{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMVO3B7OQRRV366NRHZQJPSUQB","short_pith_number":"pith:JMVO3B7O","schema_version":"1.0","canonical_sha256":"4b2aed87ee84635dfbcd89f304be548060931646219d8872200f27a86895d631","source":{"kind":"arxiv","id":"2411.09219","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Minjing Dong, Yuheng Shi","submitted_at":"2024-11-14T06:31:20Z","abstract_excerpt":"While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and constrained resolution. While previous adaptations addressed spatial invariance semantic by modifying the self-attention in CLIP's image encoder, the issue of limited resolution remains unexplored. Different from previous segment-then-splice methods that segment sub-images via a sliding window and splice the results, we introduce a splice-then-segment paradigm t"},"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":"2411.09219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T06:31:20Z","cross_cats_sorted":[],"title_canon_sha256":"db84d2be585c7ce6bf835423edf6276e214e55964b284db43c51d000bf68f2f0","abstract_canon_sha256":"f3c7624a82c0353b83f38c471d89e19c88b082c2a30880ef698c157a5a7f46a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:22.720090Z","signature_b64":"T4fesQls+YNKkDREj+r0uX95QLH9aSD/m7/cNKGUlHsy0i6+p1Dntem6071JDssTyvS0Pwd+0yBtNPd2rQgfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2aed87ee84635dfbcd89f304be548060931646219d8872200f27a86895d631","last_reissued_at":"2026-07-05T09:35:22.719603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:22.719603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Minjing Dong, Yuheng Shi","submitted_at":"2024-11-14T06:31:20Z","abstract_excerpt":"While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and constrained resolution. While previous adaptations addressed spatial invariance semantic by modifying the self-attention in CLIP's image encoder, the issue of limited resolution remains unexplored. Different from previous segment-then-splice methods that segment sub-images via a sliding window and splice the results, we introduce a splice-then-segment paradigm t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09219","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/2411.09219/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":"2411.09219","created_at":"2026-07-05T09:35:22.719657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09219v1","created_at":"2026-07-05T09:35:22.719657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09219","created_at":"2026-07-05T09:35:22.719657+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMVO3B7OQRRV","created_at":"2026-07-05T09:35:22.719657+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMVO3B7OQRRV366N","created_at":"2026-07-05T09:35:22.719657+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMVO3B7O","created_at":"2026-07-05T09:35:22.719657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.22667","citing_title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19704","citing_title":"RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28115","citing_title":"FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26067","citing_title":"RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12551","citing_title":"Cross-Attentive Multiview Fusion of Vision-Language Embeddings","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB","json":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB.json","graph_json":"https://pith.science/api/pith-number/JMVO3B7OQRRV366NRHZQJPSUQB/graph.json","events_json":"https://pith.science/api/pith-number/JMVO3B7OQRRV366NRHZQJPSUQB/events.json","paper":"https://pith.science/paper/JMVO3B7O"},"agent_actions":{"view_html":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB","download_json":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB.json","view_paper":"https://pith.science/paper/JMVO3B7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09219&json=true","fetch_graph":"https://pith.science/api/pith-number/JMVO3B7OQRRV366NRHZQJPSUQB/graph.json","fetch_events":"https://pith.science/api/pith-number/JMVO3B7OQRRV366NRHZQJPSUQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/action/storage_attestation","attest_author":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/action/author_attestation","sign_citation":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/action/citation_signature","submit_replication":"https://pith.science/pith/JMVO3B7OQRRV366NRHZQJPSUQB/action/replication_record"}},"created_at":"2026-07-05T09:35:22.719657+00:00","updated_at":"2026-07-05T09:35:22.719657+00:00"}