{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3A2CCO352O3LUAWXDGITIPGUNA","short_pith_number":"pith:3A2CCO35","schema_version":"1.0","canonical_sha256":"d834213b7dd3b6ba02d71991343cd4682e1eec0b6d05750c5f64f68cf13df8a4","source":{"kind":"arxiv","id":"1711.09125","version":2},"attestation_state":"computed","paper":{"title":"Appearance-and-Relation Networks for Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Luc Van Gool, Wei Li, Wen Li","submitted_at":"2017-11-24T20:10:26Z","abstract_excerpt":"Spatiotemporal feature learning in videos is a fundamental problem in computer vision. This paper presents a new architecture, termed as Appearance-and-Relation Network (ARTNet), to learn video representation in an end-to-end manner. ARTNets are constructed by stacking multiple generic building blocks, called as SMART, whose goal is to simultaneously model appearance and relation from RGB input in a separate and explicit manner. Specifically, SMART blocks decouple the spatiotemporal learning module into an appearance branch for spatial modeling and a relation branch for temporal modeling. The "},"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":"1711.09125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-24T20:10:26Z","cross_cats_sorted":[],"title_canon_sha256":"b61db685087c3f08ff83a61580616bab97a5fc3e426533bd3b5941dbece2fcad","abstract_canon_sha256":"cadd68a5f434f46abfe17707add932432fc925cc4e60498bba576391210f95d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:44.592850Z","signature_b64":"tKd8rR6NjxG/S8NJTF0D29Ppi2zO6i4UmLtCpGOgAGU9yfKM5Ft8seZQU226sgULUOca3qUXtCqeguvj3UZfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d834213b7dd3b6ba02d71991343cd4682e1eec0b6d05750c5f64f68cf13df8a4","last_reissued_at":"2026-05-18T00:16:44.592367Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:44.592367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Appearance-and-Relation Networks for Video Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Limin Wang, Luc Van Gool, Wei Li, Wen Li","submitted_at":"2017-11-24T20:10:26Z","abstract_excerpt":"Spatiotemporal feature learning in videos is a fundamental problem in computer vision. This paper presents a new architecture, termed as Appearance-and-Relation Network (ARTNet), to learn video representation in an end-to-end manner. ARTNets are constructed by stacking multiple generic building blocks, called as SMART, whose goal is to simultaneously model appearance and relation from RGB input in a separate and explicit manner. Specifically, SMART blocks decouple the spatiotemporal learning module into an appearance branch for spatial modeling and a relation branch for temporal modeling. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09125","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":""},"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":"1711.09125","created_at":"2026-05-18T00:16:44.592446+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09125v2","created_at":"2026-05-18T00:16:44.592446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09125","created_at":"2026-05-18T00:16:44.592446+00:00"},{"alias_kind":"pith_short_12","alias_value":"3A2CCO352O3L","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3A2CCO352O3LUAWX","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3A2CCO35","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA","json":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA.json","graph_json":"https://pith.science/api/pith-number/3A2CCO352O3LUAWXDGITIPGUNA/graph.json","events_json":"https://pith.science/api/pith-number/3A2CCO352O3LUAWXDGITIPGUNA/events.json","paper":"https://pith.science/paper/3A2CCO35"},"agent_actions":{"view_html":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA","download_json":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA.json","view_paper":"https://pith.science/paper/3A2CCO35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09125&json=true","fetch_graph":"https://pith.science/api/pith-number/3A2CCO352O3LUAWXDGITIPGUNA/graph.json","fetch_events":"https://pith.science/api/pith-number/3A2CCO352O3LUAWXDGITIPGUNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA/action/storage_attestation","attest_author":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA/action/author_attestation","sign_citation":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA/action/citation_signature","submit_replication":"https://pith.science/pith/3A2CCO352O3LUAWXDGITIPGUNA/action/replication_record"}},"created_at":"2026-05-18T00:16:44.592446+00:00","updated_at":"2026-05-18T00:16:44.592446+00:00"}