{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2FXGODENCZE7VIGLUKKZFYEYHX","short_pith_number":"pith:2FXGODEN","schema_version":"1.0","canonical_sha256":"d16e670c8d1649faa0cba29592e0983dce60ee655d6361ed23df62eb72b88cd3","source":{"kind":"arxiv","id":"1704.05775","version":2},"attestation_state":"computed","paper":{"title":"Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fran\\c{c}ois Fleuret, Pascal Fua, Pierre Baqu\\'e","submitted_at":"2017-04-19T15:30:20Z","abstract_excerpt":"People detection in single 2D images has improved greatly in recent years. However, comparatively little of this progress has percolated into multi-camera multi-people tracking algorithms, whose performance still degrades severely when scenes become very crowded. In this work, we introduce a new architecture that combines Convolutional Neural Nets and Conditional Random Fields to explicitly model those ambiguities. One of its key ingredients are high-order CRF terms that model potential occlusions and give our approach its robustness even when many people are present. Our model is trained end-"},"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":"1704.05775","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-19T15:30:20Z","cross_cats_sorted":[],"title_canon_sha256":"e3842ee36006180bcf838f3158a80753536d85e5a07160ecd188369eca6a5d97","abstract_canon_sha256":"330085fb4a2f6f7f739f2c690420374257a7d8385cd7308ec86423f9634ab1bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:03.880606Z","signature_b64":"HscVW1sdN5Oi+qp/DahGbbtfVKKGNLtmjA81M0SWtHM4a2GbKuv/WxaKTjCrF1qWHCUz7iMA4NeVDzJRB/ELDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d16e670c8d1649faa0cba29592e0983dce60ee655d6361ed23df62eb72b88cd3","last_reissued_at":"2026-05-18T00:46:03.880176Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:03.880176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fran\\c{c}ois Fleuret, Pascal Fua, Pierre Baqu\\'e","submitted_at":"2017-04-19T15:30:20Z","abstract_excerpt":"People detection in single 2D images has improved greatly in recent years. However, comparatively little of this progress has percolated into multi-camera multi-people tracking algorithms, whose performance still degrades severely when scenes become very crowded. In this work, we introduce a new architecture that combines Convolutional Neural Nets and Conditional Random Fields to explicitly model those ambiguities. One of its key ingredients are high-order CRF terms that model potential occlusions and give our approach its robustness even when many people are present. Our model is trained end-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05775","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":""},"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":"1704.05775","created_at":"2026-05-18T00:46:03.880234+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.05775v2","created_at":"2026-05-18T00:46:03.880234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05775","created_at":"2026-05-18T00:46:03.880234+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FXGODENCZE7","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FXGODENCZE7VIGL","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FXGODEN","created_at":"2026-05-18T12:30:55.937587+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/2FXGODENCZE7VIGLUKKZFYEYHX","json":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX.json","graph_json":"https://pith.science/api/pith-number/2FXGODENCZE7VIGLUKKZFYEYHX/graph.json","events_json":"https://pith.science/api/pith-number/2FXGODENCZE7VIGLUKKZFYEYHX/events.json","paper":"https://pith.science/paper/2FXGODEN"},"agent_actions":{"view_html":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX","download_json":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX.json","view_paper":"https://pith.science/paper/2FXGODEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.05775&json=true","fetch_graph":"https://pith.science/api/pith-number/2FXGODENCZE7VIGLUKKZFYEYHX/graph.json","fetch_events":"https://pith.science/api/pith-number/2FXGODENCZE7VIGLUKKZFYEYHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX/action/storage_attestation","attest_author":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX/action/author_attestation","sign_citation":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX/action/citation_signature","submit_replication":"https://pith.science/pith/2FXGODENCZE7VIGLUKKZFYEYHX/action/replication_record"}},"created_at":"2026-05-18T00:46:03.880234+00:00","updated_at":"2026-05-18T00:46:03.880234+00:00"}