{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S3L46GGMZT7GNASQOTBG2QWYQN","short_pith_number":"pith:S3L46GGM","schema_version":"1.0","canonical_sha256":"96d7cf18ccccfe66825074c26d42d8837888e7d7b71820530ba956dff62756df","source":{"kind":"arxiv","id":"2312.15720","version":1},"attestation_state":"computed","paper":{"title":"Set Prediction Guided by Semantic Concepts for Diverse Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chunfeng Yuan, Peng Li, Weiming Hu, Yan Wang, Yifan Lu, Ziqi Zhang","submitted_at":"2023-12-25T13:13:04Z","abstract_excerpt":"Diverse video captioning aims to generate a set of sentences to describe the given video in various aspects. Mainstream methods are trained with independent pairs of a video and a caption from its ground-truth set without exploiting the intra-set relationship, resulting in low diversity of generated captions. Different from them, we formulate diverse captioning into a semantic-concept-guided set prediction (SCG-SP) problem by fitting the predicted caption set to the ground-truth set, where the set-level relationship is fully captured. Specifically, our set prediction consists of two synergisti"},"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":"2312.15720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-25T13:13:04Z","cross_cats_sorted":[],"title_canon_sha256":"a6980ab0cb6c03b8ec4ead366180e7aa41c69a289daf7a28e132444fc422ed54","abstract_canon_sha256":"2366e552f67ed3c8c4ebb5064e1ae3a65c61638e924c784a52343aaab5562c9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:47.918080Z","signature_b64":"N4Bia7LX9pviazCfZm+3YVeqfDuh9Neh5KxhYeUHQ5e9td9QhUl2X/q5nB25tiI9H8buMEfilk7222aXUQAfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96d7cf18ccccfe66825074c26d42d8837888e7d7b71820530ba956dff62756df","last_reissued_at":"2026-07-05T07:28:47.917592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:47.917592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Set Prediction Guided by Semantic Concepts for Diverse Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chunfeng Yuan, Peng Li, Weiming Hu, Yan Wang, Yifan Lu, Ziqi Zhang","submitted_at":"2023-12-25T13:13:04Z","abstract_excerpt":"Diverse video captioning aims to generate a set of sentences to describe the given video in various aspects. Mainstream methods are trained with independent pairs of a video and a caption from its ground-truth set without exploiting the intra-set relationship, resulting in low diversity of generated captions. Different from them, we formulate diverse captioning into a semantic-concept-guided set prediction (SCG-SP) problem by fitting the predicted caption set to the ground-truth set, where the set-level relationship is fully captured. Specifically, our set prediction consists of two synergisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15720","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/2312.15720/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":"2312.15720","created_at":"2026-07-05T07:28:47.917659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15720v1","created_at":"2026-07-05T07:28:47.917659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15720","created_at":"2026-07-05T07:28:47.917659+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3L46GGMZT7G","created_at":"2026-07-05T07:28:47.917659+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3L46GGMZT7GNASQ","created_at":"2026-07-05T07:28:47.917659+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3L46GGM","created_at":"2026-07-05T07:28:47.917659+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/S3L46GGMZT7GNASQOTBG2QWYQN","json":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN.json","graph_json":"https://pith.science/api/pith-number/S3L46GGMZT7GNASQOTBG2QWYQN/graph.json","events_json":"https://pith.science/api/pith-number/S3L46GGMZT7GNASQOTBG2QWYQN/events.json","paper":"https://pith.science/paper/S3L46GGM"},"agent_actions":{"view_html":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN","download_json":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN.json","view_paper":"https://pith.science/paper/S3L46GGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15720&json=true","fetch_graph":"https://pith.science/api/pith-number/S3L46GGMZT7GNASQOTBG2QWYQN/graph.json","fetch_events":"https://pith.science/api/pith-number/S3L46GGMZT7GNASQOTBG2QWYQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN/action/storage_attestation","attest_author":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN/action/author_attestation","sign_citation":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN/action/citation_signature","submit_replication":"https://pith.science/pith/S3L46GGMZT7GNASQOTBG2QWYQN/action/replication_record"}},"created_at":"2026-07-05T07:28:47.917659+00:00","updated_at":"2026-07-05T07:28:47.917659+00:00"}