.0","canonical_sha256":"583e3b9e6b2b20bb3015391d151ea8e490580eb0902946565465f56bafa99505","source":{"kind":"arxiv","id":"1511.03745","version":4},"attestation_state":"computed","paper":{"title":"Grounding of Textual Phrases in Images by Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Bernt Schiele, Marcus Rohrbach, Ronghang Hu, Trevor Darrell","submitted_at":"2015-11-12T01:13:47Z","abstract_excerpt":"Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth spatial localization of phrases, thus it is desirable to learn from data with no or little grounding supervision. We propose a novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly. During training our approach encodes the phrase using a recurrent network language mo"},"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":"1511.03745","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-12T01:13:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"89d608b310badc8459e2f8354da4992566eeb9efc3f3ff257ba3e818066a852c","abstract_canon_sha256":"b15ee3273f439d46316bea97a25bc04176eea46d545d63f74a4296c851efba83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:31.213656Z","signature_b64":"i/vAnSiceDv8VwpDNvMW3Me91us04rQrduKLl9aWLVO5ItJhn0fX3lH/lSbkV0s82i1BKeZFNfvYqb2eErw8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"583e3b9e6b2b20bb3015391d151ea8e490580eb0902946565465f56bafa99505","last_reissued_at":"2026-05-18T00:50:31.212976Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:31.212976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding of Textual Phrases in Images by Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Bernt Schiele, Marcus Rohrbach, Ronghang Hu, Trevor Darrell","submitted_at":"2015-11-12T01:13:47Z","abstract_excerpt":"Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth spatial localization of phrases, thus it is desirable to learn from data with no or little grounding supervision. We propose a novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly. During training our approach encodes the phrase using a recurrent network language mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03745","kind":"arxiv","version":4},"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":"1511.03745","created_at":"2026-05-18T00:50:31.213066+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.03745v4","created_at":"2026-05-18T00:50:31.213066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03745","created_at":"2026-05-18T00:50:31.213066+00:00"},{"alias_kind":"pith_short_12","alias_value":"LA7DXHTLFMQL","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LA7DXHTLFMQLWMAV","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LA7DXHTL","created_at":"2026-05-18T12:29:29.992203+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/LA7DXHTLFMQLWMAVHEORKHVI4S","json":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S.json","graph_json":"https://pith.science/api/pith-number/LA7DXHTLFMQLWMAVHEORKHVI4S/graph.json","events_json":"https://pith.science/api/pith-number/LA7DXHTLFMQLWMAVHEORKHVI4S/events.json","paper":"https://pith.science/paper/LA7DXHTL"},"agent_actions":{"view_html":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S","download_json":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S.json","view_paper":"https://pith.science/paper/LA7DXHTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.03745&json=true","fetch_graph":"https://pith.science/api/pith-number/LA7DXHTLFMQLWMAVHEORKHVI4S/graph.json","fetch_events":"https://pith.science/api/pith-number/LA7DXHTLFMQLWMAVHEORKHVI4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/action/storage_attestation","attest_author":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/action/author_attestation","sign_citation":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/action/citation_signature","submit_replication":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/action/replication_record"}},"created_at":"2026-05-18T00:50:31.213066+00:00","updated_at":"2026-05-18T00:50:31.213066+00:00"}