{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KTMVRYI44FRAALXRVROFAQA4ZP","short_pith_number":"pith:KTMVRYI4","schema_version":"1.0","canonical_sha256":"54d958e11ce162002ef1ac5c50401ccbfec0442d07d773fdf48eabc4c04d4b6b","source":{"kind":"arxiv","id":"2408.08093","version":3},"attestation_state":"computed","paper":{"title":"When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Haoliang Li, Jinlong Li, Kecheng Chen, Long Xu, Meng Wang, Nicu Sebe, Pingping Zhang, Sam Kwong, Shiqi Wang","submitted_at":"2024-08-15T11:36:18Z","abstract_excerpt":"Existing codecs are designed to eliminate intrinsic redundancies to create a compact representation for compression. However, strong external priors from Multimodal Large Language Models (MLLMs) have not been explicitly explored in video compression. Herein, we introduce a unified paradigm for Cross-Modality Video Coding (CMVC), which is a pioneering approach to explore multimodality representation and video generative models in video coding. Specifically, on the encoder side, we disentangle a video into spatial content and motion components, which are subsequently transformed into distinct mo"},"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":"2408.08093","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-15T11:36:18Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"29a7a7275020dbbd269c271054b47b594516695a4d150cf3c2b52fc27266ec04","abstract_canon_sha256":"7ab98f525774f96b387e3341ca243b01ea6cd08a29b2d032c24847c696301c88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:04.722936Z","signature_b64":"Io3A+ulsfvFdmuGZTHdZtjBshD/XaZ5y+hV1qTmjgZZvpQNhI9Mat4kAOj/flhD40Y5MsSa8Rw2qp0tBRXPyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d958e11ce162002ef1ac5c50401ccbfec0442d07d773fdf48eabc4c04d4b6b","last_reissued_at":"2026-07-05T10:14:04.722371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:04.722371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Haoliang Li, Jinlong Li, Kecheng Chen, Long Xu, Meng Wang, Nicu Sebe, Pingping Zhang, Sam Kwong, Shiqi Wang","submitted_at":"2024-08-15T11:36:18Z","abstract_excerpt":"Existing codecs are designed to eliminate intrinsic redundancies to create a compact representation for compression. However, strong external priors from Multimodal Large Language Models (MLLMs) have not been explicitly explored in video compression. Herein, we introduce a unified paradigm for Cross-Modality Video Coding (CMVC), which is a pioneering approach to explore multimodality representation and video generative models in video coding. Specifically, on the encoder side, we disentangle a video into spatial content and motion components, which are subsequently transformed into distinct mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08093","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/2408.08093/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":"2408.08093","created_at":"2026-07-05T10:14:04.722440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08093v3","created_at":"2026-07-05T10:14:04.722440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08093","created_at":"2026-07-05T10:14:04.722440+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTMVRYI44FRA","created_at":"2026-07-05T10:14:04.722440+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTMVRYI44FRAALXR","created_at":"2026-07-05T10:14:04.722440+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTMVRYI4","created_at":"2026-07-05T10:14:04.722440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.21545","citing_title":"UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01994","citing_title":"Deeply Dual Supervised learning for melanoma recognition","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06805","citing_title":"Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06816","citing_title":"DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06819","citing_title":"VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03353","citing_title":"NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP","json":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP.json","graph_json":"https://pith.science/api/pith-number/KTMVRYI44FRAALXRVROFAQA4ZP/graph.json","events_json":"https://pith.science/api/pith-number/KTMVRYI44FRAALXRVROFAQA4ZP/events.json","paper":"https://pith.science/paper/KTMVRYI4"},"agent_actions":{"view_html":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP","download_json":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP.json","view_paper":"https://pith.science/paper/KTMVRYI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08093&json=true","fetch_graph":"https://pith.science/api/pith-number/KTMVRYI44FRAALXRVROFAQA4ZP/graph.json","fetch_events":"https://pith.science/api/pith-number/KTMVRYI44FRAALXRVROFAQA4ZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP/action/storage_attestation","attest_author":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP/action/author_attestation","sign_citation":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP/action/citation_signature","submit_replication":"https://pith.science/pith/KTMVRYI44FRAALXRVROFAQA4ZP/action/replication_record"}},"created_at":"2026-07-05T10:14:04.722440+00:00","updated_at":"2026-07-05T10:14:04.722440+00:00"}