{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:H2GOLN5XAFXWFXGEPQ3ZVIGDOG","short_pith_number":"pith:H2GOLN5X","schema_version":"1.0","canonical_sha256":"3e8ce5b7b7016f62dcc47c379aa0c371bcb43d3754b7c145c0221d98417f7a11","source":{"kind":"arxiv","id":"1703.10295","version":3},"attestation_state":"computed","paper":{"title":"DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lachlan Tychsen-Smith, Lars Petersson","submitted_at":"2017-03-30T02:50:54Z","abstract_excerpt":"We define the object detection from imagery problem as estimating a very large but extremely sparse bounding box dependent probability distribution. Subsequently we identify a sparse distribution estimation scheme, Directed Sparse Sampling, and employ it in a single end-to-end CNN based detection model. This methodology extends and formalizes previous state-of-the-art detection models with an additional emphasis on high evaluation rates and reduced manual engineering. We introduce two novelties, a corner based region-of-interest estimator and a deconvolution based CNN model. The resulting mode"},"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":"1703.10295","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-30T02:50:54Z","cross_cats_sorted":[],"title_canon_sha256":"0a269422beea731063d3db3b43c28a21cd3f75a7cbe2ddf6ed10b8122d43dda6","abstract_canon_sha256":"6a651a54583d33cccada46f7e4d265595ee1abb334f1808f8d89f1d695f572ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:52.507289Z","signature_b64":"Nwx1ld2vrc95F9ncSckWCAB67/2RUl+oW911E5HTUOCUUtOtsvcwAmtaOq/9+S2XUUaw9dYRuIBfZ13SLYGxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8ce5b7b7016f62dcc47c379aa0c371bcb43d3754b7c145c0221d98417f7a11","last_reissued_at":"2026-05-18T00:39:52.506624Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:52.506624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lachlan Tychsen-Smith, Lars Petersson","submitted_at":"2017-03-30T02:50:54Z","abstract_excerpt":"We define the object detection from imagery problem as estimating a very large but extremely sparse bounding box dependent probability distribution. Subsequently we identify a sparse distribution estimation scheme, Directed Sparse Sampling, and employ it in a single end-to-end CNN based detection model. This methodology extends and formalizes previous state-of-the-art detection models with an additional emphasis on high evaluation rates and reduced manual engineering. We introduce two novelties, a corner based region-of-interest estimator and a deconvolution based CNN model. The resulting mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10295","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":""},"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":"1703.10295","created_at":"2026-05-18T00:39:52.506739+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10295v3","created_at":"2026-05-18T00:39:52.506739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10295","created_at":"2026-05-18T00:39:52.506739+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2GOLN5XAFXW","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2GOLN5XAFXWFXGE","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2GOLN5X","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06067","citing_title":"ALFA: Agglomerative Late Fusion Algorithm for Object Detection","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG","json":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG.json","graph_json":"https://pith.science/api/pith-number/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/graph.json","events_json":"https://pith.science/api/pith-number/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/events.json","paper":"https://pith.science/paper/H2GOLN5X"},"agent_actions":{"view_html":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG","download_json":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG.json","view_paper":"https://pith.science/paper/H2GOLN5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10295&json=true","fetch_graph":"https://pith.science/api/pith-number/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/graph.json","fetch_events":"https://pith.science/api/pith-number/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/action/storage_attestation","attest_author":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/action/author_attestation","sign_citation":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/action/citation_signature","submit_replication":"https://pith.science/pith/H2GOLN5XAFXWFXGEPQ3ZVIGDOG/action/replication_record"}},"created_at":"2026-05-18T00:39:52.506739+00:00","updated_at":"2026-05-18T00:39:52.506739+00:00"}