{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:M4TPK4BL2WIUSLON43TRIY7F2T","short_pith_number":"pith:M4TPK4BL","schema_version":"1.0","canonical_sha256":"6726f5702bd591492dcde6e71463e5d4d82667144a540d4d80da5b6f0d15b228","source":{"kind":"arxiv","id":"1904.02755","version":1},"attestation_state":"computed","paper":{"title":"ExCL: Extractive Clip Localization Using Natural Language Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hauptmann, Anuva Agarwal, Soham Ghosh, Zarana Parekh","submitted_at":"2019-04-04T19:17:04Z","abstract_excerpt":"The task of retrieving clips within videos based on a given natural language query requires cross-modal reasoning over multiple frames. Prior approaches such as sliding window classifiers are inefficient, while text-clip similarity driven ranking-based approaches such as segment proposal networks are far more complicated. In order to select the most relevant video clip corresponding to the given text description, we propose a novel extractive approach that predicts the start and end frames by leveraging cross-modal interactions between the text and video - this removes the need to retrieve 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":"1904.02755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T19:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"bdc501b530023941146bf053381db9ff7d02cfc245615cd90d0b56bc52fe67ea","abstract_canon_sha256":"410374430e2f6890e8c1aa4649290d4fb5515a95155dbb68f1db61d9f43fa1d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:19.774080Z","signature_b64":"GJ3CcqkgSVRN1J1dxYCdtq5GBRzutFt8CCEtRBjdgH+Jy9VtLrVFEohV66woDBzg0uasVunA9+x3xpv3Ngn6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6726f5702bd591492dcde6e71463e5d4d82667144a540d4d80da5b6f0d15b228","last_reissued_at":"2026-05-17T23:49:19.773534Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:19.773534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExCL: Extractive Clip Localization Using Natural Language Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hauptmann, Anuva Agarwal, Soham Ghosh, Zarana Parekh","submitted_at":"2019-04-04T19:17:04Z","abstract_excerpt":"The task of retrieving clips within videos based on a given natural language query requires cross-modal reasoning over multiple frames. Prior approaches such as sliding window classifiers are inefficient, while text-clip similarity driven ranking-based approaches such as segment proposal networks are far more complicated. In order to select the most relevant video clip corresponding to the given text description, we propose a novel extractive approach that predicts the start and end frames by leveraging cross-modal interactions between the text and video - this removes the need to retrieve and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02755","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":"1904.02755","created_at":"2026-05-17T23:49:19.773640+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02755v1","created_at":"2026-05-17T23:49:19.773640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02755","created_at":"2026-05-17T23:49:19.773640+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4TPK4BL2WIU","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4TPK4BL2WIUSLON","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4TPK4BL","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2312.02549","citing_title":"DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08522","citing_title":"UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T","json":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T.json","graph_json":"https://pith.science/api/pith-number/M4TPK4BL2WIUSLON43TRIY7F2T/graph.json","events_json":"https://pith.science/api/pith-number/M4TPK4BL2WIUSLON43TRIY7F2T/events.json","paper":"https://pith.science/paper/M4TPK4BL"},"agent_actions":{"view_html":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T","download_json":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T.json","view_paper":"https://pith.science/paper/M4TPK4BL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02755&json=true","fetch_graph":"https://pith.science/api/pith-number/M4TPK4BL2WIUSLON43TRIY7F2T/graph.json","fetch_events":"https://pith.science/api/pith-number/M4TPK4BL2WIUSLON43TRIY7F2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T/action/storage_attestation","attest_author":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T/action/author_attestation","sign_citation":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T/action/citation_signature","submit_replication":"https://pith.science/pith/M4TPK4BL2WIUSLON43TRIY7F2T/action/replication_record"}},"created_at":"2026-05-17T23:49:19.773640+00:00","updated_at":"2026-05-17T23:49:19.773640+00:00"}