{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2GKKQEHLITILQK4XKDUIBUGQ4G","short_pith_number":"pith:2GKKQEHL","schema_version":"1.0","canonical_sha256":"d194a810eb44d0b82b9750e880d0d0e1a93cc2a77edb70c3d5395e1b108c261a","source":{"kind":"arxiv","id":"2507.15542","version":2},"attestation_state":"computed","paper":{"title":"HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Qinqian Lei, Robby T. Tan","submitted_at":"2025-07-21T12:15:27Z","abstract_excerpt":"Zero-shot human-object interaction (HOI) detection remains a challenging task, particularly in generalizing to unseen actions. Existing methods address this challenge by tapping Vision-Language Models (VLMs) to access knowledge beyond the training data. However, they either struggle to distinguish actions involving the same object or demonstrate limited generalization to unseen classes. In this paper, we introduce HOLa (Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation), a novel approach that both enhances generalization to unseen classes and improves action distinction. "},"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":"2507.15542","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-21T12:15:27Z","cross_cats_sorted":[],"title_canon_sha256":"c9f430029120dbed047c9ba4f442e828b28c15776262eaec30177f9b9dafd66c","abstract_canon_sha256":"d2ad4fada983e974afca3ac984e6538842c82be524d7586b6656bce8ae297281"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:26.571072Z","signature_b64":"8LluNaLxF8fy31rPeghxNTFIjB6qP9hUwx2aT9V3EuZTNgfjcCu7/UihjAhlt5GdpqRPBa01jfdJEXa+PpSyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d194a810eb44d0b82b9750e880d0d0e1a93cc2a77edb70c3d5395e1b108c261a","last_reissued_at":"2026-07-05T11:47:26.570589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:26.570589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Qinqian Lei, Robby T. Tan","submitted_at":"2025-07-21T12:15:27Z","abstract_excerpt":"Zero-shot human-object interaction (HOI) detection remains a challenging task, particularly in generalizing to unseen actions. Existing methods address this challenge by tapping Vision-Language Models (VLMs) to access knowledge beyond the training data. However, they either struggle to distinguish actions involving the same object or demonstrate limited generalization to unseen classes. In this paper, we introduce HOLa (Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation), a novel approach that both enhances generalization to unseen classes and improves action distinction. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15542","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/2507.15542/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":"2507.15542","created_at":"2026-07-05T11:47:26.570646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15542v2","created_at":"2026-07-05T11:47:26.570646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15542","created_at":"2026-07-05T11:47:26.570646+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GKKQEHLITIL","created_at":"2026-07-05T11:47:26.570646+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GKKQEHLITILQK4X","created_at":"2026-07-05T11:47:26.570646+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GKKQEHL","created_at":"2026-07-05T11:47:26.570646+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G","json":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G.json","graph_json":"https://pith.science/api/pith-number/2GKKQEHLITILQK4XKDUIBUGQ4G/graph.json","events_json":"https://pith.science/api/pith-number/2GKKQEHLITILQK4XKDUIBUGQ4G/events.json","paper":"https://pith.science/paper/2GKKQEHL"},"agent_actions":{"view_html":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G","download_json":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G.json","view_paper":"https://pith.science/paper/2GKKQEHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15542&json=true","fetch_graph":"https://pith.science/api/pith-number/2GKKQEHLITILQK4XKDUIBUGQ4G/graph.json","fetch_events":"https://pith.science/api/pith-number/2GKKQEHLITILQK4XKDUIBUGQ4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G/action/storage_attestation","attest_author":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G/action/author_attestation","sign_citation":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G/action/citation_signature","submit_replication":"https://pith.science/pith/2GKKQEHLITILQK4XKDUIBUGQ4G/action/replication_record"}},"created_at":"2026-07-05T11:47:26.570646+00:00","updated_at":"2026-07-05T11:47:26.570646+00:00"}