{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:J3Y4WSDK4OPLE7ORYUGLOUPIMB","short_pith_number":"pith:J3Y4WSDK","schema_version":"1.0","canonical_sha256":"4ef1cb486ae39eb27dd1c50cb751e8604049f92f99170626e18be101e0ec714a","source":{"kind":"arxiv","id":"1904.03885","version":1},"attestation_state":"computed","paper":{"title":"Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Larry S. Davis, Peratham Wiriyathammabhum, Vlad I. Morariu","submitted_at":"2019-04-08T08:28:54Z","abstract_excerpt":"This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and"},"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":"1904.03885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-08T08:28:54Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2d42c36034fa986e981a8c0d909fdbf7503579cb09a0d0891669c2abf464f342","abstract_canon_sha256":"3e3b42ffa1de590447cad1fe77aa62aba89271868df027616a5ca706d6fe7470"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:07.831166Z","signature_b64":"UDYkTdVINRoO0Ur/Jl9XC5Km2eD38xucfOnxUeJmmDyekgcawg3jEv1jZOIkebJ30OOYD4qj6z8OsgGe/R+fBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ef1cb486ae39eb27dd1c50cb751e8604049f92f99170626e18be101e0ec714a","last_reissued_at":"2026-05-17T23:49:07.830637Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:07.830637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Larry S. Davis, Peratham Wiriyathammabhum, Vlad I. Morariu","submitted_at":"2019-04-08T08:28:54Z","abstract_excerpt":"This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model linguistic structure. We introduce a new data collection scheme based on grammatical constraints for surface realization to enable us to investigate the problem of grounding spatio-temporal identifying descriptions in videos. We then propose a two-stream modular attention network that learns and grounds spatio-temporal identifying descriptions based on appearance and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03885","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":""},"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":"1904.03885","created_at":"2026-05-17T23:49:07.830719+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03885v1","created_at":"2026-05-17T23:49:07.830719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03885","created_at":"2026-05-17T23:49:07.830719+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3Y4WSDK4OPL","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3Y4WSDK4OPLE7OR","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3Y4WSDK","created_at":"2026-05-18T12:33:18.533446+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/J3Y4WSDK4OPLE7ORYUGLOUPIMB","json":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB.json","graph_json":"https://pith.science/api/pith-number/J3Y4WSDK4OPLE7ORYUGLOUPIMB/graph.json","events_json":"https://pith.science/api/pith-number/J3Y4WSDK4OPLE7ORYUGLOUPIMB/events.json","paper":"https://pith.science/paper/J3Y4WSDK"},"agent_actions":{"view_html":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB","download_json":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB.json","view_paper":"https://pith.science/paper/J3Y4WSDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03885&json=true","fetch_graph":"https://pith.science/api/pith-number/J3Y4WSDK4OPLE7ORYUGLOUPIMB/graph.json","fetch_events":"https://pith.science/api/pith-number/J3Y4WSDK4OPLE7ORYUGLOUPIMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/action/storage_attestation","attest_author":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/action/author_attestation","sign_citation":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/action/citation_signature","submit_replication":"https://pith.science/pith/J3Y4WSDK4OPLE7ORYUGLOUPIMB/action/replication_record"}},"created_at":"2026-05-17T23:49:07.830719+00:00","updated_at":"2026-05-17T23:49:07.830719+00:00"}