{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PFMAONOMUTJVJ4MXHWIPDV3HOE","short_pith_number":"pith:PFMAONOM","schema_version":"1.0","canonical_sha256":"79580735cca4d354f1973d90f1d767712652f4df0eb5af83e27623cc5dee8955","source":{"kind":"arxiv","id":"2003.03501","version":3},"attestation_state":"computed","paper":{"title":"Cross-modal Learning for Multi-modal Video Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chul Lee, Palash Goyal, Saurabh Sahu, Shalini Ghosh","submitted_at":"2020-03-07T03:21:15Z","abstract_excerpt":"Multi-modal machine learning (ML) models can process data in multiple modalities (e.g., video, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding, activity recognition). In this paper, we focus on the problem of video categorization using a multi-modal ML technique. In particular, we have developed a novel multi-modal ML approach that we call \"cross-modal learning\", where one modality influences another but only when there is correlation between the modalities -- for that, we first train a correlation tower that guides t"},"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":"2003.03501","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-07T03:21:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d39fbad5d678fc8a79c679a11247a4f98f4ab4128b755aed1e1d0b437f552510","abstract_canon_sha256":"be14dbf141c8e3b74116af8136c03d9f91a47211f8afcb2795ff92b3c1d0d8a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:28.518901Z","signature_b64":"d6NTVIsywfVZ2DA4r5TgjpP7o+IjXP5GRNC3WFLX4ZDaaCKWzBSw1KURDUWIgMpNG5R3W/2pgA0v30HX6LNKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79580735cca4d354f1973d90f1d767712652f4df0eb5af83e27623cc5dee8955","last_reissued_at":"2026-07-05T01:08:28.518338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:28.518338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-modal Learning for Multi-modal Video Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chul Lee, Palash Goyal, Saurabh Sahu, Shalini Ghosh","submitted_at":"2020-03-07T03:21:15Z","abstract_excerpt":"Multi-modal machine learning (ML) models can process data in multiple modalities (e.g., video, audio, text) and are useful for video content analysis in a variety of problems (e.g., object detection, scene understanding, activity recognition). In this paper, we focus on the problem of video categorization using a multi-modal ML technique. In particular, we have developed a novel multi-modal ML approach that we call \"cross-modal learning\", where one modality influences another but only when there is correlation between the modalities -- for that, we first train a correlation tower that guides t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03501","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/2003.03501/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":"2003.03501","created_at":"2026-07-05T01:08:28.518428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.03501v3","created_at":"2026-07-05T01:08:28.518428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03501","created_at":"2026-07-05T01:08:28.518428+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFMAONOMUTJV","created_at":"2026-07-05T01:08:28.518428+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFMAONOMUTJVJ4MX","created_at":"2026-07-05T01:08:28.518428+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFMAONOM","created_at":"2026-07-05T01:08:28.518428+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/PFMAONOMUTJVJ4MXHWIPDV3HOE","json":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE.json","graph_json":"https://pith.science/api/pith-number/PFMAONOMUTJVJ4MXHWIPDV3HOE/graph.json","events_json":"https://pith.science/api/pith-number/PFMAONOMUTJVJ4MXHWIPDV3HOE/events.json","paper":"https://pith.science/paper/PFMAONOM"},"agent_actions":{"view_html":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE","download_json":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE.json","view_paper":"https://pith.science/paper/PFMAONOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.03501&json=true","fetch_graph":"https://pith.science/api/pith-number/PFMAONOMUTJVJ4MXHWIPDV3HOE/graph.json","fetch_events":"https://pith.science/api/pith-number/PFMAONOMUTJVJ4MXHWIPDV3HOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/action/storage_attestation","attest_author":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/action/author_attestation","sign_citation":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/action/citation_signature","submit_replication":"https://pith.science/pith/PFMAONOMUTJVJ4MXHWIPDV3HOE/action/replication_record"}},"created_at":"2026-07-05T01:08:28.518428+00:00","updated_at":"2026-07-05T01:08:28.518428+00:00"}