{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:M5NHT5SFPDTT734B3SPCYB5KZC","short_pith_number":"pith:M5NHT5SF","schema_version":"1.0","canonical_sha256":"675a79f64578e73fef81dc9e2c07aac88f5984c2df6e4c36e5e78955a5d0f862","source":{"kind":"arxiv","id":"1906.03857","version":2},"attestation_state":"computed","paper":{"title":"UniDual: A Unified Model for Image and Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Du Tran, Lorenzo Torresani, Yufei Wang","submitted_at":"2019-06-10T09:15:52Z","abstract_excerpt":"Although a video is effectively a sequence of images, visual perception systems typically model images and videos separately, thus failing to exploit the correlation and the synergy provided by these two media. While a few prior research efforts have explored the benefits of leveraging still-image datasets for video analysis, or vice-versa, most of these attempts have been limited to pretraining a model on one type of visual modality and then adapting it via finetuning on the other modality. In contrast, in this paper we introduce a framework that enables joint training of a unified model on m"},"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":"1906.03857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-10T09:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"aa5655a528c9725c848ee8d111ecd0d4a18788700615364688c87d9fb99cac42","abstract_canon_sha256":"637a453e1729e858e24576ae9f7c22ee32f26c85a49188b4be51a1a29f66f4c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.446745Z","signature_b64":"vL577t1HNE+FX97Lg0y4IaoVi/odrVwe7UeBj1k98rHhF0n6WgidCIqSsebdkl+GM7UllrfjZEyws7H9yy8BAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675a79f64578e73fef81dc9e2c07aac88f5984c2df6e4c36e5e78955a5d0f862","last_reissued_at":"2026-05-17T23:43:32.446312Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.446312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniDual: A Unified Model for Image and Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Du Tran, Lorenzo Torresani, Yufei Wang","submitted_at":"2019-06-10T09:15:52Z","abstract_excerpt":"Although a video is effectively a sequence of images, visual perception systems typically model images and videos separately, thus failing to exploit the correlation and the synergy provided by these two media. While a few prior research efforts have explored the benefits of leveraging still-image datasets for video analysis, or vice-versa, most of these attempts have been limited to pretraining a model on one type of visual modality and then adapting it via finetuning on the other modality. In contrast, in this paper we introduce a framework that enables joint training of a unified model on m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03857","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1906.03857","created_at":"2026-05-17T23:43:32.446387+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03857v2","created_at":"2026-05-17T23:43:32.446387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03857","created_at":"2026-05-17T23:43:32.446387+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5NHT5SFPDTT","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5NHT5SFPDTT734B","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5NHT5SF","created_at":"2026-05-18T12:33:21.387695+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/M5NHT5SFPDTT734B3SPCYB5KZC","json":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC.json","graph_json":"https://pith.science/api/pith-number/M5NHT5SFPDTT734B3SPCYB5KZC/graph.json","events_json":"https://pith.science/api/pith-number/M5NHT5SFPDTT734B3SPCYB5KZC/events.json","paper":"https://pith.science/paper/M5NHT5SF"},"agent_actions":{"view_html":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC","download_json":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC.json","view_paper":"https://pith.science/paper/M5NHT5SF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03857&json=true","fetch_graph":"https://pith.science/api/pith-number/M5NHT5SFPDTT734B3SPCYB5KZC/graph.json","fetch_events":"https://pith.science/api/pith-number/M5NHT5SFPDTT734B3SPCYB5KZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/action/storage_attestation","attest_author":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/action/author_attestation","sign_citation":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/action/citation_signature","submit_replication":"https://pith.science/pith/M5NHT5SFPDTT734B3SPCYB5KZC/action/replication_record"}},"created_at":"2026-05-17T23:43:32.446387+00:00","updated_at":"2026-05-17T23:43:32.446387+00:00"}