{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UBZ3KFVYGK3L7OUMJU6FBJD3LO","short_pith_number":"pith:UBZ3KFVY","schema_version":"1.0","canonical_sha256":"a073b516b832b6bfba8c4d3c50a47b5bbc0eababfff35c0c921bf10906a451ff","source":{"kind":"arxiv","id":"2201.07436","version":3},"attestation_state":"computed","paper":{"title":"Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donggyu Joo, Doyeon Kim, Junmo Kim, Pyungwhan Ahn, Sehwan Chun, Woonghyun Ka","submitted_at":"2022-01-19T06:37:21Z","abstract_excerpt":"Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and training strategy for monocular depth estimation to further improve the prediction accuracy of the network. We deploy a hierarchical transformer encoder to capture and convey the global context, and design a lightweight yet powerful decoder to generate an estimated depth map while considering local connectivity. By constructing connected paths between multi"},"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":"2201.07436","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-19T06:37:21Z","cross_cats_sorted":[],"title_canon_sha256":"e941a90b011a218ce667c82a474000e6b53fd629b4570a223ce63154f5e160a3","abstract_canon_sha256":"932784752f6b9a28ae351f77089e30a17ce3e87151343a148f2c061fefe33441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:36.590748Z","signature_b64":"YhtPdG0MYVNydEZ63j/MYvkoOdlf2nOvNlGawy4gUVhj2cYsYoPnhJEcWETH0HefL1TVUl0iomeKOkvNpHBlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a073b516b832b6bfba8c4d3c50a47b5bbc0eababfff35c0c921bf10906a451ff","last_reissued_at":"2026-07-05T05:11:36.590189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:36.590189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donggyu Joo, Doyeon Kim, Junmo Kim, Pyungwhan Ahn, Sehwan Chun, Woonghyun Ka","submitted_at":"2022-01-19T06:37:21Z","abstract_excerpt":"Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and training strategy for monocular depth estimation to further improve the prediction accuracy of the network. We deploy a hierarchical transformer encoder to capture and convey the global context, and design a lightweight yet powerful decoder to generate an estimated depth map while considering local connectivity. By constructing connected paths between multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07436","kind":"arxiv","version":3},"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/2201.07436/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":"2201.07436","created_at":"2026-07-05T05:11:36.590255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.07436v3","created_at":"2026-07-05T05:11:36.590255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07436","created_at":"2026-07-05T05:11:36.590255+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBZ3KFVYGK3L","created_at":"2026-07-05T05:11:36.590255+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBZ3KFVYGK3L7OUM","created_at":"2026-07-05T05:11:36.590255+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBZ3KFVY","created_at":"2026-07-05T05:11:36.590255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20303","citing_title":"Physically Guided Visual Mass Estimation from a Single RGB Image","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17235","citing_title":"Massive-scale unlabeled field and labeled synthetic seismic datasets of global shelf-edge clinothems","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO","json":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO.json","graph_json":"https://pith.science/api/pith-number/UBZ3KFVYGK3L7OUMJU6FBJD3LO/graph.json","events_json":"https://pith.science/api/pith-number/UBZ3KFVYGK3L7OUMJU6FBJD3LO/events.json","paper":"https://pith.science/paper/UBZ3KFVY"},"agent_actions":{"view_html":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO","download_json":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO.json","view_paper":"https://pith.science/paper/UBZ3KFVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.07436&json=true","fetch_graph":"https://pith.science/api/pith-number/UBZ3KFVYGK3L7OUMJU6FBJD3LO/graph.json","fetch_events":"https://pith.science/api/pith-number/UBZ3KFVYGK3L7OUMJU6FBJD3LO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO/action/storage_attestation","attest_author":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO/action/author_attestation","sign_citation":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO/action/citation_signature","submit_replication":"https://pith.science/pith/UBZ3KFVYGK3L7OUMJU6FBJD3LO/action/replication_record"}},"created_at":"2026-07-05T05:11:36.590255+00:00","updated_at":"2026-07-05T05:11:36.590255+00:00"}