{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B3CPSKGK4H5Q4KPHNABZZSJUQD","short_pith_number":"pith:B3CPSKGK","schema_version":"1.0","canonical_sha256":"0ec4f928cae1fb0e29e768039cc93480f1b063b83d98e963c8667fb7148b2555","source":{"kind":"arxiv","id":"2103.11468","version":2},"attestation_state":"computed","paper":{"title":"Learning Multi-Scene Absolute Pose Regression with Transformers","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ron Ferens, Yoli Shavit, Yosi Keller","submitted_at":"2021-03-21T19:21:44Z","abstract_excerpt":"Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron head is trained with images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended for learning multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent feat"},"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":"2103.11468","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-21T19:21:44Z","cross_cats_sorted":[],"title_canon_sha256":"a1097a1ca150cfcd2c67ace41cf445641dbcac10c865e1bc25e2904ba55b9838","abstract_canon_sha256":"fd1792f42fc94803c25d028c48eed3bc3b5681e2ce23026ad900f8c5049b845f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:32.435290Z","signature_b64":"OA+4XTlO5KDoiCMr0vTYGchhX0FifQem1WfXOjZTOLcxQ9m2w0LP/CzhED645RWS7UIhYV7Kb63A7T8xDAyGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ec4f928cae1fb0e29e768039cc93480f1b063b83d98e963c8667fb7148b2555","last_reissued_at":"2026-07-05T03:00:32.434826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:32.434826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Multi-Scene Absolute Pose Regression with Transformers","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ron Ferens, Yoli Shavit, Yosi Keller","submitted_at":"2021-03-21T19:21:44Z","abstract_excerpt":"Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron head is trained with images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended for learning multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11468","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.11468/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":"2103.11468","created_at":"2026-07-05T03:00:32.434889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.11468v2","created_at":"2026-07-05T03:00:32.434889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11468","created_at":"2026-07-05T03:00:32.434889+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3CPSKGK4H5Q","created_at":"2026-07-05T03:00:32.434889+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3CPSKGK4H5Q4KPH","created_at":"2026-07-05T03:00:32.434889+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3CPSKGK","created_at":"2026-07-05T03:00:32.434889+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/B3CPSKGK4H5Q4KPHNABZZSJUQD","json":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD.json","graph_json":"https://pith.science/api/pith-number/B3CPSKGK4H5Q4KPHNABZZSJUQD/graph.json","events_json":"https://pith.science/api/pith-number/B3CPSKGK4H5Q4KPHNABZZSJUQD/events.json","paper":"https://pith.science/paper/B3CPSKGK"},"agent_actions":{"view_html":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD","download_json":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD.json","view_paper":"https://pith.science/paper/B3CPSKGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.11468&json=true","fetch_graph":"https://pith.science/api/pith-number/B3CPSKGK4H5Q4KPHNABZZSJUQD/graph.json","fetch_events":"https://pith.science/api/pith-number/B3CPSKGK4H5Q4KPHNABZZSJUQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD/action/storage_attestation","attest_author":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD/action/author_attestation","sign_citation":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD/action/citation_signature","submit_replication":"https://pith.science/pith/B3CPSKGK4H5Q4KPHNABZZSJUQD/action/replication_record"}},"created_at":"2026-07-05T03:00:32.434889+00:00","updated_at":"2026-07-05T03:00:32.434889+00:00"}