{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RGU3KSK6LR4IIOSOWKKBN24JFL","short_pith_number":"pith:RGU3KSK6","schema_version":"1.0","canonical_sha256":"89a9b5495e5c78843a4eb29416eb892acc5405f114f43fac78f65bfef868d284","source":{"kind":"arxiv","id":"2109.13499","version":1},"attestation_state":"computed","paper":{"title":"Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pheng-Ann Heng, Yueming Jin, Zixu Zhao","submitted_at":"2021-09-28T05:40:01Z","abstract_excerpt":"This paper presents a self-supervised method for learning reliable visual correspondence from unlabeled videos. We formulate the correspondence as finding paths in a joint space-time graph, where nodes are grid patches sampled from frames, and are linked by two types of edges: (i) neighbor relations that determine the aggregation strength from intra-frame neighbors in space, and (ii) similarity relations that indicate the transition probability of inter-frame paths across time. Leveraging the cycle-consistency in videos, our contrastive learning objective discriminates dynamic objects from bot"},"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":"2109.13499","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-28T05:40:01Z","cross_cats_sorted":[],"title_canon_sha256":"bf44ec39729cf33be37c3e9fbe11ec89e992978a186ed1054b29424e26f9844f","abstract_canon_sha256":"afac4cd542076dc69adba4574e01dfd2f29ccfc389621cc9066378b89079481d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:03.418776Z","signature_b64":"/bIW99xIAKWIYYvMyNgN1ziBWqAqgk9uZT1zYW/I02jxBUk8kXY/D7VaeYKdlN31L3GbrGdmWFup8Qs/4qCxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a9b5495e5c78843a4eb29416eb892acc5405f114f43fac78f65bfef868d284","last_reissued_at":"2026-07-05T03:18:03.418275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:03.418275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pheng-Ann Heng, Yueming Jin, Zixu Zhao","submitted_at":"2021-09-28T05:40:01Z","abstract_excerpt":"This paper presents a self-supervised method for learning reliable visual correspondence from unlabeled videos. We formulate the correspondence as finding paths in a joint space-time graph, where nodes are grid patches sampled from frames, and are linked by two types of edges: (i) neighbor relations that determine the aggregation strength from intra-frame neighbors in space, and (ii) similarity relations that indicate the transition probability of inter-frame paths across time. Leveraging the cycle-consistency in videos, our contrastive learning objective discriminates dynamic objects from bot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13499","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/2109.13499/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":"2109.13499","created_at":"2026-07-05T03:18:03.418347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.13499v1","created_at":"2026-07-05T03:18:03.418347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13499","created_at":"2026-07-05T03:18:03.418347+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGU3KSK6LR4I","created_at":"2026-07-05T03:18:03.418347+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGU3KSK6LR4IIOSO","created_at":"2026-07-05T03:18:03.418347+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGU3KSK6","created_at":"2026-07-05T03:18:03.418347+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/RGU3KSK6LR4IIOSOWKKBN24JFL","json":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL.json","graph_json":"https://pith.science/api/pith-number/RGU3KSK6LR4IIOSOWKKBN24JFL/graph.json","events_json":"https://pith.science/api/pith-number/RGU3KSK6LR4IIOSOWKKBN24JFL/events.json","paper":"https://pith.science/paper/RGU3KSK6"},"agent_actions":{"view_html":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL","download_json":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL.json","view_paper":"https://pith.science/paper/RGU3KSK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.13499&json=true","fetch_graph":"https://pith.science/api/pith-number/RGU3KSK6LR4IIOSOWKKBN24JFL/graph.json","fetch_events":"https://pith.science/api/pith-number/RGU3KSK6LR4IIOSOWKKBN24JFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL/action/storage_attestation","attest_author":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL/action/author_attestation","sign_citation":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL/action/citation_signature","submit_replication":"https://pith.science/pith/RGU3KSK6LR4IIOSOWKKBN24JFL/action/replication_record"}},"created_at":"2026-07-05T03:18:03.418347+00:00","updated_at":"2026-07-05T03:18:03.418347+00:00"}