{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZNYMSRP5WS64BNR7VX3STD5UUD","short_pith_number":"pith:ZNYMSRP5","schema_version":"1.0","canonical_sha256":"cb70c945fdb4bdc0b63fadf7298fb4a0d35099d41417ea6846a50b62dcdd7b1e","source":{"kind":"arxiv","id":"2504.11732","version":1},"attestation_state":"computed","paper":{"title":"EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoqi Pei, Guo Chen, Jilan Xu, Junlin Hou, Qingqiu Li, Rui Feng, Weidi Xie, Yifei Huang, Yuejie Zhang","submitted_at":"2025-04-16T03:12:39Z","abstract_excerpt":"Generating videos in the first-person perspective has broad application prospects in the field of augmented reality and embodied intelligence. In this work, we explore the cross-view video prediction task, where given an exo-centric video, the first frame of the corresponding ego-centric video, and textual instructions, the goal is to generate futur frames of the ego-centric video. Inspired by the notion that hand-object interactions (HOI) in ego-centric videos represent the primary intentions and actions of the current actor, we present EgoExo-Gen that explicitly models the hand-object dynami"},"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":"2504.11732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T03:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"30afc46f0ed593366887a57e739d98e7bf7dedb40d81c882f959a86141c6c700","abstract_canon_sha256":"8045dc6c80ee4a957b1404bdcbadea325c985315f4fea626e3ba0e6d1f490949"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:56.613336Z","signature_b64":"nrPZkHyeM+brvPXuc460BqwbJ4wMXxbAmG0yRYHPBgD2eXhgiqYF24ujxcyYM0JNccKO9NZVlpm26j0mOBldDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb70c945fdb4bdc0b63fadf7298fb4a0d35099d41417ea6846a50b62dcdd7b1e","last_reissued_at":"2026-07-05T10:49:56.612923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:56.612923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoqi Pei, Guo Chen, Jilan Xu, Junlin Hou, Qingqiu Li, Rui Feng, Weidi Xie, Yifei Huang, Yuejie Zhang","submitted_at":"2025-04-16T03:12:39Z","abstract_excerpt":"Generating videos in the first-person perspective has broad application prospects in the field of augmented reality and embodied intelligence. In this work, we explore the cross-view video prediction task, where given an exo-centric video, the first frame of the corresponding ego-centric video, and textual instructions, the goal is to generate futur frames of the ego-centric video. Inspired by the notion that hand-object interactions (HOI) in ego-centric videos represent the primary intentions and actions of the current actor, we present EgoExo-Gen that explicitly models the hand-object dynami"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11732","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/2504.11732/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":"2504.11732","created_at":"2026-07-05T10:49:56.612980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11732v1","created_at":"2026-07-05T10:49:56.612980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11732","created_at":"2026-07-05T10:49:56.612980+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNYMSRP5WS64","created_at":"2026-07-05T10:49:56.612980+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNYMSRP5WS64BNR7","created_at":"2026-07-05T10:49:56.612980+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNYMSRP5","created_at":"2026-07-05T10:49:56.612980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26316","citing_title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18127","citing_title":"SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13793","citing_title":"From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD","json":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD.json","graph_json":"https://pith.science/api/pith-number/ZNYMSRP5WS64BNR7VX3STD5UUD/graph.json","events_json":"https://pith.science/api/pith-number/ZNYMSRP5WS64BNR7VX3STD5UUD/events.json","paper":"https://pith.science/paper/ZNYMSRP5"},"agent_actions":{"view_html":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD","download_json":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD.json","view_paper":"https://pith.science/paper/ZNYMSRP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11732&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNYMSRP5WS64BNR7VX3STD5UUD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNYMSRP5WS64BNR7VX3STD5UUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD/action/storage_attestation","attest_author":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD/action/author_attestation","sign_citation":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD/action/citation_signature","submit_replication":"https://pith.science/pith/ZNYMSRP5WS64BNR7VX3STD5UUD/action/replication_record"}},"created_at":"2026-07-05T10:49:56.612980+00:00","updated_at":"2026-07-05T10:49:56.612980+00:00"}