{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SBAM3YD3NJD4JCZCB3XDRLHCQC","short_pith_number":"pith:SBAM3YD3","schema_version":"1.0","canonical_sha256":"9040cde07b6a47c48b220eee38ace280a4ced6a16287327684c5e5c3579b37c8","source":{"kind":"arxiv","id":"1611.05664","version":1},"attestation_state":"computed","paper":{"title":"Learning to detect and localize many objects from few examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bastien Moysset, Christian Wolf, Christoper Kermorvant","submitted_at":"2016-11-17T12:51:18Z","abstract_excerpt":"The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this work, we propose a new neural model which directly predicts bounding box coordinates. The particularity of our contribution lies in the local computations of predictions with a new form of local parameter sharing which keeps the overall amount of trainable parameters low. Key components of the model are spatial 2D-LSTM recurrent layers which convey contextual information betwe"},"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":"1611.05664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T12:51:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"362cbc4012e1b4856060005bdae9bd02c2d0aac2edbaa519e80082ae67bd59f6","abstract_canon_sha256":"f2c2de171423cc8450977c004e85233ee4716906d223fc62c0000a559a319e85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:02.924825Z","signature_b64":"2ani0uNLgPtytYCYibLv6sd1cdW9J8UgIk9mSLpAei7/KCC5GPk5zjQtOrxqwHcEqxM3w5rarwL4tHZKA5z3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9040cde07b6a47c48b220eee38ace280a4ced6a16287327684c5e5c3579b37c8","last_reissued_at":"2026-05-18T00:58:02.924328Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:02.924328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to detect and localize many objects from few examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bastien Moysset, Christian Wolf, Christoper Kermorvant","submitted_at":"2016-11-17T12:51:18Z","abstract_excerpt":"The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this work, we propose a new neural model which directly predicts bounding box coordinates. The particularity of our contribution lies in the local computations of predictions with a new form of local parameter sharing which keeps the overall amount of trainable parameters low. Key components of the model are spatial 2D-LSTM recurrent layers which convey contextual information betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05664","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":""},"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":"1611.05664","created_at":"2026-05-18T00:58:02.924417+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05664v1","created_at":"2026-05-18T00:58:02.924417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05664","created_at":"2026-05-18T00:58:02.924417+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBAM3YD3NJD4","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBAM3YD3NJD4JCZC","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBAM3YD3","created_at":"2026-05-18T12:30:44.179134+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/SBAM3YD3NJD4JCZCB3XDRLHCQC","json":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC.json","graph_json":"https://pith.science/api/pith-number/SBAM3YD3NJD4JCZCB3XDRLHCQC/graph.json","events_json":"https://pith.science/api/pith-number/SBAM3YD3NJD4JCZCB3XDRLHCQC/events.json","paper":"https://pith.science/paper/SBAM3YD3"},"agent_actions":{"view_html":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC","download_json":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC.json","view_paper":"https://pith.science/paper/SBAM3YD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05664&json=true","fetch_graph":"https://pith.science/api/pith-number/SBAM3YD3NJD4JCZCB3XDRLHCQC/graph.json","fetch_events":"https://pith.science/api/pith-number/SBAM3YD3NJD4JCZCB3XDRLHCQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC/action/storage_attestation","attest_author":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC/action/author_attestation","sign_citation":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC/action/citation_signature","submit_replication":"https://pith.science/pith/SBAM3YD3NJD4JCZCB3XDRLHCQC/action/replication_record"}},"created_at":"2026-05-18T00:58:02.924417+00:00","updated_at":"2026-05-18T00:58:02.924417+00:00"}