{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BKUB6K6GHTHVOORJGSPHZSV7WR","short_pith_number":"pith:BKUB6K6G","schema_version":"1.0","canonical_sha256":"0aa81f2bc63ccf573a29349e7ccabfb467d88ddf1ca4fa943d902a1f77396627","source":{"kind":"arxiv","id":"1804.09627","version":1},"attestation_state":"computed","paper":{"title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Ali Farhadi, Cordelia Schmid, Gunnar A. Sigurdsson, Karteek Alahari","submitted_at":"2018-04-25T15:30:34Z","abstract_excerpt":"Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-person (actor). Despite this, learning such models for human action recognition has not been achievable due to the lack of data. This paper takes a step in this direction, with the introduction of Charades-Ego, a large-scale dataset of paired first-person and third-person videos, involving 112 people, with 4000 paired videos. This enables learning "},"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":"1804.09627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-25T15:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"8868657f487b65ccae92187c6a522545b8ce1f692123d08e13e5926242a4442a","abstract_canon_sha256":"c77bd6d8a359f81dc2623a9315d5600e576f46d7e67f908749ca00f8f303f69e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:31.230668Z","signature_b64":"6in1jpXtq+7QDmOqMOBXeUzQ+4gzWYN901fnRebYqsO+PSwgOARHxQ+nWC4MT4fKNq20rJsPW1kPj/BWcVYCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aa81f2bc63ccf573a29349e7ccabfb467d88ddf1ca4fa943d902a1f77396627","last_reissued_at":"2026-05-18T00:17:31.229961Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:31.229961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Ali Farhadi, Cordelia Schmid, Gunnar A. Sigurdsson, Karteek Alahari","submitted_at":"2018-04-25T15:30:34Z","abstract_excerpt":"Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-person (actor). Despite this, learning such models for human action recognition has not been achievable due to the lack of data. This paper takes a step in this direction, with the introduction of Charades-Ego, a large-scale dataset of paired first-person and third-person videos, involving 112 people, with 4000 paired videos. This enables learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.09627","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":""},"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":"1804.09627","created_at":"2026-05-18T00:17:31.230068+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.09627v1","created_at":"2026-05-18T00:17:31.230068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.09627","created_at":"2026-05-18T00:17:31.230068+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKUB6K6GHTHV","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKUB6K6GHTHVOORJ","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKUB6K6G","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22858","citing_title":"A Probabilistic Jump-Diffusion Framework for Open-World Egocentric Activity Recognition","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR","json":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR.json","graph_json":"https://pith.science/api/pith-number/BKUB6K6GHTHVOORJGSPHZSV7WR/graph.json","events_json":"https://pith.science/api/pith-number/BKUB6K6GHTHVOORJGSPHZSV7WR/events.json","paper":"https://pith.science/paper/BKUB6K6G"},"agent_actions":{"view_html":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR","download_json":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR.json","view_paper":"https://pith.science/paper/BKUB6K6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.09627&json=true","fetch_graph":"https://pith.science/api/pith-number/BKUB6K6GHTHVOORJGSPHZSV7WR/graph.json","fetch_events":"https://pith.science/api/pith-number/BKUB6K6GHTHVOORJGSPHZSV7WR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR/action/storage_attestation","attest_author":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR/action/author_attestation","sign_citation":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR/action/citation_signature","submit_replication":"https://pith.science/pith/BKUB6K6GHTHVOORJGSPHZSV7WR/action/replication_record"}},"created_at":"2026-05-18T00:17:31.230068+00:00","updated_at":"2026-05-18T00:17:31.230068+00:00"}