{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZDAA744TAPZHKPOKB4LJO3SAHP","short_pith_number":"pith:ZDAA744T","schema_version":"1.0","canonical_sha256":"c8c00ff39303f2753dca0f16976e403bc81d20c93dc3b291d6206f593c35813b","source":{"kind":"arxiv","id":"2102.00831","version":2},"attestation_state":"computed","paper":{"title":"Semantic Grouping Network for Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Haeyong Kang, Hobin Ryu, Sunghun Kang","submitted_at":"2021-02-01T13:40:56Z","abstract_excerpt":"This paper considers a video caption generating network referred to as Semantic Grouping Network (SGN) that attempts (1) to group video frames with discriminating word phrases of partially decoded caption and then (2) to decode those semantically aligned groups in predicting the next word. As consecutive frames are not likely to provide unique information, prior methods have focused on discarding or merging repetitive information based only on the input video. The SGN learns an algorithm to capture the most discriminating word phrases of the partially decoded caption and a mapping that associa"},"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":"2102.00831","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-01T13:40:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd2aea18f2ccbbe51dfe383d65d74348408aee808187b00c0838f3f170cadc9e","abstract_canon_sha256":"5fbcd7a1cbe86f26523dba2d24cc24aa0e03cadc0a62cd83927df50e79c32e30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:32.291950Z","signature_b64":"LOocb+GDf4zNsfWx4lWiVi+P2mc+nKG9BqFSjUxDBn4WuykIuebOBIpUJopMIXkLYaaemDUqhcdQZVnI4Rc8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c00ff39303f2753dca0f16976e403bc81d20c93dc3b291d6206f593c35813b","last_reissued_at":"2026-07-05T02:12:32.291598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:32.291598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Grouping Network for Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chang D. Yoo, Haeyong Kang, Hobin Ryu, Sunghun Kang","submitted_at":"2021-02-01T13:40:56Z","abstract_excerpt":"This paper considers a video caption generating network referred to as Semantic Grouping Network (SGN) that attempts (1) to group video frames with discriminating word phrases of partially decoded caption and then (2) to decode those semantically aligned groups in predicting the next word. As consecutive frames are not likely to provide unique information, prior methods have focused on discarding or merging repetitive information based only on the input video. The SGN learns an algorithm to capture the most discriminating word phrases of the partially decoded caption and a mapping that associa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00831","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/2102.00831/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":"2102.00831","created_at":"2026-07-05T02:12:32.291655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.00831v2","created_at":"2026-07-05T02:12:32.291655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00831","created_at":"2026-07-05T02:12:32.291655+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDAA744TAPZH","created_at":"2026-07-05T02:12:32.291655+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDAA744TAPZHKPOK","created_at":"2026-07-05T02:12:32.291655+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDAA744T","created_at":"2026-07-05T02:12:32.291655+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/ZDAA744TAPZHKPOKB4LJO3SAHP","json":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP.json","graph_json":"https://pith.science/api/pith-number/ZDAA744TAPZHKPOKB4LJO3SAHP/graph.json","events_json":"https://pith.science/api/pith-number/ZDAA744TAPZHKPOKB4LJO3SAHP/events.json","paper":"https://pith.science/paper/ZDAA744T"},"agent_actions":{"view_html":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP","download_json":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP.json","view_paper":"https://pith.science/paper/ZDAA744T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.00831&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDAA744TAPZHKPOKB4LJO3SAHP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDAA744TAPZHKPOKB4LJO3SAHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP/action/storage_attestation","attest_author":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP/action/author_attestation","sign_citation":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP/action/citation_signature","submit_replication":"https://pith.science/pith/ZDAA744TAPZHKPOKB4LJO3SAHP/action/replication_record"}},"created_at":"2026-07-05T02:12:32.291655+00:00","updated_at":"2026-07-05T02:12:32.291655+00:00"}