{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RMAZBVUTLIM5PN6YXMGDG54CU4","short_pith_number":"pith:RMAZBVUT","schema_version":"1.0","canonical_sha256":"8b0190d6935a19d7b7d8bb0c337782a70c675dd6637ee0819a2d770b0a9ab8c1","source":{"kind":"arxiv","id":"2411.10334","version":1},"attestation_state":"computed","paper":{"title":"Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ammar Qammaz, Antonis A. Argyros, Iason Oikonomidis, Nikolaos Vasilikopoulos","submitted_at":"2024-11-15T16:33:59Z","abstract_excerpt":"We present Y-MAP-Net, a Y-shaped neural network architecture designed for real-time multi-task learning on RGB images. Y-MAP-Net, simultaneously predicts depth, surface normals, human pose, semantic segmentation and generates multi-label captions, all from a single network evaluation. To achieve this, we adopt a multi-teacher, single-student training paradigm, where task-specific foundation models supervise the network's learning, enabling it to distill their capabilities into a lightweight architecture suitable for real-time applications. Y-MAP-Net, exhibits strong generalization, simplicity "},"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":"2411.10334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:33:59Z","cross_cats_sorted":[],"title_canon_sha256":"7ede0030e67c4c10b0e56870fd84ed88f9eb01275aa640da330fc9725974f67f","abstract_canon_sha256":"effe3dfe82bd06e8a0084c823f288e991b2643b79fe2265f5d56420fd20b7a16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:03.596101Z","signature_b64":"u5/pJCkIs8xuzBLIT8f7ujRrPx9YMSJh8Jo67ZCECCEjpiCp+MjeoujXVTDjKZdU1KQ3JPZYQ1aiRLkn+5/sAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b0190d6935a19d7b7d8bb0c337782a70c675dd6637ee0819a2d770b0a9ab8c1","last_reissued_at":"2026-07-05T09:36:03.595574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:03.595574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Y-MAP-Net: Real-time depth, normals, segmentation, multi-label captioning and 2D human pose in RGB images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ammar Qammaz, Antonis A. Argyros, Iason Oikonomidis, Nikolaos Vasilikopoulos","submitted_at":"2024-11-15T16:33:59Z","abstract_excerpt":"We present Y-MAP-Net, a Y-shaped neural network architecture designed for real-time multi-task learning on RGB images. Y-MAP-Net, simultaneously predicts depth, surface normals, human pose, semantic segmentation and generates multi-label captions, all from a single network evaluation. To achieve this, we adopt a multi-teacher, single-student training paradigm, where task-specific foundation models supervise the network's learning, enabling it to distill their capabilities into a lightweight architecture suitable for real-time applications. Y-MAP-Net, exhibits strong generalization, simplicity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10334","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/2411.10334/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":"2411.10334","created_at":"2026-07-05T09:36:03.595633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10334v1","created_at":"2026-07-05T09:36:03.595633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10334","created_at":"2026-07-05T09:36:03.595633+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMAZBVUTLIM5","created_at":"2026-07-05T09:36:03.595633+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMAZBVUTLIM5PN6Y","created_at":"2026-07-05T09:36:03.595633+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMAZBVUT","created_at":"2026-07-05T09:36:03.595633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4","json":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4.json","graph_json":"https://pith.science/api/pith-number/RMAZBVUTLIM5PN6YXMGDG54CU4/graph.json","events_json":"https://pith.science/api/pith-number/RMAZBVUTLIM5PN6YXMGDG54CU4/events.json","paper":"https://pith.science/paper/RMAZBVUT"},"agent_actions":{"view_html":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4","download_json":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4.json","view_paper":"https://pith.science/paper/RMAZBVUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10334&json=true","fetch_graph":"https://pith.science/api/pith-number/RMAZBVUTLIM5PN6YXMGDG54CU4/graph.json","fetch_events":"https://pith.science/api/pith-number/RMAZBVUTLIM5PN6YXMGDG54CU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4/action/storage_attestation","attest_author":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4/action/author_attestation","sign_citation":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4/action/citation_signature","submit_replication":"https://pith.science/pith/RMAZBVUTLIM5PN6YXMGDG54CU4/action/replication_record"}},"created_at":"2026-07-05T09:36:03.595633+00:00","updated_at":"2026-07-05T09:36:03.595633+00:00"}