{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7UIUPWRF3TPHOXAZQNZRJLS64G","short_pith_number":"pith:7UIUPWRF","schema_version":"1.0","canonical_sha256":"fd1147da25dcde775c19837314ae5ee1ab6c28d013d9899a9bc6c22e5e7e9374","source":{"kind":"arxiv","id":"1705.02758","version":1},"attestation_state":"computed","paper":{"title":"Deep Descriptor Transforming for Image Co-Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen-Lin Zhang, Chen-Wei Xie, Chunhua Shen, Jianxin Wu, Xiu-Shen Wei, Yao Li, Zhi-Hua Zhou","submitted_at":"2017-05-08T06:52:44Z","abstract_excerpt":"Reusable model design becomes desirable with the rapid expansion of machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the image co-localization problem. We propose a simple but effective method, named Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the categor"},"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":"1705.02758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-08T06:52:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"efb8fe2efb2c8189dcf6d7b65e0b20522b6a741ddab73d0eb8bc8b2dcd0d5078","abstract_canon_sha256":"fc4c2915108f9efad58dc7ce67a5556bf0d9cfe489c3eb5ef8d8b07f1a0dd2d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:34.896011Z","signature_b64":"Sd8cnRwy5aUVXyf1cZHzMoD71saj37RAbQzqZXgDnUZH1FFJiLfPYMG0WsICsUTrB/nsPOaiTrzqB/vUjiR7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1147da25dcde775c19837314ae5ee1ab6c28d013d9899a9bc6c22e5e7e9374","last_reissued_at":"2026-05-18T00:43:34.895484Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:34.895484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Descriptor Transforming for Image Co-Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen-Lin Zhang, Chen-Wei Xie, Chunhua Shen, Jianxin Wu, Xiu-Shen Wei, Yao Li, Zhi-Hua Zhou","submitted_at":"2017-05-08T06:52:44Z","abstract_excerpt":"Reusable model design becomes desirable with the rapid expansion of machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the image co-localization problem. We propose a simple but effective method, named Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the categor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02758","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":"1705.02758","created_at":"2026-05-18T00:43:34.895586+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02758v1","created_at":"2026-05-18T00:43:34.895586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02758","created_at":"2026-05-18T00:43:34.895586+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UIUPWRF3TPH","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UIUPWRF3TPHOXAZ","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UIUPWRF","created_at":"2026-05-18T12:31:05.417338+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/7UIUPWRF3TPHOXAZQNZRJLS64G","json":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G.json","graph_json":"https://pith.science/api/pith-number/7UIUPWRF3TPHOXAZQNZRJLS64G/graph.json","events_json":"https://pith.science/api/pith-number/7UIUPWRF3TPHOXAZQNZRJLS64G/events.json","paper":"https://pith.science/paper/7UIUPWRF"},"agent_actions":{"view_html":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G","download_json":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G.json","view_paper":"https://pith.science/paper/7UIUPWRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02758&json=true","fetch_graph":"https://pith.science/api/pith-number/7UIUPWRF3TPHOXAZQNZRJLS64G/graph.json","fetch_events":"https://pith.science/api/pith-number/7UIUPWRF3TPHOXAZQNZRJLS64G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G/action/storage_attestation","attest_author":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G/action/author_attestation","sign_citation":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G/action/citation_signature","submit_replication":"https://pith.science/pith/7UIUPWRF3TPHOXAZQNZRJLS64G/action/replication_record"}},"created_at":"2026-05-18T00:43:34.895586+00:00","updated_at":"2026-05-18T00:43:34.895586+00:00"}