{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5DALZMGJKXF42326BUIRLE4MCF","short_pith_number":"pith:5DALZMGJ","schema_version":"1.0","canonical_sha256":"e8c0bcb0c955cbcd6f5e0d1115938c11687a3e8273bd92d3a753540f7be57033","source":{"kind":"arxiv","id":"2406.10475","version":1},"attestation_state":"computed","paper":{"title":"Discrete Latent Perspective Learning for Segmentation and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyi Ji, Feng Zhao, Hongtao Lu, Jieping Ye, Lanyun Zhu, Wenwei Jin","submitted_at":"2024-06-15T02:40:49Z","abstract_excerpt":"In this paper, we address the challenge of Perspective-Invariant Learning in machine learning and computer vision, which involves enabling a network to understand images from varying perspectives to achieve consistent semantic interpretation. While standard approaches rely on the labor-intensive collection of multi-view images or limited data augmentation techniques, we propose a novel framework, Discrete Latent Perspective Learning (DLPL), for latent multi-perspective fusion learning using conventional single-view images. DLPL comprises three main modules: Perspective Discrete Decomposition ("},"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":"2406.10475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T02:40:49Z","cross_cats_sorted":[],"title_canon_sha256":"5f2c6f3c4911c4706c395b4712c9eb2154a5ca1a28043f78b70a6d7a4486a4c0","abstract_canon_sha256":"3d80abfdbce22f552b6f051f5e108174391411bc9949e9108588d388222f0db7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:17.204524Z","signature_b64":"HBsFrmMsUjYswM6irJC72kR9NaeJ8GgJjkLI1GkxL0zuJM+PbSQwGhimu1IoeWnhnUs/KTcWaOCmpPxSk2JWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8c0bcb0c955cbcd6f5e0d1115938c11687a3e8273bd92d3a753540f7be57033","last_reissued_at":"2026-07-05T08:32:17.203996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:17.203996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Latent Perspective Learning for Segmentation and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyi Ji, Feng Zhao, Hongtao Lu, Jieping Ye, Lanyun Zhu, Wenwei Jin","submitted_at":"2024-06-15T02:40:49Z","abstract_excerpt":"In this paper, we address the challenge of Perspective-Invariant Learning in machine learning and computer vision, which involves enabling a network to understand images from varying perspectives to achieve consistent semantic interpretation. While standard approaches rely on the labor-intensive collection of multi-view images or limited data augmentation techniques, we propose a novel framework, Discrete Latent Perspective Learning (DLPL), for latent multi-perspective fusion learning using conventional single-view images. DLPL comprises three main modules: Perspective Discrete Decomposition ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10475","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/2406.10475/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":"2406.10475","created_at":"2026-07-05T08:32:17.204062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10475v1","created_at":"2026-07-05T08:32:17.204062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10475","created_at":"2026-07-05T08:32:17.204062+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DALZMGJKXF4","created_at":"2026-07-05T08:32:17.204062+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DALZMGJKXF42326","created_at":"2026-07-05T08:32:17.204062+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DALZMGJ","created_at":"2026-07-05T08:32:17.204062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16811","citing_title":"Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF","json":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF.json","graph_json":"https://pith.science/api/pith-number/5DALZMGJKXF42326BUIRLE4MCF/graph.json","events_json":"https://pith.science/api/pith-number/5DALZMGJKXF42326BUIRLE4MCF/events.json","paper":"https://pith.science/paper/5DALZMGJ"},"agent_actions":{"view_html":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF","download_json":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF.json","view_paper":"https://pith.science/paper/5DALZMGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10475&json=true","fetch_graph":"https://pith.science/api/pith-number/5DALZMGJKXF42326BUIRLE4MCF/graph.json","fetch_events":"https://pith.science/api/pith-number/5DALZMGJKXF42326BUIRLE4MCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF/action/storage_attestation","attest_author":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF/action/author_attestation","sign_citation":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF/action/citation_signature","submit_replication":"https://pith.science/pith/5DALZMGJKXF42326BUIRLE4MCF/action/replication_record"}},"created_at":"2026-07-05T08:32:17.204062+00:00","updated_at":"2026-07-05T08:32:17.204062+00:00"}