{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3O5IOPRUUFYVVEV4YBLRTTAKB","short_pith_number":"pith:Q3O5IOPR","schema_version":"1.0","canonical_sha256":"86ddd439f1a50b8ad495e602b8ce605072aa1da30c43fd36abb2858fa2c340bb","source":{"kind":"arxiv","id":"2403.02944","version":2},"attestation_state":"computed","paper":{"title":"Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dokwan Oh, Hagyeong Lee, Jaeho Lee, Jun-Hyuk Kim, Minkyu Kim, Seungeon Kim","submitted_at":"2024-03-05T13:15:01Z","abstract_excerpt":"Recent advances in text-guided image compression have shown great potential to enhance the perceptual quality of reconstructed images. These methods, however, tend to have significantly degraded pixel-wise fidelity, limiting their practicality. To fill this gap, we develop a new text-guided image compression algorithm that achieves both high perceptual and pixel-wise fidelity. In particular, we propose a compression framework that leverages text information mainly by text-adaptive encoding and training with joint image-text loss. By doing so, we avoid decoding based on text-guided generative 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":"2403.02944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T13:15:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c12028eb7bbf9c7d2b8e0bda3b316f26b29caff028ffb4aee81195b44a78a41f","abstract_canon_sha256":"2f72ee9e308d7718fafae3d1e834437ca09bbb7d8e14799afa11d9843ec28f89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:51.175677Z","signature_b64":"tUDRNFgUbujxrhHM+RMWXvsxYwXq3oTyKTWYJmvpDdzUdAhtthkOHZ92wnCYb+l0Q4d3Pz5OpjAqPRuRSaW3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86ddd439f1a50b8ad495e602b8ce605072aa1da30c43fd36abb2858fa2c340bb","last_reissued_at":"2026-07-05T08:21:51.175169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:51.175169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dokwan Oh, Hagyeong Lee, Jaeho Lee, Jun-Hyuk Kim, Minkyu Kim, Seungeon Kim","submitted_at":"2024-03-05T13:15:01Z","abstract_excerpt":"Recent advances in text-guided image compression have shown great potential to enhance the perceptual quality of reconstructed images. These methods, however, tend to have significantly degraded pixel-wise fidelity, limiting their practicality. To fill this gap, we develop a new text-guided image compression algorithm that achieves both high perceptual and pixel-wise fidelity. In particular, we propose a compression framework that leverages text information mainly by text-adaptive encoding and training with joint image-text loss. By doing so, we avoid decoding based on text-guided generative m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02944","kind":"arxiv","version":2},"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/2403.02944/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":"2403.02944","created_at":"2026-07-05T08:21:51.175224+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02944v2","created_at":"2026-07-05T08:21:51.175224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02944","created_at":"2026-07-05T08:21:51.175224+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3O5IOPRUUFY","created_at":"2026-07-05T08:21:51.175224+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3O5IOPRUUFYVVEV","created_at":"2026-07-05T08:21:51.175224+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3O5IOPR","created_at":"2026-07-05T08:21:51.175224+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01608","citing_title":"Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04560","citing_title":"SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB","json":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB.json","graph_json":"https://pith.science/api/pith-number/Q3O5IOPRUUFYVVEV4YBLRTTAKB/graph.json","events_json":"https://pith.science/api/pith-number/Q3O5IOPRUUFYVVEV4YBLRTTAKB/events.json","paper":"https://pith.science/paper/Q3O5IOPR"},"agent_actions":{"view_html":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB","download_json":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB.json","view_paper":"https://pith.science/paper/Q3O5IOPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02944&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3O5IOPRUUFYVVEV4YBLRTTAKB/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3O5IOPRUUFYVVEV4YBLRTTAKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB/action/storage_attestation","attest_author":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB/action/author_attestation","sign_citation":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB/action/citation_signature","submit_replication":"https://pith.science/pith/Q3O5IOPRUUFYVVEV4YBLRTTAKB/action/replication_record"}},"created_at":"2026-07-05T08:21:51.175224+00:00","updated_at":"2026-07-05T08:21:51.175224+00:00"}