{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7J6BAUM5P4RJCVD4F34BZDSTXX","short_pith_number":"pith:7J6BAUM5","schema_version":"1.0","canonical_sha256":"fa7c10519d7f2291547c2ef81c8e53bdd367ed3916401a01e3e23d4585f48356","source":{"kind":"arxiv","id":"2212.01638","version":1},"attestation_state":"computed","paper":{"title":"VLG: General Video Recognition with Web Textual Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jintao Lin, Limin Wang, Wayne Wu, Wenhai Wang, Zhaoyang Liu","submitted_at":"2022-12-03T15:46:49Z","abstract_excerpt":"Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the Internet, we focus on the general video recognition (GVR) problem of solving different recognition tasks within a unified framework. The core contribution of this paper is twofold. First, we build a comprehensive video recognition benchmark of Kinetics-GVR, including four sub-task datasets to cover the mentioned settings. To facilitate the research of GVR, "},"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":"2212.01638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-03T15:46:49Z","cross_cats_sorted":[],"title_canon_sha256":"6c542a9302532992c6445f41168d2dbe686a794be00a04da86892127884686d1","abstract_canon_sha256":"f25fa5390dcbb0038f321dc3dd16efe00f4866682d2a66269365c17734eec9eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:14.549746Z","signature_b64":"HjkfOcuay3ByXplmVXJ7pHGxZe+HLHHS0SSHu1UYfpE/5Q6LKkpPUA8cay2UyHnJy0exGKO5gpU9zoUN9G9OBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa7c10519d7f2291547c2ef81c8e53bdd367ed3916401a01e3e23d4585f48356","last_reissued_at":"2026-07-05T05:22:14.549261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:14.549261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLG: General Video Recognition with Web Textual Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jintao Lin, Limin Wang, Wayne Wu, Wenhai Wang, Zhaoyang Liu","submitted_at":"2022-12-03T15:46:49Z","abstract_excerpt":"Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the Internet, we focus on the general video recognition (GVR) problem of solving different recognition tasks within a unified framework. The core contribution of this paper is twofold. First, we build a comprehensive video recognition benchmark of Kinetics-GVR, including four sub-task datasets to cover the mentioned settings. To facilitate the research of GVR, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01638","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/2212.01638/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":"2212.01638","created_at":"2026-07-05T05:22:14.549325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01638v1","created_at":"2026-07-05T05:22:14.549325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01638","created_at":"2026-07-05T05:22:14.549325+00:00"},{"alias_kind":"pith_short_12","alias_value":"7J6BAUM5P4RJ","created_at":"2026-07-05T05:22:14.549325+00:00"},{"alias_kind":"pith_short_16","alias_value":"7J6BAUM5P4RJCVD4","created_at":"2026-07-05T05:22:14.549325+00:00"},{"alias_kind":"pith_short_8","alias_value":"7J6BAUM5","created_at":"2026-07-05T05:22:14.549325+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/7J6BAUM5P4RJCVD4F34BZDSTXX","json":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX.json","graph_json":"https://pith.science/api/pith-number/7J6BAUM5P4RJCVD4F34BZDSTXX/graph.json","events_json":"https://pith.science/api/pith-number/7J6BAUM5P4RJCVD4F34BZDSTXX/events.json","paper":"https://pith.science/paper/7J6BAUM5"},"agent_actions":{"view_html":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX","download_json":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX.json","view_paper":"https://pith.science/paper/7J6BAUM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01638&json=true","fetch_graph":"https://pith.science/api/pith-number/7J6BAUM5P4RJCVD4F34BZDSTXX/graph.json","fetch_events":"https://pith.science/api/pith-number/7J6BAUM5P4RJCVD4F34BZDSTXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX/action/storage_attestation","attest_author":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX/action/author_attestation","sign_citation":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX/action/citation_signature","submit_replication":"https://pith.science/pith/7J6BAUM5P4RJCVD4F34BZDSTXX/action/replication_record"}},"created_at":"2026-07-05T05:22:14.549325+00:00","updated_at":"2026-07-05T05:22:14.549325+00:00"}