{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AMUTLNQE5GQAELOCPTXG2OD6IA","short_pith_number":"pith:AMUTLNQE","schema_version":"1.0","canonical_sha256":"032935b604e9a0022dc27cee6d387e401dbf2fb7e808791e4c9edfc89200a4c0","source":{"kind":"arxiv","id":"2304.11975","version":1},"attestation_state":"computed","paper":{"title":"MRSN: Multi-Relation Support Network for Video Action Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Chen, Minglei Yuan, Tong Lu, Yin-Dong Zheng","submitted_at":"2023-04-24T10:15:31Z","abstract_excerpt":"Action detection is a challenging video understanding task, requiring modeling spatio-temporal and interaction relations. Current methods usually model actor-actor and actor-context relations separately, ignoring their complementarity and mutual support. To solve this problem, we propose a novel network called Multi-Relation Support Network (MRSN). In MRSN, Actor-Context Relation Encoder (ACRE) and Actor-Actor Relation Encoder (AARE) model the actor-context and actor-actor relation separately. Then Relation Support Encoder (RSE) computes the supports between the two relations and performs rela"},"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":"2304.11975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-24T10:15:31Z","cross_cats_sorted":[],"title_canon_sha256":"e9154f6f57d6c70acb48a9fa6bf7eeaeafe4840e2793a4071d352e655e06ac1d","abstract_canon_sha256":"88a092166bf799a2c8a3ad86b787e77ccd88936bc3baf3fd99af830db5a2519b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:39.178244Z","signature_b64":"eweM+B7+HE+Jto7WDeAKXF0GUcYWbic0NMN9PN+bLXkc2QQZDJooNeaDr1y8UraHjcFL0UI9tilPKVru6K/LAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"032935b604e9a0022dc27cee6d387e401dbf2fb7e808791e4c9edfc89200a4c0","last_reissued_at":"2026-07-05T06:03:39.177860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:39.177860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MRSN: Multi-Relation Support Network for Video Action Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Chen, Minglei Yuan, Tong Lu, Yin-Dong Zheng","submitted_at":"2023-04-24T10:15:31Z","abstract_excerpt":"Action detection is a challenging video understanding task, requiring modeling spatio-temporal and interaction relations. Current methods usually model actor-actor and actor-context relations separately, ignoring their complementarity and mutual support. To solve this problem, we propose a novel network called Multi-Relation Support Network (MRSN). In MRSN, Actor-Context Relation Encoder (ACRE) and Actor-Actor Relation Encoder (AARE) model the actor-context and actor-actor relation separately. Then Relation Support Encoder (RSE) computes the supports between the two relations and performs rela"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11975","kind":"arxiv","version":1},"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/2304.11975/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":"2304.11975","created_at":"2026-07-05T06:03:39.177917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11975v1","created_at":"2026-07-05T06:03:39.177917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11975","created_at":"2026-07-05T06:03:39.177917+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMUTLNQE5GQA","created_at":"2026-07-05T06:03:39.177917+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMUTLNQE5GQAELOC","created_at":"2026-07-05T06:03:39.177917+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMUTLNQE","created_at":"2026-07-05T06:03:39.177917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10922","citing_title":"Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection","ref_index":92,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA","json":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA.json","graph_json":"https://pith.science/api/pith-number/AMUTLNQE5GQAELOCPTXG2OD6IA/graph.json","events_json":"https://pith.science/api/pith-number/AMUTLNQE5GQAELOCPTXG2OD6IA/events.json","paper":"https://pith.science/paper/AMUTLNQE"},"agent_actions":{"view_html":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA","download_json":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA.json","view_paper":"https://pith.science/paper/AMUTLNQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11975&json=true","fetch_graph":"https://pith.science/api/pith-number/AMUTLNQE5GQAELOCPTXG2OD6IA/graph.json","fetch_events":"https://pith.science/api/pith-number/AMUTLNQE5GQAELOCPTXG2OD6IA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA/action/storage_attestation","attest_author":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA/action/author_attestation","sign_citation":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA/action/citation_signature","submit_replication":"https://pith.science/pith/AMUTLNQE5GQAELOCPTXG2OD6IA/action/replication_record"}},"created_at":"2026-07-05T06:03:39.177917+00:00","updated_at":"2026-07-05T06:03:39.177917+00:00"}