{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:23DIRO6NZ73U3FTIFA2PEELA7I","short_pith_number":"pith:23DIRO6N","schema_version":"1.0","canonical_sha256":"d6c688bbcdcff74d96682834f21160fa0856ce36b4bbf47e950125682db1b80e","source":{"kind":"arxiv","id":"2406.10079","version":3},"attestation_state":"computed","paper":{"title":"Localizing Events in Videos with Multimodal Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, Gengyuan Zhang, Jialu Ma, Jindong Gu, Mang Ling Ada Fok, Philip Torr, Volker Tresp, Yan Xia","submitted_at":"2024-06-14T14:35:58Z","abstract_excerpt":"Localizing events in videos based on semantic queries is a pivotal task in video understanding, with the growing significance of user-oriented applications like video search. Yet, current research predominantly relies on natural language queries (NLQs), overlooking the potential of using multimodal queries (MQs) that integrate images to more flexibly represent semantic queries -- especially when it is difficult to express non-verbal or unfamiliar concepts in words. To bridge this gap, we introduce ICQ, a new benchmark designed for localizing events in videos with MQs, alongside an evaluation d"},"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":"2406.10079","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T14:35:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0aa193936154197300b4917acfe8338e1f505788d70ed97ca3da253782316614","abstract_canon_sha256":"53557051126be6e096c51326a1b503392db9257b62706e5e58ca900e73e53999"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:27.212015Z","signature_b64":"UsKawqQ9wKcaA6AwRr3XZa17gZhJF0rbnu6vwPETVihGVGIOjXhPbfe/Os6DxFjnXjmd1GAPrY8cuMcL3rUnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6c688bbcdcff74d96682834f21160fa0856ce36b4bbf47e950125682db1b80e","last_reissued_at":"2026-07-05T09:38:27.211586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:27.211586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Localizing Events in Videos with Multimodal Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, Gengyuan Zhang, Jialu Ma, Jindong Gu, Mang Ling Ada Fok, Philip Torr, Volker Tresp, Yan Xia","submitted_at":"2024-06-14T14:35:58Z","abstract_excerpt":"Localizing events in videos based on semantic queries is a pivotal task in video understanding, with the growing significance of user-oriented applications like video search. Yet, current research predominantly relies on natural language queries (NLQs), overlooking the potential of using multimodal queries (MQs) that integrate images to more flexibly represent semantic queries -- especially when it is difficult to express non-verbal or unfamiliar concepts in words. To bridge this gap, we introduce ICQ, a new benchmark designed for localizing events in videos with MQs, alongside an evaluation d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10079","kind":"arxiv","version":3},"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/2406.10079/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":"2406.10079","created_at":"2026-07-05T09:38:27.211642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10079v3","created_at":"2026-07-05T09:38:27.211642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10079","created_at":"2026-07-05T09:38:27.211642+00:00"},{"alias_kind":"pith_short_12","alias_value":"23DIRO6NZ73U","created_at":"2026-07-05T09:38:27.211642+00:00"},{"alias_kind":"pith_short_16","alias_value":"23DIRO6NZ73U3FTI","created_at":"2026-07-05T09:38:27.211642+00:00"},{"alias_kind":"pith_short_8","alias_value":"23DIRO6N","created_at":"2026-07-05T09:38:27.211642+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/23DIRO6NZ73U3FTIFA2PEELA7I","json":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I.json","graph_json":"https://pith.science/api/pith-number/23DIRO6NZ73U3FTIFA2PEELA7I/graph.json","events_json":"https://pith.science/api/pith-number/23DIRO6NZ73U3FTIFA2PEELA7I/events.json","paper":"https://pith.science/paper/23DIRO6N"},"agent_actions":{"view_html":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I","download_json":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I.json","view_paper":"https://pith.science/paper/23DIRO6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10079&json=true","fetch_graph":"https://pith.science/api/pith-number/23DIRO6NZ73U3FTIFA2PEELA7I/graph.json","fetch_events":"https://pith.science/api/pith-number/23DIRO6NZ73U3FTIFA2PEELA7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I/action/storage_attestation","attest_author":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I/action/author_attestation","sign_citation":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I/action/citation_signature","submit_replication":"https://pith.science/pith/23DIRO6NZ73U3FTIFA2PEELA7I/action/replication_record"}},"created_at":"2026-07-05T09:38:27.211642+00:00","updated_at":"2026-07-05T09:38:27.211642+00:00"}