{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BSHI4HS35MOXFKD4VFMM5VNICZ","short_pith_number":"pith:BSHI4HS3","schema_version":"1.0","canonical_sha256":"0c8e8e1e5beb1d72a87ca958ced5a816679dfe0f974b2887d3aa149622fec76d","source":{"kind":"arxiv","id":"1909.11895","version":1},"attestation_state":"computed","paper":{"title":"Joint-task Self-supervised Learning for Temporal Correspondence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jan Kautz, Ming-Hsuan Yang, Shalini De Mello, Sifei Liu, Xiaolong Wang, Xueting Li","submitted_at":"2019-09-26T05:11:26Z","abstract_excerpt":"This paper proposes to learn reliable dense correspondence from videos in a self-supervised manner. Our learning process integrates two highly related tasks: tracking large image regions \\emph{and} establishing fine-grained pixel-level associations between consecutive video frames. We exploit the synergy between both tasks through a shared inter-frame affinity matrix, which simultaneously models transitions between video frames at both the region- and pixel-levels. While region-level localization helps reduce ambiguities in fine-grained matching by narrowing down search regions; fine-grained m"},"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":"1909.11895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-26T05:11:26Z","cross_cats_sorted":[],"title_canon_sha256":"bb7b5ea4ad20cb7be668c35d624f5f9e12707f32e075f2eedd4cd6a1872cec88","abstract_canon_sha256":"7cbe332ca366d3b9eabeec1fd218dd23d14f019075b3d3d6fc9efd6ca9dd5e86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:29.131242Z","signature_b64":"x4q1tT4ydD0NS2jhm/kI6U9Pp7hYRV9TAXGBly7EbAgKaV6//gA2pf8A2Kp7k+wzsMWpRvzMngCSQIhPYvOyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c8e8e1e5beb1d72a87ca958ced5a816679dfe0f974b2887d3aa149622fec76d","last_reissued_at":"2026-07-05T00:07:29.130843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:29.130843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint-task Self-supervised Learning for Temporal Correspondence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jan Kautz, Ming-Hsuan Yang, Shalini De Mello, Sifei Liu, Xiaolong Wang, Xueting Li","submitted_at":"2019-09-26T05:11:26Z","abstract_excerpt":"This paper proposes to learn reliable dense correspondence from videos in a self-supervised manner. Our learning process integrates two highly related tasks: tracking large image regions \\emph{and} establishing fine-grained pixel-level associations between consecutive video frames. We exploit the synergy between both tasks through a shared inter-frame affinity matrix, which simultaneously models transitions between video frames at both the region- and pixel-levels. While region-level localization helps reduce ambiguities in fine-grained matching by narrowing down search regions; fine-grained m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11895","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/1909.11895/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":"1909.11895","created_at":"2026-07-05T00:07:29.130902+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11895v1","created_at":"2026-07-05T00:07:29.130902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11895","created_at":"2026-07-05T00:07:29.130902+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSHI4HS35MOX","created_at":"2026-07-05T00:07:29.130902+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSHI4HS35MOXFKD4","created_at":"2026-07-05T00:07:29.130902+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSHI4HS3","created_at":"2026-07-05T00:07:29.130902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05543","citing_title":"FRAME: Pre-Training Video Feature Representations via Anticipation and Memory","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ","json":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ.json","graph_json":"https://pith.science/api/pith-number/BSHI4HS35MOXFKD4VFMM5VNICZ/graph.json","events_json":"https://pith.science/api/pith-number/BSHI4HS35MOXFKD4VFMM5VNICZ/events.json","paper":"https://pith.science/paper/BSHI4HS3"},"agent_actions":{"view_html":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ","download_json":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ.json","view_paper":"https://pith.science/paper/BSHI4HS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11895&json=true","fetch_graph":"https://pith.science/api/pith-number/BSHI4HS35MOXFKD4VFMM5VNICZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BSHI4HS35MOXFKD4VFMM5VNICZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ/action/storage_attestation","attest_author":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ/action/author_attestation","sign_citation":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ/action/citation_signature","submit_replication":"https://pith.science/pith/BSHI4HS35MOXFKD4VFMM5VNICZ/action/replication_record"}},"created_at":"2026-07-05T00:07:29.130902+00:00","updated_at":"2026-07-05T00:07:29.130902+00:00"}