{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3SFH55APIN3G4U2M4QOSNP4YX7","short_pith_number":"pith:3SFH55AP","schema_version":"1.0","canonical_sha256":"dc8a7ef40f43766e534ce41d26bf98bfc9918648c79a8e9b164c470b87015777","source":{"kind":"arxiv","id":"1908.03846","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Temporal Relationships in Video Moment Localization with Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.MM","authors_text":"Jiebo Luo, Jinsong Su, Songyang Zhang","submitted_at":"2019-08-11T03:59:18Z","abstract_excerpt":"We address the problem of video moment localization with natural language, i.e. localizing a video segment described by a natural language sentence. While most prior work focuses on grounding the query as a whole, temporal dependencies and reasoning between events within the text are not fully considered. In this paper, we propose a novel Temporal Compositional Modular Network (TCMN) where a tree attention network first automatically decomposes a sentence into three descriptions with respect to the main event, context event and temporal signal. Two modules are then utilized to measure the visu"},"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":"1908.03846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-08-11T03:59:18Z","cross_cats_sorted":["cs.CV","cs.IR"],"title_canon_sha256":"2a8e294c0f4e3d3e5ad0d493c8bc45a7710dd3c5ee544aac3df8e073ba241d32","abstract_canon_sha256":"77329d38a6e6e7c84e00bf2913546a85e7c3ad3302c2bce3368e8bea826d8fed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:18.784254Z","signature_b64":"aepCXQ69FXQIkV48SnQkzXFZLXCuenm7/rZvG55CrImokxjaa86x7xBElQl4yJkHpPnNaxeSs4xUyclPw3njBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc8a7ef40f43766e534ce41d26bf98bfc9918648c79a8e9b164c470b87015777","last_reissued_at":"2026-07-04T23:53:18.783861Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:18.783861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Temporal Relationships in Video Moment Localization with Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR"],"primary_cat":"cs.MM","authors_text":"Jiebo Luo, Jinsong Su, Songyang Zhang","submitted_at":"2019-08-11T03:59:18Z","abstract_excerpt":"We address the problem of video moment localization with natural language, i.e. localizing a video segment described by a natural language sentence. While most prior work focuses on grounding the query as a whole, temporal dependencies and reasoning between events within the text are not fully considered. In this paper, we propose a novel Temporal Compositional Modular Network (TCMN) where a tree attention network first automatically decomposes a sentence into three descriptions with respect to the main event, context event and temporal signal. Two modules are then utilized to measure the visu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03846","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/1908.03846/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":"1908.03846","created_at":"2026-07-04T23:53:18.783916+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03846v1","created_at":"2026-07-04T23:53:18.783916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03846","created_at":"2026-07-04T23:53:18.783916+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SFH55APIN3G","created_at":"2026-07-04T23:53:18.783916+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SFH55APIN3G4U2M","created_at":"2026-07-04T23:53:18.783916+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SFH55AP","created_at":"2026-07-04T23:53:18.783916+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/3SFH55APIN3G4U2M4QOSNP4YX7","json":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7.json","graph_json":"https://pith.science/api/pith-number/3SFH55APIN3G4U2M4QOSNP4YX7/graph.json","events_json":"https://pith.science/api/pith-number/3SFH55APIN3G4U2M4QOSNP4YX7/events.json","paper":"https://pith.science/paper/3SFH55AP"},"agent_actions":{"view_html":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7","download_json":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7.json","view_paper":"https://pith.science/paper/3SFH55AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03846&json=true","fetch_graph":"https://pith.science/api/pith-number/3SFH55APIN3G4U2M4QOSNP4YX7/graph.json","fetch_events":"https://pith.science/api/pith-number/3SFH55APIN3G4U2M4QOSNP4YX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7/action/storage_attestation","attest_author":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7/action/author_attestation","sign_citation":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7/action/citation_signature","submit_replication":"https://pith.science/pith/3SFH55APIN3G4U2M4QOSNP4YX7/action/replication_record"}},"created_at":"2026-07-04T23:53:18.783916+00:00","updated_at":"2026-07-04T23:53:18.783916+00:00"}