{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TPRX4LO7Q66FXJSYEIF27YBB2T","short_pith_number":"pith:TPRX4LO7","schema_version":"1.0","canonical_sha256":"9be37e2ddf87bc5ba658220bafe021d4ebb72c0e3b6dbdbb07a78fdb45d75b2b","source":{"kind":"arxiv","id":"1903.10863","version":3},"attestation_state":"computed","paper":{"title":"AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Guo-jun Qi, Liheng Zhang, Qi Tian","submitted_at":"2019-03-23T21:31:10Z","abstract_excerpt":"The learning of Transformation-Equivariant Representations (TERs), which is introduced by Hinton et al. \\cite{hinton2011transforming}, has been considered as a principle to reveal visual structures under various transformations. It contains the celebrated Convolutional Neural Networks (CNNs) as a special case that only equivary to the translations. In contrast, we seek to train TERs for a generic class of transformations and train them in an {\\em unsupervised} fashion. To this end, we present a novel principled method by Autoencoding Variational Transformations (AVT), compared with the convent"},"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":"1903.10863","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-23T21:31:10Z","cross_cats_sorted":[],"title_canon_sha256":"83487ae351e96c19fb8ee85a51658206c99d7ce63783429df4b03c1a767a716f","abstract_canon_sha256":"267fae38f8ac099550b44a876ab37344f3ac168dfda3a4b44c38432a19e029d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:54.498404Z","signature_b64":"lSrBK0VUjtQqbxdUpCAIY7UMAyD12FTbopL25tXmTfh+g+lDfWUOh9LR4DAW+0M7/VmEHpMv0xGz4HOBBWJSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9be37e2ddf87bc5ba658220bafe021d4ebb72c0e3b6dbdbb07a78fdb45d75b2b","last_reissued_at":"2026-05-17T23:39:54.497925Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:54.497925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Guo-jun Qi, Liheng Zhang, Qi Tian","submitted_at":"2019-03-23T21:31:10Z","abstract_excerpt":"The learning of Transformation-Equivariant Representations (TERs), which is introduced by Hinton et al. \\cite{hinton2011transforming}, has been considered as a principle to reveal visual structures under various transformations. It contains the celebrated Convolutional Neural Networks (CNNs) as a special case that only equivary to the translations. In contrast, we seek to train TERs for a generic class of transformations and train them in an {\\em unsupervised} fashion. To this end, we present a novel principled method by Autoencoding Variational Transformations (AVT), compared with the convent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10863","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":""},"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":"1903.10863","created_at":"2026-05-17T23:39:54.497991+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10863v3","created_at":"2026-05-17T23:39:54.497991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10863","created_at":"2026-05-17T23:39:54.497991+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPRX4LO7Q66F","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPRX4LO7Q66FXJSY","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPRX4LO7","created_at":"2026-05-18T12:33:30.264802+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/TPRX4LO7Q66FXJSYEIF27YBB2T","json":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T.json","graph_json":"https://pith.science/api/pith-number/TPRX4LO7Q66FXJSYEIF27YBB2T/graph.json","events_json":"https://pith.science/api/pith-number/TPRX4LO7Q66FXJSYEIF27YBB2T/events.json","paper":"https://pith.science/paper/TPRX4LO7"},"agent_actions":{"view_html":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T","download_json":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T.json","view_paper":"https://pith.science/paper/TPRX4LO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10863&json=true","fetch_graph":"https://pith.science/api/pith-number/TPRX4LO7Q66FXJSYEIF27YBB2T/graph.json","fetch_events":"https://pith.science/api/pith-number/TPRX4LO7Q66FXJSYEIF27YBB2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T/action/storage_attestation","attest_author":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T/action/author_attestation","sign_citation":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T/action/citation_signature","submit_replication":"https://pith.science/pith/TPRX4LO7Q66FXJSYEIF27YBB2T/action/replication_record"}},"created_at":"2026-05-17T23:39:54.497991+00:00","updated_at":"2026-05-17T23:39:54.497991+00:00"}