{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NRN46TGMKVELBBUQPEPDB23REO","short_pith_number":"pith:NRN46TGM","schema_version":"1.0","canonical_sha256":"6c5bcf4ccc5548b08690791e30eb71239816b8bb32e99e28f8bcacd609730d98","source":{"kind":"arxiv","id":"2507.06510","version":1},"attestation_state":"computed","paper":{"title":"Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Sun, Changxing Ding, Shaoli Huang, Xiangmin Xu, Yupeng Hu","submitted_at":"2025-07-09T03:16:39Z","abstract_excerpt":"Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-defined in the training set. Existing approaches typically rely on output features generated by large Vision-Language Models (VLMs) to enhance the generalization ability of interaction representations. However, the visual features produced by VLMs are holistic and coarse-grained, which contradicts the nature of detection tasks. To address this issue, we propose a novel Bilateral Collaboration framework for open vocab"},"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":"2507.06510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T03:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"5207c01baee22d9d3af25009a9cefc775a057f634ea758178a706474462bfdf1","abstract_canon_sha256":"adfc47429c72f3f0fa29a42b50900022ef2e01d9dc36b446c2dd7ae6db70726d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:17.446764Z","signature_b64":"Y5AMAef6TV5dH2GyIhUSSnZS1S6D5PKTY9ha3KLSN/doeQ1Cce08E5peqX8sJ0sR38kqLEC5b9EvrUnlEJaxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c5bcf4ccc5548b08690791e30eb71239816b8bb32e99e28f8bcacd609730d98","last_reissued_at":"2026-07-05T11:34:17.446335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:17.446335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Sun, Changxing Ding, Shaoli Huang, Xiangmin Xu, Yupeng Hu","submitted_at":"2025-07-09T03:16:39Z","abstract_excerpt":"Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-defined in the training set. Existing approaches typically rely on output features generated by large Vision-Language Models (VLMs) to enhance the generalization ability of interaction representations. However, the visual features produced by VLMs are holistic and coarse-grained, which contradicts the nature of detection tasks. To address this issue, we propose a novel Bilateral Collaboration framework for open vocab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06510","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/2507.06510/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":"2507.06510","created_at":"2026-07-05T11:34:17.446395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06510v1","created_at":"2026-07-05T11:34:17.446395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06510","created_at":"2026-07-05T11:34:17.446395+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRN46TGMKVEL","created_at":"2026-07-05T11:34:17.446395+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRN46TGMKVELBBUQ","created_at":"2026-07-05T11:34:17.446395+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRN46TGM","created_at":"2026-07-05T11:34:17.446395+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/NRN46TGMKVELBBUQPEPDB23REO","json":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO.json","graph_json":"https://pith.science/api/pith-number/NRN46TGMKVELBBUQPEPDB23REO/graph.json","events_json":"https://pith.science/api/pith-number/NRN46TGMKVELBBUQPEPDB23REO/events.json","paper":"https://pith.science/paper/NRN46TGM"},"agent_actions":{"view_html":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO","download_json":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO.json","view_paper":"https://pith.science/paper/NRN46TGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06510&json=true","fetch_graph":"https://pith.science/api/pith-number/NRN46TGMKVELBBUQPEPDB23REO/graph.json","fetch_events":"https://pith.science/api/pith-number/NRN46TGMKVELBBUQPEPDB23REO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/action/storage_attestation","attest_author":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/action/author_attestation","sign_citation":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/action/citation_signature","submit_replication":"https://pith.science/pith/NRN46TGMKVELBBUQPEPDB23REO/action/replication_record"}},"created_at":"2026-07-05T11:34:17.446395+00:00","updated_at":"2026-07-05T11:34:17.446395+00:00"}