{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A3M2Z3NSJBCIWUXBYSETKLH7Z4","short_pith_number":"pith:A3M2Z3NS","schema_version":"1.0","canonical_sha256":"06d9acedb248448b52e1c489352cffcf2ace9676d8b6670b04ef91db10e7b6f8","source":{"kind":"arxiv","id":"2307.06701","version":3},"attestation_state":"computed","paper":{"title":"S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Giampiero Salvi, Kalin Stefanov, Mohammad Adiban, Sabato Marco Siniscalchi","submitted_at":"2023-07-13T11:58:27Z","abstract_excerpt":"We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive model (AST-PM). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the AST-PM's ability to handle spatiotemporal information, S-HR-VQVAE can better deal with 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":"2307.06701","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T11:58:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ee1299e2cdade764348ca338626f0006c6381efac5b3e44a1ed3e219eb4cc2bf","abstract_canon_sha256":"12fdb7ce4e752a2f0b985c3ca91a0b7b4654f961c7595f8cc88f57c7faee7e99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:32.168472Z","signature_b64":"LXObOHlWcMWD+2h0Vj0AE4oYVyY+cVYHmS0PkHS6SF52uATVPpqcazRXHlng4kCI819kElESP0m/kh3vzfDTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06d9acedb248448b52e1c489352cffcf2ace9676d8b6670b04ef91db10e7b6f8","last_reissued_at":"2026-07-05T09:37:32.168110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:32.168110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Giampiero Salvi, Kalin Stefanov, Mohammad Adiban, Sabato Marco Siniscalchi","submitted_at":"2023-07-13T11:58:27Z","abstract_excerpt":"We address the video prediction task by putting forth a novel model that combines (i) a novel hierarchical residual learning vector quantized variational autoencoder (HR-VQVAE), and (ii) a novel autoregressive spatiotemporal predictive model (AST-PM). We refer to this approach as a sequential hierarchical residual learning vector quantized variational autoencoder (S-HR-VQVAE). By leveraging the intrinsic capabilities of HR-VQVAE at modeling still images with a parsimonious representation, combined with the AST-PM's ability to handle spatiotemporal information, S-HR-VQVAE can better deal with m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06701","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/2307.06701/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":"2307.06701","created_at":"2026-07-05T09:37:32.168172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06701v3","created_at":"2026-07-05T09:37:32.168172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06701","created_at":"2026-07-05T09:37:32.168172+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3M2Z3NSJBCI","created_at":"2026-07-05T09:37:32.168172+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3M2Z3NSJBCIWUXB","created_at":"2026-07-05T09:37:32.168172+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3M2Z3NS","created_at":"2026-07-05T09:37:32.168172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04559","citing_title":"MambaVideo for Discrete Video Tokenization with Channel-Split Quantization","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4","json":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4.json","graph_json":"https://pith.science/api/pith-number/A3M2Z3NSJBCIWUXBYSETKLH7Z4/graph.json","events_json":"https://pith.science/api/pith-number/A3M2Z3NSJBCIWUXBYSETKLH7Z4/events.json","paper":"https://pith.science/paper/A3M2Z3NS"},"agent_actions":{"view_html":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4","download_json":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4.json","view_paper":"https://pith.science/paper/A3M2Z3NS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06701&json=true","fetch_graph":"https://pith.science/api/pith-number/A3M2Z3NSJBCIWUXBYSETKLH7Z4/graph.json","fetch_events":"https://pith.science/api/pith-number/A3M2Z3NSJBCIWUXBYSETKLH7Z4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4/action/storage_attestation","attest_author":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4/action/author_attestation","sign_citation":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4/action/citation_signature","submit_replication":"https://pith.science/pith/A3M2Z3NSJBCIWUXBYSETKLH7Z4/action/replication_record"}},"created_at":"2026-07-05T09:37:32.168172+00:00","updated_at":"2026-07-05T09:37:32.168172+00:00"}