{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DEIM4BAJUZWYW6VQDZQQXLZLGA","short_pith_number":"pith:DEIM4BAJ","schema_version":"1.0","canonical_sha256":"1910ce0409a66d8b7ab01e610baf2b3005ab788f253892d749b75be1bd0aed04","source":{"kind":"arxiv","id":"2409.18478","version":2},"attestation_state":"computed","paper":{"title":"Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Min Yang, Qian Dang, Zichen Zhang","submitted_at":"2024-09-27T06:37:47Z","abstract_excerpt":"With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action detection (TAD), temporal action segmentation (TAS), and generic event boundary detection (GEBD). While task-specific video understanding models have exhibited outstanding performance in each task, there remains a dearth of a unified framework capable of simultaneously addressing multiple tasks, which is a promising direction for the next generation of AI. To this end, in this paper, we propose a single unified framework, coined as Temporal2Seq, to fo"},"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":"2409.18478","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-27T06:37:47Z","cross_cats_sorted":[],"title_canon_sha256":"51c335b70ac7dd9a2f8d90c73a340547eb20bd3df31e4f42affaaf89c79f7176","abstract_canon_sha256":"72bdac86cf4b99231e68fa809fcb27d6f526e7697ce6589d9ad43bc5bc5e2b0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:24.780027Z","signature_b64":"fRbyctLY8//cHztUwrGwWdZ42iBkhx2dUewzU5h3Q0NU4yvHFX0iOBr72Mmit1qOC74ClWv7LY/Mx7hn6HkZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1910ce0409a66d8b7ab01e610baf2b3005ab788f253892d749b75be1bd0aed04","last_reissued_at":"2026-06-11T01:10:24.778963Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:24.778963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Min Yang, Qian Dang, Zichen Zhang","submitted_at":"2024-09-27T06:37:47Z","abstract_excerpt":"With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action detection (TAD), temporal action segmentation (TAS), and generic event boundary detection (GEBD). While task-specific video understanding models have exhibited outstanding performance in each task, there remains a dearth of a unified framework capable of simultaneously addressing multiple tasks, which is a promising direction for the next generation of AI. To this end, in this paper, we propose a single unified framework, coined as Temporal2Seq, to fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18478","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/2409.18478/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":"2409.18478","created_at":"2026-06-11T01:10:24.779125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18478v2","created_at":"2026-06-11T01:10:24.779125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18478","created_at":"2026-06-11T01:10:24.779125+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEIM4BAJUZWY","created_at":"2026-06-11T01:10:24.779125+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEIM4BAJUZWYW6VQ","created_at":"2026-06-11T01:10:24.779125+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEIM4BAJ","created_at":"2026-06-11T01:10:24.779125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11391","citing_title":"Temporal Contrastive Learning for Video Temporal Reasoning in Large Vision-Language Models","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA","json":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA.json","graph_json":"https://pith.science/api/pith-number/DEIM4BAJUZWYW6VQDZQQXLZLGA/graph.json","events_json":"https://pith.science/api/pith-number/DEIM4BAJUZWYW6VQDZQQXLZLGA/events.json","paper":"https://pith.science/paper/DEIM4BAJ"},"agent_actions":{"view_html":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA","download_json":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA.json","view_paper":"https://pith.science/paper/DEIM4BAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18478&json=true","fetch_graph":"https://pith.science/api/pith-number/DEIM4BAJUZWYW6VQDZQQXLZLGA/graph.json","fetch_events":"https://pith.science/api/pith-number/DEIM4BAJUZWYW6VQDZQQXLZLGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA/action/storage_attestation","attest_author":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA/action/author_attestation","sign_citation":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA/action/citation_signature","submit_replication":"https://pith.science/pith/DEIM4BAJUZWYW6VQDZQQXLZLGA/action/replication_record"}},"created_at":"2026-06-11T01:10:24.779125+00:00","updated_at":"2026-06-11T01:10:24.779125+00:00"}