{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DL2WCSZNSFHVG2UX67KF2EWGBR","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":"374381a7ec8505255e08bdcbb235b856e005aa942cf9ae5bd32b88a18798285a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T02:07:23Z","title_canon_sha256":"68b531e1a342c11b55a57227d97d126aefd35b5e2ff0648f34bf6e2abc5a1c9a"},"schema_version":"1.0","source":{"id":"2403.07246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07246","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07246v1","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07246","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_12","alias_value":"DL2WCSZNSFHV","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_16","alias_value":"DL2WCSZNSFHVG2UX","created_at":"2026-07-05T07:55:01Z"},{"alias_kind":"pith_short_8","alias_value":"DL2WCSZN","created_at":"2026-07-05T07:55:01Z"}],"graph_snapshots":[{"event_id":"sha256:6ccfe807a1296868c65480fed2df6d44083581abfa35ace7425c33685f90c396","target":"graph","created_at":"2026-07-05T07:55:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.07246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human-object interaction (HOI) detection aims to locate human-object pairs and identify their interaction categories in images. Most existing methods primarily focus on supervised learning, which relies on extensive manual HOI annotations. In this paper, we propose a novel framework, termed Knowledge Integration to HOI (KI2HOI), that effectively integrates the knowledge of visual-language model to improve zero-shot HOI detection. Specifically, the verb feature learning module is designed based on visual semantics, by employing the verb extraction decoder to convert corresponding verb queries i","authors_text":"Qi Liu, Qiwei Xiong, Weiying Xue, Xiangmin Xu, Xiaofen Xing, Yuxiao Wang, Zhenao Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T02:07:23Z","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07246","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":"sha256:69b1f6335c852d9a00dd21ce275b6ffc31ec0defaec09e7df2edac325385f439","target":"record","created_at":"2026-07-05T07:55:01Z","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":"374381a7ec8505255e08bdcbb235b856e005aa942cf9ae5bd32b88a18798285a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T02:07:23Z","title_canon_sha256":"68b531e1a342c11b55a57227d97d126aefd35b5e2ff0648f34bf6e2abc5a1c9a"},"schema_version":"1.0","source":{"id":"2403.07246","kind":"arxiv","version":1}},"canonical_sha256":"1af5614b2d914f536a97f7d45d12c60c7c452800986df1e69033c0fea36d1c4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1af5614b2d914f536a97f7d45d12c60c7c452800986df1e69033c0fea36d1c4c","first_computed_at":"2026-07-05T07:55:01.142692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:01.142692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QXVklithO/QiLJ2+z43z7WlGQcisXD2IAISNQnl1yHNBGRNxsr0E1kkVcx8+4QhFNiSRvJ024VOJVRWToyEUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:01.143507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69b1f6335c852d9a00dd21ce275b6ffc31ec0defaec09e7df2edac325385f439","sha256:6ccfe807a1296868c65480fed2df6d44083581abfa35ace7425c33685f90c396"],"state_sha256":"a6fb4382a0a88282474592efdc393def827c2cedb7144d4cfd6889a6672649c6"}