{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IPRSTJ4SAKGF4QNHJHBONYEESB","short_pith_number":"pith:IPRSTJ4S","schema_version":"1.0","canonical_sha256":"43e329a792028c5e41a749c2e6e084904a9d59cb2dbc82905ae294bf43babb0a","source":{"kind":"arxiv","id":"2110.05204","version":3},"attestation_state":"computed","paper":{"title":"CLIP4Caption ++: Multi-CLIP for Video Caption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dian Li, Fengyun Rao, Mingkang Tang, Zhanyu Wang, Zhaoyang Zeng","submitted_at":"2021-10-11T12:13:22Z","abstract_excerpt":"This report describes our solution to the VALUE Challenge 2021 in the captioning task. Our solution, named CLIP4Caption++, is built on X-Linear/X-Transformer, which is an advanced model with encoder-decoder architecture. We make the following improvements on the proposed CLIP4Caption++: We employ an advanced encoder-decoder model architecture X-Transformer as our main framework and make the following improvements: 1) we utilize three strong pre-trained CLIP models to extract the text-related appearance visual features. 2) we adopt the TSN sampling strategy for data enhancement. 3) we involve t"},"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":"2110.05204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T12:13:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41d7df8f49df621bddfa700686745f9cf43515c466aa4588d52fe09a78d2becd","abstract_canon_sha256":"b624e9d8dd0d044993cc3ab930487b82bcfa859973416b297a0f5685e4d69eab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:37.412887Z","signature_b64":"JVD8UzKRgc/q3HZ/4F6csG1kkBBo3/lCWB/r4ZsNLh98JFufmxhuf97pzOWlI1PVvtGARMEwGIYOJgOK5v4FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43e329a792028c5e41a749c2e6e084904a9d59cb2dbc82905ae294bf43babb0a","last_reissued_at":"2026-07-05T03:22:37.412464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:37.412464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP4Caption ++: Multi-CLIP for Video Caption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dian Li, Fengyun Rao, Mingkang Tang, Zhanyu Wang, Zhaoyang Zeng","submitted_at":"2021-10-11T12:13:22Z","abstract_excerpt":"This report describes our solution to the VALUE Challenge 2021 in the captioning task. Our solution, named CLIP4Caption++, is built on X-Linear/X-Transformer, which is an advanced model with encoder-decoder architecture. We make the following improvements on the proposed CLIP4Caption++: We employ an advanced encoder-decoder model architecture X-Transformer as our main framework and make the following improvements: 1) we utilize three strong pre-trained CLIP models to extract the text-related appearance visual features. 2) we adopt the TSN sampling strategy for data enhancement. 3) we involve t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05204","kind":"arxiv","version":3},"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/2110.05204/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":"2110.05204","created_at":"2026-07-05T03:22:37.412521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05204v3","created_at":"2026-07-05T03:22:37.412521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05204","created_at":"2026-07-05T03:22:37.412521+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPRSTJ4SAKGF","created_at":"2026-07-05T03:22:37.412521+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPRSTJ4SAKGF4QNH","created_at":"2026-07-05T03:22:37.412521+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPRSTJ4S","created_at":"2026-07-05T03:22:37.412521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB","json":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB.json","graph_json":"https://pith.science/api/pith-number/IPRSTJ4SAKGF4QNHJHBONYEESB/graph.json","events_json":"https://pith.science/api/pith-number/IPRSTJ4SAKGF4QNHJHBONYEESB/events.json","paper":"https://pith.science/paper/IPRSTJ4S"},"agent_actions":{"view_html":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB","download_json":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB.json","view_paper":"https://pith.science/paper/IPRSTJ4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05204&json=true","fetch_graph":"https://pith.science/api/pith-number/IPRSTJ4SAKGF4QNHJHBONYEESB/graph.json","fetch_events":"https://pith.science/api/pith-number/IPRSTJ4SAKGF4QNHJHBONYEESB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB/action/storage_attestation","attest_author":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB/action/author_attestation","sign_citation":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB/action/citation_signature","submit_replication":"https://pith.science/pith/IPRSTJ4SAKGF4QNHJHBONYEESB/action/replication_record"}},"created_at":"2026-07-05T03:22:37.412521+00:00","updated_at":"2026-07-05T03:22:37.412521+00:00"}