{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RD6MEALQ5EAPSFT4FHTL5XMDGU","short_pith_number":"pith:RD6MEALQ","schema_version":"1.0","canonical_sha256":"88fcc20170e900f9167c29e6bedd8335354d0fe4fd28646958943c6ff8760bf0","source":{"kind":"arxiv","id":"1912.07872","version":2},"attestation_state":"computed","paper":{"title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Cui, Renchun You, Shilei Wen, Xiang Long, Yingze Bao, Zhiyao Guo","submitted_at":"2019-12-17T08:41:01Z","abstract_excerpt":"Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our nove"},"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":"1912.07872","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-17T08:41:01Z","cross_cats_sorted":[],"title_canon_sha256":"fe87632258bb311066c1c76375752398e08758c64040775446934743aa90a0ec","abstract_canon_sha256":"e02a2dbc38bc2ad0fb1aafa19ebcb9d4dbba7c80ec2e082de212a1cf47408a42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:53.748180Z","signature_b64":"P868GCgyi9wejNhOGrOg7wkd5IPs3jlf4+FvxhtZ/9sp0klxtXQolIKTcULXk51e4OFc292KpQw7kXsMVZLYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88fcc20170e900f9167c29e6bedd8335354d0fe4fd28646958943c6ff8760bf0","last_reissued_at":"2026-07-05T00:50:53.747820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:53.747820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Cui, Renchun You, Shilei Wen, Xiang Long, Yingze Bao, Zhiyao Guo","submitted_at":"2019-12-17T08:41:01Z","abstract_excerpt":"Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07872","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.07872/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":"1912.07872","created_at":"2026-07-05T00:50:53.747876+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07872v2","created_at":"2026-07-05T00:50:53.747876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07872","created_at":"2026-07-05T00:50:53.747876+00:00"},{"alias_kind":"pith_short_12","alias_value":"RD6MEALQ5EAP","created_at":"2026-07-05T00:50:53.747876+00:00"},{"alias_kind":"pith_short_16","alias_value":"RD6MEALQ5EAPSFT4","created_at":"2026-07-05T00:50:53.747876+00:00"},{"alias_kind":"pith_short_8","alias_value":"RD6MEALQ","created_at":"2026-07-05T00:50:53.747876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06227","citing_title":"Depth Jitter: Seeing through the Depth","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU","json":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU.json","graph_json":"https://pith.science/api/pith-number/RD6MEALQ5EAPSFT4FHTL5XMDGU/graph.json","events_json":"https://pith.science/api/pith-number/RD6MEALQ5EAPSFT4FHTL5XMDGU/events.json","paper":"https://pith.science/paper/RD6MEALQ"},"agent_actions":{"view_html":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU","download_json":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU.json","view_paper":"https://pith.science/paper/RD6MEALQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07872&json=true","fetch_graph":"https://pith.science/api/pith-number/RD6MEALQ5EAPSFT4FHTL5XMDGU/graph.json","fetch_events":"https://pith.science/api/pith-number/RD6MEALQ5EAPSFT4FHTL5XMDGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU/action/storage_attestation","attest_author":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU/action/author_attestation","sign_citation":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU/action/citation_signature","submit_replication":"https://pith.science/pith/RD6MEALQ5EAPSFT4FHTL5XMDGU/action/replication_record"}},"created_at":"2026-07-05T00:50:53.747876+00:00","updated_at":"2026-07-05T00:50:53.747876+00:00"}