{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7ODFCL3Q2MCHCCKS4QZUIUNN5S","short_pith_number":"pith:7ODFCL3Q","schema_version":"1.0","canonical_sha256":"fb86512f70d304710952e4334451adec9008dbdc42e50090b91c0713d96fa84b","source":{"kind":"arxiv","id":"1805.08587","version":5},"attestation_state":"computed","paper":{"title":"Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Jianru Xue, Jihua Zhu, Jin Ma, Shanmin Pang, Vicente Ordonez","submitted_at":"2018-05-22T14:06:28Z","abstract_excerpt":"Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address deep convolutional feature aggregation and image re-ranking by simulating the dynamics of heat diffusion. A distinctive problem in image retrieval is that repetitive or \\emph{bursty} features tend to dominate final image representations, resulting in representations less distinguishable. We show that by considering each deep feature as a heat source, our unsupervised aggregation method is able to avoid over-representat"},"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":"1805.08587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-05-22T14:06:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"84d23f61e306c333c0cb4a31160a057fbff992fa13b402684b31933ddd5f52d2","abstract_canon_sha256":"c344c358e8dd5dbff993be335f22c6a5433096b9d10f59aa9070c5c1255d1960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:48.787436Z","signature_b64":"/p1uYvjil9PGfgfjaRi1B6TGJKnK3obp+S04zbXy9awHB9F1c8miac8utSQBvx2K9+WkAJvUgdz52zVnyQj6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb86512f70d304710952e4334451adec9008dbdc42e50090b91c0713d96fa84b","last_reissued_at":"2026-05-18T00:03:48.786930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:48.786930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Jianru Xue, Jihua Zhu, Jin Ma, Shanmin Pang, Vicente Ordonez","submitted_at":"2018-05-22T14:06:28Z","abstract_excerpt":"Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address deep convolutional feature aggregation and image re-ranking by simulating the dynamics of heat diffusion. A distinctive problem in image retrieval is that repetitive or \\emph{bursty} features tend to dominate final image representations, resulting in representations less distinguishable. We show that by considering each deep feature as a heat source, our unsupervised aggregation method is able to avoid over-representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08587","kind":"arxiv","version":5},"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":"1805.08587","created_at":"2026-05-18T00:03:48.787010+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08587v5","created_at":"2026-05-18T00:03:48.787010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08587","created_at":"2026-05-18T00:03:48.787010+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ODFCL3Q2MCH","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ODFCL3Q2MCHCCKS","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ODFCL3Q","created_at":"2026-05-18T12:32:11.075285+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/7ODFCL3Q2MCHCCKS4QZUIUNN5S","json":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S.json","graph_json":"https://pith.science/api/pith-number/7ODFCL3Q2MCHCCKS4QZUIUNN5S/graph.json","events_json":"https://pith.science/api/pith-number/7ODFCL3Q2MCHCCKS4QZUIUNN5S/events.json","paper":"https://pith.science/paper/7ODFCL3Q"},"agent_actions":{"view_html":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S","download_json":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S.json","view_paper":"https://pith.science/paper/7ODFCL3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08587&json=true","fetch_graph":"https://pith.science/api/pith-number/7ODFCL3Q2MCHCCKS4QZUIUNN5S/graph.json","fetch_events":"https://pith.science/api/pith-number/7ODFCL3Q2MCHCCKS4QZUIUNN5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S/action/storage_attestation","attest_author":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S/action/author_attestation","sign_citation":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S/action/citation_signature","submit_replication":"https://pith.science/pith/7ODFCL3Q2MCHCCKS4QZUIUNN5S/action/replication_record"}},"created_at":"2026-05-18T00:03:48.787010+00:00","updated_at":"2026-05-18T00:03:48.787010+00:00"}