{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3DQRZTB3TTONAWMF76QHC6IPYS","short_pith_number":"pith:3DQRZTB3","schema_version":"1.0","canonical_sha256":"d8e11ccc3b9cdcd05985ffa071790fc4880046c3fc37c27b04b1d8602a496d27","source":{"kind":"arxiv","id":"2311.17118","version":2},"attestation_state":"computed","paper":{"title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanjun Li, Jiaming Zhou, Junwei Liang, Kun-Yu Lin","submitted_at":"2023-11-28T12:30:47Z","abstract_excerpt":"Developing end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding. Due to the unaffordable cost of end-to-end training on the whole long videos, existing works generally train models on short clips trimmed from long videos. However, this ``trimming-then-training'' practice requires action interval annotations for clip-level supervision, i.e., knowing which actions are trimmed into the clips. Unfortunately, collecting such annotations is very expensive and prevents model training at scale. To this end, this work aims to build a weakly "},"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":"2311.17118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T12:30:47Z","cross_cats_sorted":[],"title_canon_sha256":"98c96bd562a9eb3e4c6990bed96d1cd649e52f41d953455d85db2004e8396692","abstract_canon_sha256":"9b7d2f0b100fe0e6296d9d0c0133bc652075f1611a3bba6bd1b6619906a8bbba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:35.103613Z","signature_b64":"fCz245bn832s/+xnqGm148LJYoM/CGlfGQVHaDcAjkjly/oqi8Wi2f6yvJenmz+NSQg2mP6ByXo+F+rSVRUYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8e11ccc3b9cdcd05985ffa071790fc4880046c3fc37c27b04b1d8602a496d27","last_reissued_at":"2026-07-05T08:22:35.103121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:35.103121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanjun Li, Jiaming Zhou, Junwei Liang, Kun-Yu Lin","submitted_at":"2023-11-28T12:30:47Z","abstract_excerpt":"Developing end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding. Due to the unaffordable cost of end-to-end training on the whole long videos, existing works generally train models on short clips trimmed from long videos. However, this ``trimming-then-training'' practice requires action interval annotations for clip-level supervision, i.e., knowing which actions are trimmed into the clips. Unfortunately, collecting such annotations is very expensive and prevents model training at scale. To this end, this work aims to build a weakly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17118","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/2311.17118/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":"2311.17118","created_at":"2026-07-05T08:22:35.103182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17118v2","created_at":"2026-07-05T08:22:35.103182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17118","created_at":"2026-07-05T08:22:35.103182+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DQRZTB3TTON","created_at":"2026-07-05T08:22:35.103182+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DQRZTB3TTONAWMF","created_at":"2026-07-05T08:22:35.103182+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DQRZTB3","created_at":"2026-07-05T08:22:35.103182+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/3DQRZTB3TTONAWMF76QHC6IPYS","json":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS.json","graph_json":"https://pith.science/api/pith-number/3DQRZTB3TTONAWMF76QHC6IPYS/graph.json","events_json":"https://pith.science/api/pith-number/3DQRZTB3TTONAWMF76QHC6IPYS/events.json","paper":"https://pith.science/paper/3DQRZTB3"},"agent_actions":{"view_html":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS","download_json":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS.json","view_paper":"https://pith.science/paper/3DQRZTB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17118&json=true","fetch_graph":"https://pith.science/api/pith-number/3DQRZTB3TTONAWMF76QHC6IPYS/graph.json","fetch_events":"https://pith.science/api/pith-number/3DQRZTB3TTONAWMF76QHC6IPYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS/action/storage_attestation","attest_author":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS/action/author_attestation","sign_citation":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS/action/citation_signature","submit_replication":"https://pith.science/pith/3DQRZTB3TTONAWMF76QHC6IPYS/action/replication_record"}},"created_at":"2026-07-05T08:22:35.103182+00:00","updated_at":"2026-07-05T08:22:35.103182+00:00"}