{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CXOBJE362M2EBMMWDYUBPR6VBB","short_pith_number":"pith:CXOBJE36","schema_version":"1.0","canonical_sha256":"15dc14937ed33440b1961e2817c7d50870f9c8d7bf6c315cc2149bef4cb5fc9f","source":{"kind":"arxiv","id":"2304.04688","version":4},"attestation_state":"computed","paper":{"title":"Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gueter Josmy Faure, Jheng-Hsien Yeh, Min-Hung Chen, Shang-Hong Lai, Wei-Jhe Huang","submitted_at":"2023-04-10T16:08:59Z","abstract_excerpt":"The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning, which requires a large amount of training data, making it very difficult to achieve zero-shot learning. In this paper, we propose to utilize a pre-trained visual-language model to extract the representative image and text features, and model the relationship between these features through different interaction modules to obtain the interaction feature. In additi"},"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":"2304.04688","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T16:08:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"395ed7091d71b0f2e8bf736940ab285c9bf732b305ea30a72531cd45677b7b58","abstract_canon_sha256":"e3125b0b05a6cbcf703ac01348c489d56a7be3a45297267741e7a2d592ac2d44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:22.178440Z","signature_b64":"RoVhvoR0okQAycYKUErThywglJqQMk7I1Yc9Kqrge03De+qM3gVk6KDr4gJwQDJxK7tyqq3XV402QrQlCaNRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15dc14937ed33440b1961e2817c7d50870f9c8d7bf6c315cc2149bef4cb5fc9f","last_reissued_at":"2026-07-05T06:52:22.178027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:22.178027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gueter Josmy Faure, Jheng-Hsien Yeh, Min-Hung Chen, Shang-Hong Lai, Wei-Jhe Huang","submitted_at":"2023-04-10T16:08:59Z","abstract_excerpt":"The goal of spatial-temporal action detection is to determine the time and place where each person's action occurs in a video and classify the corresponding action category. Most of the existing methods adopt fully-supervised learning, which requires a large amount of training data, making it very difficult to achieve zero-shot learning. In this paper, we propose to utilize a pre-trained visual-language model to extract the representative image and text features, and model the relationship between these features through different interaction modules to obtain the interaction feature. In additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04688","kind":"arxiv","version":4},"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/2304.04688/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":"2304.04688","created_at":"2026-07-05T06:52:22.178088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04688v4","created_at":"2026-07-05T06:52:22.178088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04688","created_at":"2026-07-05T06:52:22.178088+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXOBJE362M2E","created_at":"2026-07-05T06:52:22.178088+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXOBJE362M2EBMMW","created_at":"2026-07-05T06:52:22.178088+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXOBJE36","created_at":"2026-07-05T06:52:22.178088+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/CXOBJE362M2EBMMWDYUBPR6VBB","json":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB.json","graph_json":"https://pith.science/api/pith-number/CXOBJE362M2EBMMWDYUBPR6VBB/graph.json","events_json":"https://pith.science/api/pith-number/CXOBJE362M2EBMMWDYUBPR6VBB/events.json","paper":"https://pith.science/paper/CXOBJE36"},"agent_actions":{"view_html":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB","download_json":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB.json","view_paper":"https://pith.science/paper/CXOBJE36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04688&json=true","fetch_graph":"https://pith.science/api/pith-number/CXOBJE362M2EBMMWDYUBPR6VBB/graph.json","fetch_events":"https://pith.science/api/pith-number/CXOBJE362M2EBMMWDYUBPR6VBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/action/storage_attestation","attest_author":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/action/author_attestation","sign_citation":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/action/citation_signature","submit_replication":"https://pith.science/pith/CXOBJE362M2EBMMWDYUBPR6VBB/action/replication_record"}},"created_at":"2026-07-05T06:52:22.178088+00:00","updated_at":"2026-07-05T06:52:22.178088+00:00"}