{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X74LOOI2L6Z6MC2VVCWZ7UHIPF","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":"375b22487c554c93aa89bbd88efec2077a3ec7c590431b45f5cb9bf72667b3c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-15T11:40:18Z","title_canon_sha256":"9ab2fea22d94e73492d063681832d628b11c08e7f5698e217413f82e9c78a2dc"},"schema_version":"1.0","source":{"id":"2106.08061","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08061","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08061v2","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08061","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"X74LOOI2L6Z6","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"X74LOOI2L6Z6MC2V","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"X74LOOI2","created_at":"2026-07-05T02:49:56Z"}],"graph_snapshots":[{"event_id":"sha256:529a3451591b4aa3bda0280e136a68e359580643b2b25a69a94758dea6f8470e","target":"graph","created_at":"2026-07-05T02:49:56Z","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/2106.08061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation modeling methods for spatio-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. Learning with memory bank and finetuning for long-tailed distribution are also investigated to further improve the performance. In this paper, we detail the implementations of our solution and provide experiments results and corresponding discussions.","authors_text":"Jianwen Jiang, Mingqian Tang, Shiwei Zhang, Xiang Wang, Yue Gao, Yutong Feng, Zhiwu Qing, Ziyuan Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-15T11:40:18Z","title":"Relation Modeling in Spatio-Temporal Action Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08061","kind":"arxiv","version":2},"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:f05c7e663b25022fb563ba3e18e947b43579c0b6cab7160234ccddd8181af82a","target":"record","created_at":"2026-07-05T02:49:56Z","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":"375b22487c554c93aa89bbd88efec2077a3ec7c590431b45f5cb9bf72667b3c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-15T11:40:18Z","title_canon_sha256":"9ab2fea22d94e73492d063681832d628b11c08e7f5698e217413f82e9c78a2dc"},"schema_version":"1.0","source":{"id":"2106.08061","kind":"arxiv","version":2}},"canonical_sha256":"bff8b7391a5fb3e60b55a8ad9fd0e8795e28f608f9faa519f2f66832e9b9da09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bff8b7391a5fb3e60b55a8ad9fd0e8795e28f608f9faa519f2f66832e9b9da09","first_computed_at":"2026-07-05T02:49:56.614357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:56.614357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TiQN4ddAgGrHJ9axKE6Lh0gbLcfHTZ8JNTU3IvO+p/1JWiNBgSa+lxv0GALv+KD5vS1alOVsaN1Jyl0CneWoBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:56.614803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08061","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f05c7e663b25022fb563ba3e18e947b43579c0b6cab7160234ccddd8181af82a","sha256:529a3451591b4aa3bda0280e136a68e359580643b2b25a69a94758dea6f8470e"],"state_sha256":"5ef88a8a6602d7b6205e3100138c31e9d5d0b1979766595f863b119755ef5d46"}