{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TNDMYDA26BDDLOD2XFZCTHPQZZ","short_pith_number":"pith:TNDMYDA2","schema_version":"1.0","canonical_sha256":"9b46cc0c1af04635b87ab972299df0ce49fb1b0d9848610ccc89761b0bf2b701","source":{"kind":"arxiv","id":"2501.07783","version":1},"attestation_state":"computed","paper":{"title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Gen Luo, Hao Li, Jifeng Dai, Junqi Ge, Lewei Lu, Wenhan Dou, Xizhou Zhu, Xue Yang, Yu Qiao, Zhaokai Wang","submitted_at":"2025-01-14T01:57:41Z","abstract_excerpt":"Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of images, leading to significant computational cost. To address this challenge, we propose a novel network architecture, called Parameter-Inverted Image Pyramid Networks (PIIP). Specifically, PIIP uses pretrained models (ViTs or CNNs) as branches to process multi-scale images, where images of higher resolutions are processed by smaller network branches to balanc"},"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":"2501.07783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T01:57:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7003aa416392734d4c30e05f60b50c98b84fee9568f4a98597fb300f7a8d525c","abstract_canon_sha256":"4d07ba53ff524d163f4417e34ca7975d16ed17a8cbf8ef089bcd3e13dfc82287"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:09.133889Z","signature_b64":"CtzmUK9qX4BZBRZ02J00BNuJaFlLRIftAomb+Hnn3jWjDlgi5UpGo5/r2spzf0W2+IIYsMMYzoHm76qulQGaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b46cc0c1af04635b87ab972299df0ce49fb1b0d9848610ccc89761b0bf2b701","last_reissued_at":"2026-07-05T11:43:09.133464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:09.133464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Gen Luo, Hao Li, Jifeng Dai, Junqi Ge, Lewei Lu, Wenhan Dou, Xizhou Zhu, Xue Yang, Yu Qiao, Zhaokai Wang","submitted_at":"2025-01-14T01:57:41Z","abstract_excerpt":"Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of images, leading to significant computational cost. To address this challenge, we propose a novel network architecture, called Parameter-Inverted Image Pyramid Networks (PIIP). Specifically, PIIP uses pretrained models (ViTs or CNNs) as branches to process multi-scale images, where images of higher resolutions are processed by smaller network branches to balanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07783","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/2501.07783/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":"2501.07783","created_at":"2026-07-05T11:43:09.133523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07783v1","created_at":"2026-07-05T11:43:09.133523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07783","created_at":"2026-07-05T11:43:09.133523+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNDMYDA26BDD","created_at":"2026-07-05T11:43:09.133523+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNDMYDA26BDDLOD2","created_at":"2026-07-05T11:43:09.133523+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNDMYDA2","created_at":"2026-07-05T11:43:09.133523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12566","citing_title":"Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ","json":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ.json","graph_json":"https://pith.science/api/pith-number/TNDMYDA26BDDLOD2XFZCTHPQZZ/graph.json","events_json":"https://pith.science/api/pith-number/TNDMYDA26BDDLOD2XFZCTHPQZZ/events.json","paper":"https://pith.science/paper/TNDMYDA2"},"agent_actions":{"view_html":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ","download_json":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ.json","view_paper":"https://pith.science/paper/TNDMYDA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07783&json=true","fetch_graph":"https://pith.science/api/pith-number/TNDMYDA26BDDLOD2XFZCTHPQZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TNDMYDA26BDDLOD2XFZCTHPQZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ/action/storage_attestation","attest_author":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ/action/author_attestation","sign_citation":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ/action/citation_signature","submit_replication":"https://pith.science/pith/TNDMYDA26BDDLOD2XFZCTHPQZZ/action/replication_record"}},"created_at":"2026-07-05T11:43:09.133523+00:00","updated_at":"2026-07-05T11:43:09.133523+00:00"}