{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4KTIBGRZPJAEYJ7U3QQG34BVGQ","short_pith_number":"pith:4KTIBGRZ","schema_version":"1.0","canonical_sha256":"e2a6809a397a404c27f4dc206df035342378574154342585d60e8363f83e386e","source":{"kind":"arxiv","id":"1509.04874","version":3},"attestation_state":"computed","paper":{"title":"DenseBox: Unifying Landmark Localization with End to End Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lichao Huang, Yafeng Deng, Yinan Yu, Yi Yang","submitted_at":"2015-09-16T10:30:37Z","abstract_excerpt":"How can a single fully convolutional neural network (FCN) perform on object detection? We introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding boxes and object class confidences through all locations and scales of an image. Our contribution is two-fold. First, we show that a single FCN, if designed and optimized carefully, can detect multiple different objects extremely accurately and efficiently. Second, we show that when incorporating with landmark localization during multi-task learning, DenseBox further improves object detection accuray. We present experim"},"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":"1509.04874","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-16T10:30:37Z","cross_cats_sorted":[],"title_canon_sha256":"48549ce58a968835ff8dca7ad65511304e83c19de857c735bb9a7deb4ad7c6ad","abstract_canon_sha256":"d6e82e3e7e04c197b286002a98ca86a46f7e14141f869b4f9cf5151c5196d322"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:36.625468Z","signature_b64":"2/ABD9k9GfjYPInIU7VWx2obDsf7/2lclc6DrmLs458bTwQkCQwCvO8zsG+N7hx0cyE01skX0D88LGT6kQg1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2a6809a397a404c27f4dc206df035342378574154342585d60e8363f83e386e","last_reissued_at":"2026-05-18T01:32:36.624862Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:36.624862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DenseBox: Unifying Landmark Localization with End to End Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lichao Huang, Yafeng Deng, Yinan Yu, Yi Yang","submitted_at":"2015-09-16T10:30:37Z","abstract_excerpt":"How can a single fully convolutional neural network (FCN) perform on object detection? We introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding boxes and object class confidences through all locations and scales of an image. Our contribution is two-fold. First, we show that a single FCN, if designed and optimized carefully, can detect multiple different objects extremely accurately and efficiently. Second, we show that when incorporating with landmark localization during multi-task learning, DenseBox further improves object detection accuray. We present experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.04874","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":"1509.04874","created_at":"2026-05-18T01:32:36.624951+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.04874v3","created_at":"2026-05-18T01:32:36.624951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.04874","created_at":"2026-05-18T01:32:36.624951+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KTIBGRZPJAE","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KTIBGRZPJAEYJ7U","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KTIBGRZ","created_at":"2026-05-18T12:29:05.191682+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/4KTIBGRZPJAEYJ7U3QQG34BVGQ","json":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ.json","graph_json":"https://pith.science/api/pith-number/4KTIBGRZPJAEYJ7U3QQG34BVGQ/graph.json","events_json":"https://pith.science/api/pith-number/4KTIBGRZPJAEYJ7U3QQG34BVGQ/events.json","paper":"https://pith.science/paper/4KTIBGRZ"},"agent_actions":{"view_html":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ","download_json":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ.json","view_paper":"https://pith.science/paper/4KTIBGRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.04874&json=true","fetch_graph":"https://pith.science/api/pith-number/4KTIBGRZPJAEYJ7U3QQG34BVGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4KTIBGRZPJAEYJ7U3QQG34BVGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ/action/storage_attestation","attest_author":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ/action/author_attestation","sign_citation":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ/action/citation_signature","submit_replication":"https://pith.science/pith/4KTIBGRZPJAEYJ7U3QQG34BVGQ/action/replication_record"}},"created_at":"2026-05-18T01:32:36.624951+00:00","updated_at":"2026-05-18T01:32:36.624951+00:00"}