{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M5VK3JPL73E7OXUY4FLBTOZXIC","short_pith_number":"pith:M5VK3JPL","schema_version":"1.0","canonical_sha256":"676aada5ebfec9f75e98e15619bb37408f7829ee039c233072795e76d7a85829","source":{"kind":"arxiv","id":"2104.00969","version":5},"attestation_state":"computed","paper":{"title":"TubeR: Tubelet Transformer for Video Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G.M. Snoek, Chunhui Liu, Davide Modolo, Hao Chen, Ivan Marsic, Jiaojiao Zhao, Joseph Tighe, Kaustav Kundu, Mingze Xu, Shuai Bing, Xinyu Li, Yanyi Zhang, Yuanjun Xiong","submitted_at":"2021-04-02T10:21:22Z","abstract_excerpt":"We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-po"},"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":"2104.00969","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-02T10:21:22Z","cross_cats_sorted":[],"title_canon_sha256":"f55a136cd94d7ebac2d52fbd0f2455ee77591ec4f6c1fc90a7c1eb9991b4d18a","abstract_canon_sha256":"3e8d2048fe04649fc66cb18217f585d20e6c5d613ba9306e3ff51a7beac5c489"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:45.079450Z","signature_b64":"88dLlN35X16WTYwh24wLwL5zns9jakOHQILa5E31mUbP6N8FPDxTFK0FecetRFcBUvXuptGdlNeTtoCP+QIPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"676aada5ebfec9f75e98e15619bb37408f7829ee039c233072795e76d7a85829","last_reissued_at":"2026-07-05T04:21:45.079029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:45.079029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TubeR: Tubelet Transformer for Video Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G.M. Snoek, Chunhui Liu, Davide Modolo, Hao Chen, Ivan Marsic, Jiaojiao Zhao, Joseph Tighe, Kaustav Kundu, Mingze Xu, Shuai Bing, Xinyu Li, Yanyi Zhang, Yuanjun Xiong","submitted_at":"2021-04-02T10:21:22Z","abstract_excerpt":"We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00969","kind":"arxiv","version":5},"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/2104.00969/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":"2104.00969","created_at":"2026-07-05T04:21:45.079085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00969v5","created_at":"2026-07-05T04:21:45.079085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00969","created_at":"2026-07-05T04:21:45.079085+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5VK3JPL73E7","created_at":"2026-07-05T04:21:45.079085+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5VK3JPL73E7OXUY","created_at":"2026-07-05T04:21:45.079085+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5VK3JPL","created_at":"2026-07-05T04:21:45.079085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07072","citing_title":"Stable Mean Teacher for Semi-supervised Video Action Detection","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC","json":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC.json","graph_json":"https://pith.science/api/pith-number/M5VK3JPL73E7OXUY4FLBTOZXIC/graph.json","events_json":"https://pith.science/api/pith-number/M5VK3JPL73E7OXUY4FLBTOZXIC/events.json","paper":"https://pith.science/paper/M5VK3JPL"},"agent_actions":{"view_html":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC","download_json":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC.json","view_paper":"https://pith.science/paper/M5VK3JPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00969&json=true","fetch_graph":"https://pith.science/api/pith-number/M5VK3JPL73E7OXUY4FLBTOZXIC/graph.json","fetch_events":"https://pith.science/api/pith-number/M5VK3JPL73E7OXUY4FLBTOZXIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC/action/storage_attestation","attest_author":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC/action/author_attestation","sign_citation":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC/action/citation_signature","submit_replication":"https://pith.science/pith/M5VK3JPL73E7OXUY4FLBTOZXIC/action/replication_record"}},"created_at":"2026-07-05T04:21:45.079085+00:00","updated_at":"2026-07-05T04:21:45.079085+00:00"}