{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2M54LPO5DUZSPLH5VGRSTECUNW","short_pith_number":"pith:2M54LPO5","schema_version":"1.0","canonical_sha256":"d33bc5bddd1d3327acfda9a32990546d9b7e448213d5a0858dc3a39dc7155e12","source":{"kind":"arxiv","id":"2401.05676","version":1},"attestation_state":"computed","paper":{"title":"Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honghai Liu, Jiandong Tian, Liangqiong Qu, Weibo Jiang, Weihong Ren, Zhiyong Wang","submitted_at":"2024-01-11T05:38:24Z","abstract_excerpt":"Human-Object Interaction (HOI) detection plays a vital role in scene understanding, which aims to predict the HOI triplet in the form of <human, object, action>. Existing methods mainly extract multi-modal features (e.g., appearance, object semantics, human pose) and then fuse them together to directly predict HOI triplets. However, most of these methods focus on seeking for self-triplet aggregation, but ignore the potential cross-triplet dependencies, resulting in ambiguity of action prediction. In this work, we propose to explore Self- and Cross-Triplet Correlations (SCTC) for HOI detection."},"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":"2401.05676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T05:38:24Z","cross_cats_sorted":[],"title_canon_sha256":"878c6b878f373156d0a1aa308a8b5c3bf31d5bcb8e82ec6594e7f416c19a2bdb","abstract_canon_sha256":"9517eb7a3b68829e9196e192540d2eee88b478716c81bb809cc9c014c97bd6ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:33.741342Z","signature_b64":"c5TcyJzg1KplZH/HfI76QMQbMchyu/OY04F9SuBX8E9cjpQpBHdUKEpZPlqa9IyjdUk2wJk6WLCWA26aOQhYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d33bc5bddd1d3327acfda9a32990546d9b7e448213d5a0858dc3a39dc7155e12","last_reissued_at":"2026-07-05T07:32:33.740799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:33.740799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honghai Liu, Jiandong Tian, Liangqiong Qu, Weibo Jiang, Weihong Ren, Zhiyong Wang","submitted_at":"2024-01-11T05:38:24Z","abstract_excerpt":"Human-Object Interaction (HOI) detection plays a vital role in scene understanding, which aims to predict the HOI triplet in the form of <human, object, action>. Existing methods mainly extract multi-modal features (e.g., appearance, object semantics, human pose) and then fuse them together to directly predict HOI triplets. However, most of these methods focus on seeking for self-triplet aggregation, but ignore the potential cross-triplet dependencies, resulting in ambiguity of action prediction. In this work, we propose to explore Self- and Cross-Triplet Correlations (SCTC) for HOI detection."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05676","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/2401.05676/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":"2401.05676","created_at":"2026-07-05T07:32:33.740862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05676v1","created_at":"2026-07-05T07:32:33.740862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05676","created_at":"2026-07-05T07:32:33.740862+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M54LPO5DUZS","created_at":"2026-07-05T07:32:33.740862+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M54LPO5DUZSPLH5","created_at":"2026-07-05T07:32:33.740862+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M54LPO5","created_at":"2026-07-05T07:32:33.740862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09050","citing_title":"ContextHOI: Spatial Context Learning for Human-Object Interaction Detection","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW","json":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW.json","graph_json":"https://pith.science/api/pith-number/2M54LPO5DUZSPLH5VGRSTECUNW/graph.json","events_json":"https://pith.science/api/pith-number/2M54LPO5DUZSPLH5VGRSTECUNW/events.json","paper":"https://pith.science/paper/2M54LPO5"},"agent_actions":{"view_html":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW","download_json":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW.json","view_paper":"https://pith.science/paper/2M54LPO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05676&json=true","fetch_graph":"https://pith.science/api/pith-number/2M54LPO5DUZSPLH5VGRSTECUNW/graph.json","fetch_events":"https://pith.science/api/pith-number/2M54LPO5DUZSPLH5VGRSTECUNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW/action/storage_attestation","attest_author":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW/action/author_attestation","sign_citation":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW/action/citation_signature","submit_replication":"https://pith.science/pith/2M54LPO5DUZSPLH5VGRSTECUNW/action/replication_record"}},"created_at":"2026-07-05T07:32:33.740862+00:00","updated_at":"2026-07-05T07:32:33.740862+00:00"}