{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W7JGJ5ZURLKQ64SKJM7PZX2DEI","short_pith_number":"pith:W7JGJ5ZU","schema_version":"1.0","canonical_sha256":"b7d264f7348ad50f724a4b3efcdf43222d1bbba6760128665ba3f4055b5f69b0","source":{"kind":"arxiv","id":"2412.18386","version":3},"attestation_state":"computed","paper":{"title":"Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah","submitted_at":"2024-12-24T12:16:43Z","abstract_excerpt":"We introduce SWITCH-A-VIEW, a model that learns to automatically select the viewpoint to display at each timepoint when creating a how-to video. The key insight of our approach is how to train such a model from unlabeled -- but human-edited -- video samples. We pose a pretext task that pseudo-labels segments in the training videos for their primary viewpoint (egocentric or exocentric), and then discovers the patterns between the visual and spoken content in a how-to video on the one hand and its view-switch moments on the other hand. Armed with this predictor, our model can be applied to new 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":"2412.18386","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T12:16:43Z","cross_cats_sorted":[],"title_canon_sha256":"e2cde88a5237c57a58cf3e87e2c7044fa5a5136e579f2c9c3ec4326c955faf5a","abstract_canon_sha256":"010f893190fc97307e68af11711756e1b6e603b2fbe8e3a03e94d9300c99cff3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:17.413291Z","signature_b64":"yvbJtKQB/kTuNjj0AogEVHYvap5ZkX1BltIl4Be3vvGdj0sx/hLQzUu7PtmlqWdO5rq8wIlIxyHMqL6O8WCRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7d264f7348ad50f724a4b3efcdf43222d1bbba6760128665ba3f4055b5f69b0","last_reissued_at":"2026-07-05T10:52:17.412754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:17.412754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Sagnik Majumder, Tushar Nagarajan, Ziad Al-Halah","submitted_at":"2024-12-24T12:16:43Z","abstract_excerpt":"We introduce SWITCH-A-VIEW, a model that learns to automatically select the viewpoint to display at each timepoint when creating a how-to video. The key insight of our approach is how to train such a model from unlabeled -- but human-edited -- video samples. We pose a pretext task that pseudo-labels segments in the training videos for their primary viewpoint (egocentric or exocentric), and then discovers the patterns between the visual and spoken content in a how-to video on the one hand and its view-switch moments on the other hand. Armed with this predictor, our model can be applied to new m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18386","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/2412.18386/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":"2412.18386","created_at":"2026-07-05T10:52:17.412805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18386v3","created_at":"2026-07-05T10:52:17.412805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18386","created_at":"2026-07-05T10:52:17.412805+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7JGJ5ZURLKQ","created_at":"2026-07-05T10:52:17.412805+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7JGJ5ZURLKQ64SK","created_at":"2026-07-05T10:52:17.412805+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7JGJ5ZU","created_at":"2026-07-05T10:52:17.412805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06253","citing_title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","ref_index":188,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI","json":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI.json","graph_json":"https://pith.science/api/pith-number/W7JGJ5ZURLKQ64SKJM7PZX2DEI/graph.json","events_json":"https://pith.science/api/pith-number/W7JGJ5ZURLKQ64SKJM7PZX2DEI/events.json","paper":"https://pith.science/paper/W7JGJ5ZU"},"agent_actions":{"view_html":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI","download_json":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI.json","view_paper":"https://pith.science/paper/W7JGJ5ZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18386&json=true","fetch_graph":"https://pith.science/api/pith-number/W7JGJ5ZURLKQ64SKJM7PZX2DEI/graph.json","fetch_events":"https://pith.science/api/pith-number/W7JGJ5ZURLKQ64SKJM7PZX2DEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI/action/storage_attestation","attest_author":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI/action/author_attestation","sign_citation":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI/action/citation_signature","submit_replication":"https://pith.science/pith/W7JGJ5ZURLKQ64SKJM7PZX2DEI/action/replication_record"}},"created_at":"2026-07-05T10:52:17.412805+00:00","updated_at":"2026-07-05T10:52:17.412805+00:00"}