{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Z43OTFAO4G5UNZ3Y2XOAAFYHRF","short_pith_number":"pith:Z43OTFAO","schema_version":"1.0","canonical_sha256":"cf36e9940ee1bb46e778d5dc00170789570763194b59991f19708549e1f45d98","source":{"kind":"arxiv","id":"1605.08359","version":1},"attestation_state":"computed","paper":{"title":"Pairwise Decomposition of Image Sequences for Active Multi-View Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew J. Davison, Edward Johns, Stefan Leutenegger","submitted_at":"2016-05-26T16:44:19Z","abstract_excerpt":"A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary ca"},"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":"1605.08359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-26T16:44:19Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"945bb5c02767e2331f0039a5b32ce00cab53d9e4c29cb84275fcb38fe5260f44","abstract_canon_sha256":"3de90ae0975209dcb0130d92f523d0b6befcfd7fcd27a24bb977c36b0af7677a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:31.775137Z","signature_b64":"eoJYcVA8fTil6Ub568Vmrt7RCrw2/45mX55PTGDJ2rEs9AxdvqAPBQurm/F+Lmi3F6Qy0cupM660nsC0PiCxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf36e9940ee1bb46e778d5dc00170789570763194b59991f19708549e1f45d98","last_reissued_at":"2026-05-18T01:13:31.774472Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:31.774472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pairwise Decomposition of Image Sequences for Active Multi-View Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew J. Davison, Edward Johns, Stefan Leutenegger","submitted_at":"2016-05-26T16:44:19Z","abstract_excerpt":"A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08359","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":"1605.08359","created_at":"2026-05-18T01:13:31.774577+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.08359v1","created_at":"2026-05-18T01:13:31.774577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08359","created_at":"2026-05-18T01:13:31.774577+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z43OTFAO4G5U","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z43OTFAO4G5UNZ3Y","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z43OTFAO","created_at":"2026-05-18T12:30:53.716459+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/Z43OTFAO4G5UNZ3Y2XOAAFYHRF","json":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF.json","graph_json":"https://pith.science/api/pith-number/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/graph.json","events_json":"https://pith.science/api/pith-number/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/events.json","paper":"https://pith.science/paper/Z43OTFAO"},"agent_actions":{"view_html":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF","download_json":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF.json","view_paper":"https://pith.science/paper/Z43OTFAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.08359&json=true","fetch_graph":"https://pith.science/api/pith-number/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/graph.json","fetch_events":"https://pith.science/api/pith-number/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/action/storage_attestation","attest_author":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/action/author_attestation","sign_citation":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/action/citation_signature","submit_replication":"https://pith.science/pith/Z43OTFAO4G5UNZ3Y2XOAAFYHRF/action/replication_record"}},"created_at":"2026-05-18T01:13:31.774577+00:00","updated_at":"2026-05-18T01:13:31.774577+00:00"}