{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJ5GZEH3N4F3Y55YHI2UUHBWIH","short_pith_number":"pith:ZJ5GZEH3","schema_version":"1.0","canonical_sha256":"ca7a6c90fb6f0bbc77b83a354a1c3641c89fd83368f5c2c7637b4249242d7731","source":{"kind":"arxiv","id":"2310.16387","version":4},"attestation_state":"computed","paper":{"title":"Frequency-Aware Transformer for Learned Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chenglin Li, Han Li, Hongkai Xiong, Junni Zou, Shaohui Li, Wenrui Dai","submitted_at":"2023-10-25T05:59:25Z","abstract_excerpt":"Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing anisotropic frequency components and preserving directional details. To overcome these challenges, we propose a novel frequency-aware transformer (FAT) block that for the first time achieves multiscale directional ananlysis for LIC. The FAT block comprises frequency-decomposition window attention (FDWA) modules to capture multiscale and directional frequency component"},"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":"2310.16387","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2023-10-25T05:59:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ef88f74058559166f801673b91770609f9410490348b304219fce67b02fb81fb","abstract_canon_sha256":"14dc2cfbddbdd14dd73ca3a4b213b3db0e0647932a07f63ba18428b4b176ae6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:00.835019Z","signature_b64":"KSnPpmDtESdthBaaRLPFgJ1nM9eLb0uhDuOUU9Y+w6/5vJPjX1IJBu5ZDBPruhkvzmoD849Cj2r9IrDClWOxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca7a6c90fb6f0bbc77b83a354a1c3641c89fd83368f5c2c7637b4249242d7731","last_reissued_at":"2026-07-05T09:49:00.834501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:00.834501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frequency-Aware Transformer for Learned Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chenglin Li, Han Li, Hongkai Xiong, Junni Zou, Shaohui Li, Wenrui Dai","submitted_at":"2023-10-25T05:59:25Z","abstract_excerpt":"Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing anisotropic frequency components and preserving directional details. To overcome these challenges, we propose a novel frequency-aware transformer (FAT) block that for the first time achieves multiscale directional ananlysis for LIC. The FAT block comprises frequency-decomposition window attention (FDWA) modules to capture multiscale and directional frequency component"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16387","kind":"arxiv","version":4},"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/2310.16387/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":"2310.16387","created_at":"2026-07-05T09:49:00.834559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16387v4","created_at":"2026-07-05T09:49:00.834559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16387","created_at":"2026-07-05T09:49:00.834559+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJ5GZEH3N4F3","created_at":"2026-07-05T09:49:00.834559+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJ5GZEH3N4F3Y55Y","created_at":"2026-07-05T09:49:00.834559+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJ5GZEH3","created_at":"2026-07-05T09:49:00.834559+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01608","citing_title":"Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21366","citing_title":"BADiff: Bandwidth Adaptive Diffusion Model","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04560","citing_title":"SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10546","citing_title":"Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH","json":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH.json","graph_json":"https://pith.science/api/pith-number/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/graph.json","events_json":"https://pith.science/api/pith-number/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/events.json","paper":"https://pith.science/paper/ZJ5GZEH3"},"agent_actions":{"view_html":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH","download_json":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH.json","view_paper":"https://pith.science/paper/ZJ5GZEH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16387&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/action/storage_attestation","attest_author":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/action/author_attestation","sign_citation":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/action/citation_signature","submit_replication":"https://pith.science/pith/ZJ5GZEH3N4F3Y55YHI2UUHBWIH/action/replication_record"}},"created_at":"2026-07-05T09:49:00.834559+00:00","updated_at":"2026-07-05T09:49:00.834559+00:00"}