{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M5VK3JPL73E7OXUY4FLBTOZXIC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3e8d2048fe04649fc66cb18217f585d20e6c5d613ba9306e3ff51a7beac5c489","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-02T10:21:22Z","title_canon_sha256":"f55a136cd94d7ebac2d52fbd0f2455ee77591ec4f6c1fc90a7c1eb9991b4d18a"},"schema_version":"1.0","source":{"id":"2104.00969","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00969","created_at":"2026-07-05T04:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00969v5","created_at":"2026-07-05T04:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00969","created_at":"2026-07-05T04:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"M5VK3JPL73E7","created_at":"2026-07-05T04:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"M5VK3JPL73E7OXUY","created_at":"2026-07-05T04:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"M5VK3JPL","created_at":"2026-07-05T04:21:45Z"}],"graph_snapshots":[{"event_id":"sha256:4dee748c772d9b5c3a55ad9f23e7f7cd3a686c672890a105533290ab4ba08db1","target":"graph","created_at":"2026-07-05T04:21:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.00969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-02T10:21:22Z","title":"TubeR: Tubelet Transformer for Video Action Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00969","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:99e174d564b3db607da69739ed2033cdb63dced4559fa1fdeb22926d9a1da98c","target":"record","created_at":"2026-07-05T04:21:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3e8d2048fe04649fc66cb18217f585d20e6c5d613ba9306e3ff51a7beac5c489","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-02T10:21:22Z","title_canon_sha256":"f55a136cd94d7ebac2d52fbd0f2455ee77591ec4f6c1fc90a7c1eb9991b4d18a"},"schema_version":"1.0","source":{"id":"2104.00969","kind":"arxiv","version":5}},"canonical_sha256":"676aada5ebfec9f75e98e15619bb37408f7829ee039c233072795e76d7a85829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"676aada5ebfec9f75e98e15619bb37408f7829ee039c233072795e76d7a85829","first_computed_at":"2026-07-05T04:21:45.079029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:21:45.079029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"88dLlN35X16WTYwh24wLwL5zns9jakOHQILa5E31mUbP6N8FPDxTFK0FecetRFcBUvXuptGdlNeTtoCP+QIPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:21:45.079450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00969","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99e174d564b3db607da69739ed2033cdb63dced4559fa1fdeb22926d9a1da98c","sha256:4dee748c772d9b5c3a55ad9f23e7f7cd3a686c672890a105533290ab4ba08db1"],"state_sha256":"fc0fc24281b38dd57d4dc0d50876554a05b86a7589d86c9d27cd5824caacee8a"}