{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4Q4LYXTZ6EVQCQGACFOHXZDHZC","short_pith_number":"pith:4Q4LYXTZ","schema_version":"1.0","canonical_sha256":"e438bc5e79f12b0140c0115c7be467c8a05ae70cd276094ee0cb6b61dae78d97","source":{"kind":"arxiv","id":"2111.06707","version":1},"attestation_state":"computed","paper":{"title":"Transformer-based Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chuntong Cao, Huiqing Shi, Ming Lu, Peiyao Guo, Zhan Ma","submitted_at":"2021-11-12T13:13:20Z","abstract_excerpt":"A Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders. Both main and hyper encoders are comprised of a sequence of neural transformation units (NTUs) to analyse and aggregate important information for more compact representation of input image, while the decoders mirror the encoder-side operations to generate pixel-domain image reconstruction from the compressed bitstream. Each NTU is consist of a Swin Transformer Block (STB) and a convolutional layer (Conv) to best emb"},"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":"2111.06707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2021-11-12T13:13:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"448f69f43ad566dcb1468d96113e0a531391965cca0a168c311a9e4998a696cc","abstract_canon_sha256":"935087fd6915b56fe83b1160c44fa83607d44922252e7d05c1b0556e53d664de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:16.881472Z","signature_b64":"uWbvHOxjwnCLinWpVHBAYN6gyoKvd6KXUjf8XvqBkvLHx05K3dV4egJy8k0FjxXhbBcEg8HrEWbzkyVwwRbICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e438bc5e79f12b0140c0115c7be467c8a05ae70cd276094ee0cb6b61dae78d97","last_reissued_at":"2026-07-05T03:31:16.880946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:16.880946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-based Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chuntong Cao, Huiqing Shi, Ming Lu, Peiyao Guo, Zhan Ma","submitted_at":"2021-11-12T13:13:20Z","abstract_excerpt":"A Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders. Both main and hyper encoders are comprised of a sequence of neural transformation units (NTUs) to analyse and aggregate important information for more compact representation of input image, while the decoders mirror the encoder-side operations to generate pixel-domain image reconstruction from the compressed bitstream. Each NTU is consist of a Swin Transformer Block (STB) and a convolutional layer (Conv) to best emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06707","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.06707/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":"2111.06707","created_at":"2026-07-05T03:31:16.881005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.06707v1","created_at":"2026-07-05T03:31:16.881005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06707","created_at":"2026-07-05T03:31:16.881005+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Q4LYXTZ6EVQ","created_at":"2026-07-05T03:31:16.881005+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Q4LYXTZ6EVQCQGA","created_at":"2026-07-05T03:31:16.881005+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Q4LYXTZ","created_at":"2026-07-05T03:31:16.881005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21033","citing_title":"MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04560","citing_title":"SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10017","citing_title":"What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC","json":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC.json","graph_json":"https://pith.science/api/pith-number/4Q4LYXTZ6EVQCQGACFOHXZDHZC/graph.json","events_json":"https://pith.science/api/pith-number/4Q4LYXTZ6EVQCQGACFOHXZDHZC/events.json","paper":"https://pith.science/paper/4Q4LYXTZ"},"agent_actions":{"view_html":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC","download_json":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC.json","view_paper":"https://pith.science/paper/4Q4LYXTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.06707&json=true","fetch_graph":"https://pith.science/api/pith-number/4Q4LYXTZ6EVQCQGACFOHXZDHZC/graph.json","fetch_events":"https://pith.science/api/pith-number/4Q4LYXTZ6EVQCQGACFOHXZDHZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC/action/storage_attestation","attest_author":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC/action/author_attestation","sign_citation":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC/action/citation_signature","submit_replication":"https://pith.science/pith/4Q4LYXTZ6EVQCQGACFOHXZDHZC/action/replication_record"}},"created_at":"2026-07-05T03:31:16.881005+00:00","updated_at":"2026-07-05T03:31:16.881005+00:00"}