{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KYGQJYA3PMBXBEQUZ6KKB74ZV7","short_pith_number":"pith:KYGQJYA3","schema_version":"1.0","canonical_sha256":"560d04e01b7b03709214cf94a0ff99afed57f1561491d83eb012c95b7375c7ae","source":{"kind":"arxiv","id":"2505.19503","version":1},"attestation_state":"computed","paper":{"title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deunsol Jung, Minsu Cho, Sanghyun Kim","submitted_at":"2025-05-26T04:31:34Z","abstract_excerpt":"Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework enhancing the locality and interaction awareness of CLIP representations. The locality aw"},"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":"2505.19503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T04:31:34Z","cross_cats_sorted":[],"title_canon_sha256":"8d2c078054b4c37c991566bd3370136cb5ef4953943f89136325b3ee813ab0ea","abstract_canon_sha256":"2ee03c4a1c5abc6e5c7d06a854b0e7a185e6a8e26bda9f72a817c834e83f133d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:31.367266Z","signature_b64":"xu1qE3cHv79CVZD20zzbvw8D9mQNpZk6UpwM0O2jxBv+pINn6Lzd4HmiWGLMZzIX9tiy6ueJPYehJgacugo9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"560d04e01b7b03709214cf94a0ff99afed57f1561491d83eb012c95b7375c7ae","last_reissued_at":"2026-07-05T11:09:31.366746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:31.366746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deunsol Jung, Minsu Cho, Sanghyun Kim","submitted_at":"2025-05-26T04:31:34Z","abstract_excerpt":"Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework enhancing the locality and interaction awareness of CLIP representations. The locality aw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19503","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/2505.19503/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":"2505.19503","created_at":"2026-07-05T11:09:31.366793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19503v1","created_at":"2026-07-05T11:09:31.366793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19503","created_at":"2026-07-05T11:09:31.366793+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYGQJYA3PMBX","created_at":"2026-07-05T11:09:31.366793+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYGQJYA3PMBXBEQU","created_at":"2026-07-05T11:09:31.366793+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYGQJYA3","created_at":"2026-07-05T11:09:31.366793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12923","citing_title":"Pi-HOC: Pairwise 3D Human-Object Contact Estimation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12923","citing_title":"Pi-HOC: Pairwise 3D Human-Object Contact Estimation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7","json":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7.json","graph_json":"https://pith.science/api/pith-number/KYGQJYA3PMBXBEQUZ6KKB74ZV7/graph.json","events_json":"https://pith.science/api/pith-number/KYGQJYA3PMBXBEQUZ6KKB74ZV7/events.json","paper":"https://pith.science/paper/KYGQJYA3"},"agent_actions":{"view_html":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7","download_json":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7.json","view_paper":"https://pith.science/paper/KYGQJYA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19503&json=true","fetch_graph":"https://pith.science/api/pith-number/KYGQJYA3PMBXBEQUZ6KKB74ZV7/graph.json","fetch_events":"https://pith.science/api/pith-number/KYGQJYA3PMBXBEQUZ6KKB74ZV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/action/storage_attestation","attest_author":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/action/author_attestation","sign_citation":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/action/citation_signature","submit_replication":"https://pith.science/pith/KYGQJYA3PMBXBEQUZ6KKB74ZV7/action/replication_record"}},"created_at":"2026-07-05T11:09:31.366793+00:00","updated_at":"2026-07-05T11:09:31.366793+00:00"}