{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2MOB6EC6P74DKPAWX6WCG2OV6X","short_pith_number":"pith:2MOB6EC6","schema_version":"1.0","canonical_sha256":"d31c1f105e7ff8353c16bfac2369d5f5dfbbb03ff72864147121df16e46b2ee7","source":{"kind":"arxiv","id":"2311.17241","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Chen-Lin Zhang, Chen Zhao, Shuming Liu","submitted_at":"2023-11-28T21:31:04Z","abstract_excerpt":"Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited scales and limited data volumes can afford end-to-end training, which inevitably restricts TAD performance. In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1,536 frames, leading to significant detection performance. The key to our approach lies in our proposed temporal-informative adapter (TIA), which is a nov"},"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":"2311.17241","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T21:31:04Z","cross_cats_sorted":[],"title_canon_sha256":"1eb30af38b2dcbaecd89acab103cedc4d6677d49b9844dd49b369e3effd52a49","abstract_canon_sha256":"f96718bed33580b60af6a00c8055021be770cea703a060a8843ef8d73ec2411f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:20.160289Z","signature_b64":"qDFQPMaMxR0eMmL0iR85zaWxuTMdpCd1lHmU2a9QRZTAIqd48nj7TFYd6c5tgN5smKK6jmotn+BXmNpVm40AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d31c1f105e7ff8353c16bfac2369d5f5dfbbb03ff72864147121df16e46b2ee7","last_reissued_at":"2026-07-05T08:10:20.159839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:20.159839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernard Ghanem, Chen-Lin Zhang, Chen Zhao, Shuming Liu","submitted_at":"2023-11-28T21:31:04Z","abstract_excerpt":"Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited scales and limited data volumes can afford end-to-end training, which inevitably restricts TAD performance. In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1,536 frames, leading to significant detection performance. The key to our approach lies in our proposed temporal-informative adapter (TIA), which is a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17241","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/2311.17241/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":"2311.17241","created_at":"2026-07-05T08:10:20.159897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17241v2","created_at":"2026-07-05T08:10:20.159897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17241","created_at":"2026-07-05T08:10:20.159897+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MOB6EC6P74D","created_at":"2026-07-05T08:10:20.159897+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MOB6EC6P74DKPAW","created_at":"2026-07-05T08:10:20.159897+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MOB6EC6","created_at":"2026-07-05T08:10:20.159897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09164","citing_title":"Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X","json":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X.json","graph_json":"https://pith.science/api/pith-number/2MOB6EC6P74DKPAWX6WCG2OV6X/graph.json","events_json":"https://pith.science/api/pith-number/2MOB6EC6P74DKPAWX6WCG2OV6X/events.json","paper":"https://pith.science/paper/2MOB6EC6"},"agent_actions":{"view_html":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X","download_json":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X.json","view_paper":"https://pith.science/paper/2MOB6EC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17241&json=true","fetch_graph":"https://pith.science/api/pith-number/2MOB6EC6P74DKPAWX6WCG2OV6X/graph.json","fetch_events":"https://pith.science/api/pith-number/2MOB6EC6P74DKPAWX6WCG2OV6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X/action/storage_attestation","attest_author":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X/action/author_attestation","sign_citation":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X/action/citation_signature","submit_replication":"https://pith.science/pith/2MOB6EC6P74DKPAWX6WCG2OV6X/action/replication_record"}},"created_at":"2026-07-05T08:10:20.159897+00:00","updated_at":"2026-07-05T08:10:20.159897+00:00"}