{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JYUWJ62U5DBRWGLQMBZQH2NNSX","short_pith_number":"pith:JYUWJ62U","schema_version":"1.0","canonical_sha256":"4e2964fb54e8c31b1970607303e9ad95cbaf6faaebda7977f3607a9246152c77","source":{"kind":"arxiv","id":"2005.02472","version":1},"attestation_state":"computed","paper":{"title":"Cross-media Structured Common Space for Multimedia Event Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.MM","authors_text":"Alireza Zareian, Di Lu, Heng Ji, Manling Li, Qi Zeng, Shih-Fu Chang, Spencer Whitehead","submitted_at":"2020-05-05T20:21:53Z","abstract_excerpt":"We introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events and their arguments from multimedia documents. We develop the first benchmark and collect a dataset of 245 multimedia news articles with extensively annotated events and arguments. We propose a novel method, Weakly Aligned Structured Embedding (WASE), that encodes structured representations of semantic information from textual and visual data into a common embedding space. The structures are aligned across modalities by employing a weakly supervised training strategy, which enables exploiting available re"},"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":"2005.02472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2020-05-05T20:21:53Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"551446607c194183799065436ac65f35d029ffd17b7cec00d9c4c80f63658c03","abstract_canon_sha256":"f01df186bc2075ecd56bebd276189e481cc55f8a456d743c30f55195ecf7be92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:52.400190Z","signature_b64":"FJJH57THSEwFOY0aUXjVMkyz4kdlKWjv3MtmJ7EIAO7PuaX6ZjLQr3meJgCpVy9joOT8NiQmBQOMbobY/NRXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e2964fb54e8c31b1970607303e9ad95cbaf6faaebda7977f3607a9246152c77","last_reissued_at":"2026-07-05T01:00:52.399722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:52.399722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-media Structured Common Space for Multimedia Event Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.MM","authors_text":"Alireza Zareian, Di Lu, Heng Ji, Manling Li, Qi Zeng, Shih-Fu Chang, Spencer Whitehead","submitted_at":"2020-05-05T20:21:53Z","abstract_excerpt":"We introduce a new task, MultiMedia Event Extraction (M2E2), which aims to extract events and their arguments from multimedia documents. We develop the first benchmark and collect a dataset of 245 multimedia news articles with extensively annotated events and arguments. We propose a novel method, Weakly Aligned Structured Embedding (WASE), that encodes structured representations of semantic information from textual and visual data into a common embedding space. The structures are aligned across modalities by employing a weakly supervised training strategy, which enables exploiting available re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02472","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/2005.02472/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":"2005.02472","created_at":"2026-07-05T01:00:52.399798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.02472v1","created_at":"2026-07-05T01:00:52.399798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02472","created_at":"2026-07-05T01:00:52.399798+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYUWJ62U5DBR","created_at":"2026-07-05T01:00:52.399798+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYUWJ62U5DBRWGLQ","created_at":"2026-07-05T01:00:52.399798+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYUWJ62U","created_at":"2026-07-05T01:00:52.399798+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/JYUWJ62U5DBRWGLQMBZQH2NNSX","json":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX.json","graph_json":"https://pith.science/api/pith-number/JYUWJ62U5DBRWGLQMBZQH2NNSX/graph.json","events_json":"https://pith.science/api/pith-number/JYUWJ62U5DBRWGLQMBZQH2NNSX/events.json","paper":"https://pith.science/paper/JYUWJ62U"},"agent_actions":{"view_html":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX","download_json":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX.json","view_paper":"https://pith.science/paper/JYUWJ62U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.02472&json=true","fetch_graph":"https://pith.science/api/pith-number/JYUWJ62U5DBRWGLQMBZQH2NNSX/graph.json","fetch_events":"https://pith.science/api/pith-number/JYUWJ62U5DBRWGLQMBZQH2NNSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX/action/storage_attestation","attest_author":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX/action/author_attestation","sign_citation":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX/action/citation_signature","submit_replication":"https://pith.science/pith/JYUWJ62U5DBRWGLQMBZQH2NNSX/action/replication_record"}},"created_at":"2026-07-05T01:00:52.399798+00:00","updated_at":"2026-07-05T01:00:52.399798+00:00"}