{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NK72FEHLHSH4Y6DWH4LFROOFOI","short_pith_number":"pith:NK72FEHL","schema_version":"1.0","canonical_sha256":"6abfa290eb3c8fcc78763f1658b9c57213d60fe18a81056ae07d63adaf84c38e","source":{"kind":"arxiv","id":"2109.06085","version":2},"attestation_state":"computed","paper":{"title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Can Zhang, Long Chen, Meng Cao, Mike Zheng Shou, Yuexian Zou","submitted_at":"2021-09-13T16:01:19Z","abstract_excerpt":"Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment candidates and then conducts segment classification and regression. 2) Bottom-up model: It directly predicts frame-wise probabilities of the referential segment boundaries. However, all these methods are not end-to-end, i.e., they always rely on some time-consuming post-processing steps to refine predictions. To this end, we reformulate video grounding as a set pre"},"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":"2109.06085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T16:01:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7f4c8c9cbcd1d7bc310fdc8727766faee29e8dee37e6fe1d6afa362ea1b20e66","abstract_canon_sha256":"900664fdc511fde69137ebd9c1b9e8dd39538d92e3849ade54c1738e344aa755"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:10.535518Z","signature_b64":"umzuwxtMwSVP08siurZPf+wZb5Ad/BNFSG2B3O966EIhNz4dEZNH9xdF21qWyQu/ucEvUIc89Zzb2mmzQ1IqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6abfa290eb3c8fcc78763f1658b9c57213d60fe18a81056ae07d63adaf84c38e","last_reissued_at":"2026-07-05T04:13:10.535058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:10.535058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Can Zhang, Long Chen, Meng Cao, Mike Zheng Shou, Yuexian Zou","submitted_at":"2021-09-13T16:01:19Z","abstract_excerpt":"Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video. Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment candidates and then conducts segment classification and regression. 2) Bottom-up model: It directly predicts frame-wise probabilities of the referential segment boundaries. However, all these methods are not end-to-end, i.e., they always rely on some time-consuming post-processing steps to refine predictions. To this end, we reformulate video grounding as a set pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06085","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/2109.06085/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":"2109.06085","created_at":"2026-07-05T04:13:10.535107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06085v2","created_at":"2026-07-05T04:13:10.535107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06085","created_at":"2026-07-05T04:13:10.535107+00:00"},{"alias_kind":"pith_short_12","alias_value":"NK72FEHLHSH4","created_at":"2026-07-05T04:13:10.535107+00:00"},{"alias_kind":"pith_short_16","alias_value":"NK72FEHLHSH4Y6DW","created_at":"2026-07-05T04:13:10.535107+00:00"},{"alias_kind":"pith_short_8","alias_value":"NK72FEHL","created_at":"2026-07-05T04:13:10.535107+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/NK72FEHLHSH4Y6DWH4LFROOFOI","json":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI.json","graph_json":"https://pith.science/api/pith-number/NK72FEHLHSH4Y6DWH4LFROOFOI/graph.json","events_json":"https://pith.science/api/pith-number/NK72FEHLHSH4Y6DWH4LFROOFOI/events.json","paper":"https://pith.science/paper/NK72FEHL"},"agent_actions":{"view_html":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI","download_json":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI.json","view_paper":"https://pith.science/paper/NK72FEHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06085&json=true","fetch_graph":"https://pith.science/api/pith-number/NK72FEHLHSH4Y6DWH4LFROOFOI/graph.json","fetch_events":"https://pith.science/api/pith-number/NK72FEHLHSH4Y6DWH4LFROOFOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/action/storage_attestation","attest_author":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/action/author_attestation","sign_citation":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/action/citation_signature","submit_replication":"https://pith.science/pith/NK72FEHLHSH4Y6DWH4LFROOFOI/action/replication_record"}},"created_at":"2026-07-05T04:13:10.535107+00:00","updated_at":"2026-07-05T04:13:10.535107+00:00"}