{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LQ3OIMW4NKZ34GF7Q7STBOWYNC","short_pith_number":"pith:LQ3OIMW4","schema_version":"1.0","canonical_sha256":"5c36e432dc6ab3be18bf87e530bad868be7ba57036935705929b4db4ffae7c29","source":{"kind":"arxiv","id":"1707.06397","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen-Lin Zhang, Chunhua Shen, Jianxin Wu, Xiu-Shen Wei, Zhi-Hua Zhou","submitted_at":"2017-07-20T07:07:33Z","abstract_excerpt":"Reusable model design becomes desirable with the rapid expansion of computer vision and 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 yet effective method, termed Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then "},"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":"1707.06397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-20T07:07:33Z","cross_cats_sorted":[],"title_canon_sha256":"92c00b18ea67ee0697092291a9b4f379edacf1c4e826f1cec681afd6e67a4fde","abstract_canon_sha256":"0ba3aa4f0dad33d13970fac864d4a0a5e7dd878b3276d2d54fb3b7fe1e2cbdbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:53.889557Z","signature_b64":"3pGA0WYpnlWaFVCmRy7lWaapBTh7oyZFBOqx8VKEXo0qRPHm7jOR0LW4bv5Z+ZAuLGbxINOdGOOta0XqttnkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c36e432dc6ab3be18bf87e530bad868be7ba57036935705929b4db4ffae7c29","last_reissued_at":"2026-05-18T00:39:53.888887Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:53.888887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen-Lin Zhang, Chunhua Shen, Jianxin Wu, Xiu-Shen Wei, Zhi-Hua Zhou","submitted_at":"2017-07-20T07:07:33Z","abstract_excerpt":"Reusable model design becomes desirable with the rapid expansion of computer vision and 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 yet effective method, termed Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06397","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":"1707.06397","created_at":"2026-05-18T00:39:53.888996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.06397v1","created_at":"2026-05-18T00:39:53.888996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06397","created_at":"2026-05-18T00:39:53.888996+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ3OIMW4NKZ3","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ3OIMW4NKZ34GF7","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ3OIMW4","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.08051","citing_title":"Self-supervised Training of Proposal-based Segmentation via Background Prediction","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC","json":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC.json","graph_json":"https://pith.science/api/pith-number/LQ3OIMW4NKZ34GF7Q7STBOWYNC/graph.json","events_json":"https://pith.science/api/pith-number/LQ3OIMW4NKZ34GF7Q7STBOWYNC/events.json","paper":"https://pith.science/paper/LQ3OIMW4"},"agent_actions":{"view_html":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC","download_json":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC.json","view_paper":"https://pith.science/paper/LQ3OIMW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.06397&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ3OIMW4NKZ34GF7Q7STBOWYNC/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ3OIMW4NKZ34GF7Q7STBOWYNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC/action/storage_attestation","attest_author":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC/action/author_attestation","sign_citation":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC/action/citation_signature","submit_replication":"https://pith.science/pith/LQ3OIMW4NKZ34GF7Q7STBOWYNC/action/replication_record"}},"created_at":"2026-05-18T00:39:53.888996+00:00","updated_at":"2026-05-18T00:39:53.888996+00:00"}