{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SUEJCXKLZ355O66DTNIPLMIYTP","short_pith_number":"pith:SUEJCXKL","schema_version":"1.0","canonical_sha256":"9508915d4bcefbd77bc39b50f5b1189bc9b24457af79651d5fd4e13964a64a0b","source":{"kind":"arxiv","id":"2411.15106","version":2},"attestation_state":"computed","paper":{"title":"About Time: Advances, Challenges, and Outlooks of Action Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Ronald Poppe","submitted_at":"2024-11-22T18:09:27Z","abstract_excerpt":"We have witnessed impressive advances in video action understanding. Increased dataset sizes, variability, and computation availability have enabled leaps in performance and task diversification. Current systems can provide coarse- and fine-grained descriptions of video scenes, extract segments corresponding to queries, synthesize unobserved parts of videos, and predict context across multiple modalities. This survey comprehensively reviews advances in uni- and multi-modal action understanding across a range of tasks. We focus on prevalent challenges, overview widely adopted datasets, and surv"},"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":"2411.15106","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T18:09:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1a9aa573119e07f7a6ea6e0bfde953d81fa83f6806b5bd77871a5884a62df1f6","abstract_canon_sha256":"d27282da9121d5d0f8f578d76b259e8287b338b733bcfab82be2df9bf9a4d238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:03.795205Z","signature_b64":"qvbjW1QHwQlJtajMjflMW8oRkW1UHLuZ4JtFKcxec09k6bDjKvB05Cz3J7UFll2cslKUc4Bdz7ciKzBVagaXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9508915d4bcefbd77bc39b50f5b1189bc9b24457af79651d5fd4e13964a64a0b","last_reissued_at":"2026-07-05T10:59:03.794722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:03.794722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"About Time: Advances, Challenges, and Outlooks of Action Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Ronald Poppe","submitted_at":"2024-11-22T18:09:27Z","abstract_excerpt":"We have witnessed impressive advances in video action understanding. Increased dataset sizes, variability, and computation availability have enabled leaps in performance and task diversification. Current systems can provide coarse- and fine-grained descriptions of video scenes, extract segments corresponding to queries, synthesize unobserved parts of videos, and predict context across multiple modalities. This survey comprehensively reviews advances in uni- and multi-modal action understanding across a range of tasks. We focus on prevalent challenges, overview widely adopted datasets, and surv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15106","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/2411.15106/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":"2411.15106","created_at":"2026-07-05T10:59:03.794782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15106v2","created_at":"2026-07-05T10:59:03.794782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15106","created_at":"2026-07-05T10:59:03.794782+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUEJCXKLZ355","created_at":"2026-07-05T10:59:03.794782+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUEJCXKLZ355O66D","created_at":"2026-07-05T10:59:03.794782+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUEJCXKL","created_at":"2026-07-05T10:59:03.794782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06253","citing_title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP","json":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP.json","graph_json":"https://pith.science/api/pith-number/SUEJCXKLZ355O66DTNIPLMIYTP/graph.json","events_json":"https://pith.science/api/pith-number/SUEJCXKLZ355O66DTNIPLMIYTP/events.json","paper":"https://pith.science/paper/SUEJCXKL"},"agent_actions":{"view_html":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP","download_json":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP.json","view_paper":"https://pith.science/paper/SUEJCXKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15106&json=true","fetch_graph":"https://pith.science/api/pith-number/SUEJCXKLZ355O66DTNIPLMIYTP/graph.json","fetch_events":"https://pith.science/api/pith-number/SUEJCXKLZ355O66DTNIPLMIYTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP/action/storage_attestation","attest_author":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP/action/author_attestation","sign_citation":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP/action/citation_signature","submit_replication":"https://pith.science/pith/SUEJCXKLZ355O66DTNIPLMIYTP/action/replication_record"}},"created_at":"2026-07-05T10:59:03.794782+00:00","updated_at":"2026-07-05T10:59:03.794782+00:00"}