{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VV7IX76O4ENM44QPRVXF6GCDYI","short_pith_number":"pith:VV7IX76O","schema_version":"1.0","canonical_sha256":"ad7e8bffcee11ace720f8d6e5f1843c2147c2b706d915e10f4398c78268365bd","source":{"kind":"arxiv","id":"1806.01810","version":2},"attestation_state":"computed","paper":{"title":"Videos as Space-Time Region Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Xiaolong Wang","submitted_at":"2018-06-05T16:58:59Z","abstract_excerpt":"How do humans recognize the action \"opening a book\" ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent videos as space-time region graphs which capture these two important cues. Our graph nodes are defined by the object region proposals from different frames in a long range video. These nodes are connected by two types of relations: (i) similarity relations capturing the long range dependencies between correlated objects and (ii) spatial-temporal relations captur"},"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":"1806.01810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-05T16:58:59Z","cross_cats_sorted":[],"title_canon_sha256":"e8504309824a2c1bae14bd4e429483f4869940504479c39c9c3b072d98660a13","abstract_canon_sha256":"e36f757d2e66e0fa831c86ccbf48865e05a92858178fb34215258a41a41e06b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:31.865954Z","signature_b64":"kKPkIgWINbxLth5mZVJ9eEj1bDj72beqKQ/UsAzdhVEG6J3mXOyt0BZR09q0wUzzznQjECAzodLMN2T5HgS+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad7e8bffcee11ace720f8d6e5f1843c2147c2b706d915e10f4398c78268365bd","last_reissued_at":"2026-05-17T23:57:31.865479Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:31.865479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Videos as Space-Time Region Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Xiaolong Wang","submitted_at":"2018-06-05T16:58:59Z","abstract_excerpt":"How do humans recognize the action \"opening a book\" ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent videos as space-time region graphs which capture these two important cues. Our graph nodes are defined by the object region proposals from different frames in a long range video. These nodes are connected by two types of relations: (i) similarity relations capturing the long range dependencies between correlated objects and (ii) spatial-temporal relations captur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01810","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":"1806.01810","created_at":"2026-05-17T23:57:31.865555+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01810v2","created_at":"2026-05-17T23:57:31.865555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01810","created_at":"2026-05-17T23:57:31.865555+00:00"},{"alias_kind":"pith_short_12","alias_value":"VV7IX76O4ENM","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VV7IX76O4ENM44QP","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VV7IX76O","created_at":"2026-05-18T12:32:59.047623+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/VV7IX76O4ENM44QPRVXF6GCDYI","json":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI.json","graph_json":"https://pith.science/api/pith-number/VV7IX76O4ENM44QPRVXF6GCDYI/graph.json","events_json":"https://pith.science/api/pith-number/VV7IX76O4ENM44QPRVXF6GCDYI/events.json","paper":"https://pith.science/paper/VV7IX76O"},"agent_actions":{"view_html":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI","download_json":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI.json","view_paper":"https://pith.science/paper/VV7IX76O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01810&json=true","fetch_graph":"https://pith.science/api/pith-number/VV7IX76O4ENM44QPRVXF6GCDYI/graph.json","fetch_events":"https://pith.science/api/pith-number/VV7IX76O4ENM44QPRVXF6GCDYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI/action/storage_attestation","attest_author":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI/action/author_attestation","sign_citation":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI/action/citation_signature","submit_replication":"https://pith.science/pith/VV7IX76O4ENM44QPRVXF6GCDYI/action/replication_record"}},"created_at":"2026-05-17T23:57:31.865555+00:00","updated_at":"2026-05-17T23:57:31.865555+00:00"}