{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:X74LOOI2L6Z6MC2VVCWZ7UHIPF","short_pith_number":"pith:X74LOOI2","schema_version":"1.0","canonical_sha256":"bff8b7391a5fb3e60b55a8ad9fd0e8795e28f608f9faa519f2f66832e9b9da09","source":{"kind":"arxiv","id":"2106.08061","version":2},"attestation_state":"computed","paper":{"title":"Relation Modeling in Spatio-Temporal Action Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianwen Jiang, Mingqian Tang, Shiwei Zhang, Xiang Wang, Yue Gao, Yutong Feng, Zhiwu Qing, Ziyuan Huang","submitted_at":"2021-06-15T11:40:18Z","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."},"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":"2106.08061","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-15T11:40:18Z","cross_cats_sorted":[],"title_canon_sha256":"9ab2fea22d94e73492d063681832d628b11c08e7f5698e217413f82e9c78a2dc","abstract_canon_sha256":"375b22487c554c93aa89bbd88efec2077a3ec7c590431b45f5cb9bf72667b3c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:56.614803Z","signature_b64":"TiQN4ddAgGrHJ9axKE6Lh0gbLcfHTZ8JNTU3IvO+p/1JWiNBgSa+lxv0GALv+KD5vS1alOVsaN1Jyl0CneWoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bff8b7391a5fb3e60b55a8ad9fd0e8795e28f608f9faa519f2f66832e9b9da09","last_reissued_at":"2026-07-05T02:49:56.614357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:56.614357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relation Modeling in Spatio-Temporal Action Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianwen Jiang, Mingqian Tang, Shiwei Zhang, Xiang Wang, Yue Gao, Yutong Feng, Zhiwu Qing, Ziyuan Huang","submitted_at":"2021-06-15T11:40:18Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08061","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/2106.08061/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":"2106.08061","created_at":"2026-07-05T02:49:56.614421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.08061v2","created_at":"2026-07-05T02:49:56.614421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08061","created_at":"2026-07-05T02:49:56.614421+00:00"},{"alias_kind":"pith_short_12","alias_value":"X74LOOI2L6Z6","created_at":"2026-07-05T02:49:56.614421+00:00"},{"alias_kind":"pith_short_16","alias_value":"X74LOOI2L6Z6MC2V","created_at":"2026-07-05T02:49:56.614421+00:00"},{"alias_kind":"pith_short_8","alias_value":"X74LOOI2","created_at":"2026-07-05T02:49:56.614421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2212.03191","citing_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF","json":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF.json","graph_json":"https://pith.science/api/pith-number/X74LOOI2L6Z6MC2VVCWZ7UHIPF/graph.json","events_json":"https://pith.science/api/pith-number/X74LOOI2L6Z6MC2VVCWZ7UHIPF/events.json","paper":"https://pith.science/paper/X74LOOI2"},"agent_actions":{"view_html":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF","download_json":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF.json","view_paper":"https://pith.science/paper/X74LOOI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.08061&json=true","fetch_graph":"https://pith.science/api/pith-number/X74LOOI2L6Z6MC2VVCWZ7UHIPF/graph.json","fetch_events":"https://pith.science/api/pith-number/X74LOOI2L6Z6MC2VVCWZ7UHIPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF/action/storage_attestation","attest_author":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF/action/author_attestation","sign_citation":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF/action/citation_signature","submit_replication":"https://pith.science/pith/X74LOOI2L6Z6MC2VVCWZ7UHIPF/action/replication_record"}},"created_at":"2026-07-05T02:49:56.614421+00:00","updated_at":"2026-07-05T02:49:56.614421+00:00"}