{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:67HRTP7PZ26Q2OFPDVHIDFZRVJ","short_pith_number":"pith:67HRTP7P","schema_version":"1.0","canonical_sha256":"f7cf19bfefcebd0d38af1d4e819731aa665c8fb352a33c46c3f8d5e75480bd02","source":{"kind":"arxiv","id":"1904.04492","version":2},"attestation_state":"computed","paper":{"title":"Convolutional Temporal Attention Model for Video-based Person Re-identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mrigank Rochan, Tanzila Rahman, Yang Wang","submitted_at":"2019-04-09T07:03:53Z","abstract_excerpt":"The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to first extract image features for all frames in the video, then aggregate all the features to form a video-level feature. The video-level features of two videos can then be used to calculate the distance of the two videos. In this paper, we propose a temporal attention approach for aggregating frame-level features into a video-level feature vector for re-identification. Our metho"},"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":"1904.04492","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-09T07:03:53Z","cross_cats_sorted":[],"title_canon_sha256":"bb7657be4db2fd83966f103e3a2f67c48e5a9c37dd76c6a3918f22319818babe","abstract_canon_sha256":"e8113f90a7f63ccd60880db1496565ff97ce80c921b8bf2228ae0c1adb561882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:54.650335Z","signature_b64":"gKmWjlVAW1YjRwBGMBJFD6U04EzE5b5/msgCoezHfkdm8z7FSrrlso+uT83HWKi1W/n1gnSbXhA5spkzWNvpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7cf19bfefcebd0d38af1d4e819731aa665c8fb352a33c46c3f8d5e75480bd02","last_reissued_at":"2026-05-17T23:48:54.649777Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:54.649777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Temporal Attention Model for Video-based Person Re-identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mrigank Rochan, Tanzila Rahman, Yang Wang","submitted_at":"2019-04-09T07:03:53Z","abstract_excerpt":"The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to first extract image features for all frames in the video, then aggregate all the features to form a video-level feature. The video-level features of two videos can then be used to calculate the distance of the two videos. In this paper, we propose a temporal attention approach for aggregating frame-level features into a video-level feature vector for re-identification. Our metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04492","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":"1904.04492","created_at":"2026-05-17T23:48:54.649871+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.04492v2","created_at":"2026-05-17T23:48:54.649871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04492","created_at":"2026-05-17T23:48:54.649871+00:00"},{"alias_kind":"pith_short_12","alias_value":"67HRTP7PZ26Q","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"67HRTP7PZ26Q2OFP","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"67HRTP7P","created_at":"2026-05-18T12:33:10.108867+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/67HRTP7PZ26Q2OFPDVHIDFZRVJ","json":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ.json","graph_json":"https://pith.science/api/pith-number/67HRTP7PZ26Q2OFPDVHIDFZRVJ/graph.json","events_json":"https://pith.science/api/pith-number/67HRTP7PZ26Q2OFPDVHIDFZRVJ/events.json","paper":"https://pith.science/paper/67HRTP7P"},"agent_actions":{"view_html":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ","download_json":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ.json","view_paper":"https://pith.science/paper/67HRTP7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.04492&json=true","fetch_graph":"https://pith.science/api/pith-number/67HRTP7PZ26Q2OFPDVHIDFZRVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/67HRTP7PZ26Q2OFPDVHIDFZRVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ/action/storage_attestation","attest_author":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ/action/author_attestation","sign_citation":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ/action/citation_signature","submit_replication":"https://pith.science/pith/67HRTP7PZ26Q2OFPDVHIDFZRVJ/action/replication_record"}},"created_at":"2026-05-17T23:48:54.649871+00:00","updated_at":"2026-05-17T23:48:54.649871+00:00"}