{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U3PDVPYCTKAWWLWAB5GHKLGXHI","short_pith_number":"pith:U3PDVPYC","schema_version":"1.0","canonical_sha256":"a6de3abf029a816b2ec00f4c752cd73a08f5c3e9baa010139b33fa0faa4fcecd","source":{"kind":"arxiv","id":"1908.05860","version":1},"attestation_state":"computed","paper":{"title":"Learning Deep Representations by Mutual Information for Person Re-identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyue Chen, Jianjun Wu, Peng Chen, Pengfei Wu, Tong Jia","submitted_at":"2019-08-16T06:15:30Z","abstract_excerpt":"Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods. However, these works concentrate on the similarity between encoder output and ground-truth, ignoring the correlation between input and encoder output, which affects the performance of identifying different pedestrians. To address this limitation, We design a Deep InfoMax (DIM) network to maximize the mutual information (MI) between the input image and encoder output, which doesn't need any auxiliary labels. "},"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":"1908.05860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-16T06:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"e7c9b63df213b846cd5c8360c44ad6ae036675924ac8a4914aeeeee2378498bb","abstract_canon_sha256":"3cf337d375e2ae27674fb0b93616253c08085293a047493aadbe387f837f7c4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:57:53.811504Z","signature_b64":"0/PM5X1HP5Gx4X9pmi5hhnJ/Qdghbq6M4Nap2MPL1D+08ngSYWsIfZcVQPwiCX23CgWuUehs1yx6swOGljWQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6de3abf029a816b2ec00f4c752cd73a08f5c3e9baa010139b33fa0faa4fcecd","last_reissued_at":"2026-07-04T23:57:53.811099Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:57:53.811099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep Representations by Mutual Information for Person Re-identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyue Chen, Jianjun Wu, Peng Chen, Pengfei Wu, Tong Jia","submitted_at":"2019-08-16T06:15:30Z","abstract_excerpt":"Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods. However, these works concentrate on the similarity between encoder output and ground-truth, ignoring the correlation between input and encoder output, which affects the performance of identifying different pedestrians. To address this limitation, We design a Deep InfoMax (DIM) network to maximize the mutual information (MI) between the input image and encoder output, which doesn't need any auxiliary labels. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05860","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.05860/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1908.05860","created_at":"2026-07-04T23:57:53.811159+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05860v1","created_at":"2026-07-04T23:57:53.811159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05860","created_at":"2026-07-04T23:57:53.811159+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3PDVPYCTKAW","created_at":"2026-07-04T23:57:53.811159+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3PDVPYCTKAWWLWA","created_at":"2026-07-04T23:57:53.811159+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3PDVPYC","created_at":"2026-07-04T23:57:53.811159+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/U3PDVPYCTKAWWLWAB5GHKLGXHI","json":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI.json","graph_json":"https://pith.science/api/pith-number/U3PDVPYCTKAWWLWAB5GHKLGXHI/graph.json","events_json":"https://pith.science/api/pith-number/U3PDVPYCTKAWWLWAB5GHKLGXHI/events.json","paper":"https://pith.science/paper/U3PDVPYC"},"agent_actions":{"view_html":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI","download_json":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI.json","view_paper":"https://pith.science/paper/U3PDVPYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05860&json=true","fetch_graph":"https://pith.science/api/pith-number/U3PDVPYCTKAWWLWAB5GHKLGXHI/graph.json","fetch_events":"https://pith.science/api/pith-number/U3PDVPYCTKAWWLWAB5GHKLGXHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI/action/storage_attestation","attest_author":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI/action/author_attestation","sign_citation":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI/action/citation_signature","submit_replication":"https://pith.science/pith/U3PDVPYCTKAWWLWAB5GHKLGXHI/action/replication_record"}},"created_at":"2026-07-04T23:57:53.811159+00:00","updated_at":"2026-07-04T23:57:53.811159+00:00"}