{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5ZPZ6KV26WCDMSZR3QS6RPJVUZ","short_pith_number":"pith:5ZPZ6KV2","schema_version":"1.0","canonical_sha256":"ee5f9f2abaf584364b31dc25e8bd35a64f6a7a40411c7e1dac03e62afb4f4788","source":{"kind":"arxiv","id":"2507.10977","version":1},"attestation_state":"computed","paper":{"title":"Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Junn Yong Loo, KokSheik Wong, Quan Bi Pay, Simon See, Vishnu Monn Baskaran","submitted_at":"2025-07-15T04:44:54Z","abstract_excerpt":"Human-object interaction (HOI) detection is essential for accurately localizing and characterizing interactions between humans and objects, providing a comprehensive understanding of complex visual scenes across various domains. However, existing HOI detectors often struggle to deliver reliable predictions efficiently, relying on resource-intensive training methods and inefficient architectures. To address these challenges, we conceptualize a wavelet attention-like backbone and a novel ray-based encoder architecture tailored for HOI detection. Our wavelet backbone addresses the limitations of "},"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":"2507.10977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T04:44:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f116a31795ff64559eaa0a6f88f89a778203bbb321a40840eec7aa8efd472b36","abstract_canon_sha256":"c417d712254211111a7159e837a5c4c6d0564b221b2544b9ceffb6dccfa38b76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:29.694706Z","signature_b64":"9a1QK4iizKEy9uCaCFreg4exg00STAV+YPE/MZQFGMhwWP9Q8xEIJ9IYA17BN5kGUHPMXcNxMWsDPs7EoQ04Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee5f9f2abaf584364b31dc25e8bd35a64f6a7a40411c7e1dac03e62afb4f4788","last_reissued_at":"2026-07-05T11:37:29.694150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:29.694150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Junn Yong Loo, KokSheik Wong, Quan Bi Pay, Simon See, Vishnu Monn Baskaran","submitted_at":"2025-07-15T04:44:54Z","abstract_excerpt":"Human-object interaction (HOI) detection is essential for accurately localizing and characterizing interactions between humans and objects, providing a comprehensive understanding of complex visual scenes across various domains. However, existing HOI detectors often struggle to deliver reliable predictions efficiently, relying on resource-intensive training methods and inefficient architectures. To address these challenges, we conceptualize a wavelet attention-like backbone and a novel ray-based encoder architecture tailored for HOI detection. Our wavelet backbone addresses the limitations of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10977","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/2507.10977/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":"2507.10977","created_at":"2026-07-05T11:37:29.694212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10977v1","created_at":"2026-07-05T11:37:29.694212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10977","created_at":"2026-07-05T11:37:29.694212+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZPZ6KV26WCD","created_at":"2026-07-05T11:37:29.694212+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZPZ6KV26WCDMSZR","created_at":"2026-07-05T11:37:29.694212+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZPZ6KV2","created_at":"2026-07-05T11:37:29.694212+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/5ZPZ6KV26WCDMSZR3QS6RPJVUZ","json":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ.json","graph_json":"https://pith.science/api/pith-number/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/graph.json","events_json":"https://pith.science/api/pith-number/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/events.json","paper":"https://pith.science/paper/5ZPZ6KV2"},"agent_actions":{"view_html":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ","download_json":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ.json","view_paper":"https://pith.science/paper/5ZPZ6KV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10977&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/action/storage_attestation","attest_author":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/action/author_attestation","sign_citation":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/action/citation_signature","submit_replication":"https://pith.science/pith/5ZPZ6KV26WCDMSZR3QS6RPJVUZ/action/replication_record"}},"created_at":"2026-07-05T11:37:29.694212+00:00","updated_at":"2026-07-05T11:37:29.694212+00:00"}