{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QCP3TZB2OLLR75JBUGT376EDXL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3f7573320ee5ec1ddf47aca10e5fe8176a133db482622b0fee4d6a120d52de7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-07T04:57:45Z","title_canon_sha256":"82c3fd4c5f25faafcbe19022e487030f283bbc2f48cf1c5ee95a3e665fd4efbc"},"schema_version":"1.0","source":{"id":"1708.01988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01988","created_at":"2026-05-18T00:38:32Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01988v1","created_at":"2026-05-18T00:38:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01988","created_at":"2026-05-18T00:38:32Z"},{"alias_kind":"pith_short_12","alias_value":"QCP3TZB2OLLR","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QCP3TZB2OLLR75JB","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QCP3TZB2","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:1533e8af205083bc358c14f16fdd50871a60740fff2a812da5ace0bd59c283ea","target":"graph","created_at":"2026-05-18T00:38:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Textual-visual matching aims at measuring similarities between sentence descriptions and images. Most existing methods tackle this problem without effectively utilizing identity-level annotations. In this paper, we propose an identity-aware two-stage framework for the textual-visual matching problem. Our stage-1 CNN-LSTM network learns to embed cross-modal features with a novel Cross-Modal Cross-Entropy (CMCE) loss. The stage-1 network is able to efficiently screen easy incorrect matchings and also provide initial training point for the stage-2 training. The stage-2 CNN-LSTM network refines th","authors_text":"Hongsheng Li, Shuang Li, Tong Xiao, Wei Yang, Xiaogang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-07T04:57:45Z","title":"Identity-Aware Textual-Visual Matching with Latent Co-attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01988","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d7c94d1a623ed1d834b5bb551a05665ce643bde96630ffe675d5787d8a09d17a","target":"record","created_at":"2026-05-18T00:38:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3f7573320ee5ec1ddf47aca10e5fe8176a133db482622b0fee4d6a120d52de7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-07T04:57:45Z","title_canon_sha256":"82c3fd4c5f25faafcbe19022e487030f283bbc2f48cf1c5ee95a3e665fd4efbc"},"schema_version":"1.0","source":{"id":"1708.01988","kind":"arxiv","version":1}},"canonical_sha256":"809fb9e43a72d71ff521a1a7bff883bad11e9adee1284c1250aea4ac9dab6469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"809fb9e43a72d71ff521a1a7bff883bad11e9adee1284c1250aea4ac9dab6469","first_computed_at":"2026-05-18T00:38:32.616917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:32.616917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2kGii+8foI2O6uVFriHZN2CjQ9oOhjiPtTLNk/kwgkrBGDbIQWSduQAQCFuWhEpVWoVt+Y1lpTRG3NlbuONHBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:32.617450Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.01988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7c94d1a623ed1d834b5bb551a05665ce643bde96630ffe675d5787d8a09d17a","sha256:1533e8af205083bc358c14f16fdd50871a60740fff2a812da5ace0bd59c283ea"],"state_sha256":"6f43558e9692854eecbd7f25698eb487851d90218bdd9d34f35b587e101e960a"}