{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SF7J6EAXEESYJAQJQKTXCFSJCH","short_pith_number":"pith:SF7J6EAX","schema_version":"1.0","canonical_sha256":"917e9f1017212584820982a771164911fb0fb3836d77b24c947fa767312ec888","source":{"kind":"arxiv","id":"2412.10292","version":1},"attestation_state":"computed","paper":{"title":"Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajinkya Kale, Kun Wan, Lantao Yu, Xin Lu, Xinyang Zhang, Yu-Jhe Li","submitted_at":"2024-12-13T17:22:50Z","abstract_excerpt":"We tackle the challenge of open-vocabulary segmentation, where we need to identify objects from a wide range of categories in different environments, using text prompts as our input. To overcome this challenge, existing methods often use multi-modal models like CLIP, which combine image and text features in a shared embedding space to bridge the gap between limited and extensive vocabulary recognition, resulting in a two-stage approach: In the first stage, a mask generator takes an input image to generate mask proposals, and the in the second stage the target mask is picked based on the query."},"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":"2412.10292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T17:22:50Z","cross_cats_sorted":[],"title_canon_sha256":"fc84e2ebbe80c8c22890aaf611004ed3b66431d27a40bda4c08bee48e6b970b4","abstract_canon_sha256":"9be00c29c7dadac3693c6f8d3cb96db36d2c4518e592abf98d4703db1d20bbd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:55.874288Z","signature_b64":"hH4LecS+MLOr779TyFVLquqKSpGyF3zU7dlsqcUr6Ajln8YlJ2wm1OtS4PLk0K9i3q7l7FZZxVhPzAhe6NOVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917e9f1017212584820982a771164911fb0fb3836d77b24c947fa767312ec888","last_reissued_at":"2026-07-05T09:48:55.873750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:55.873750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajinkya Kale, Kun Wan, Lantao Yu, Xin Lu, Xinyang Zhang, Yu-Jhe Li","submitted_at":"2024-12-13T17:22:50Z","abstract_excerpt":"We tackle the challenge of open-vocabulary segmentation, where we need to identify objects from a wide range of categories in different environments, using text prompts as our input. To overcome this challenge, existing methods often use multi-modal models like CLIP, which combine image and text features in a shared embedding space to bridge the gap between limited and extensive vocabulary recognition, resulting in a two-stage approach: In the first stage, a mask generator takes an input image to generate mask proposals, and the in the second stage the target mask is picked based on the query."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10292","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/2412.10292/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":"2412.10292","created_at":"2026-07-05T09:48:55.873805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10292v1","created_at":"2026-07-05T09:48:55.873805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10292","created_at":"2026-07-05T09:48:55.873805+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF7J6EAXEESY","created_at":"2026-07-05T09:48:55.873805+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF7J6EAXEESYJAQJ","created_at":"2026-07-05T09:48:55.873805+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF7J6EAX","created_at":"2026-07-05T09:48:55.873805+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/SF7J6EAXEESYJAQJQKTXCFSJCH","json":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH.json","graph_json":"https://pith.science/api/pith-number/SF7J6EAXEESYJAQJQKTXCFSJCH/graph.json","events_json":"https://pith.science/api/pith-number/SF7J6EAXEESYJAQJQKTXCFSJCH/events.json","paper":"https://pith.science/paper/SF7J6EAX"},"agent_actions":{"view_html":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH","download_json":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH.json","view_paper":"https://pith.science/paper/SF7J6EAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10292&json=true","fetch_graph":"https://pith.science/api/pith-number/SF7J6EAXEESYJAQJQKTXCFSJCH/graph.json","fetch_events":"https://pith.science/api/pith-number/SF7J6EAXEESYJAQJQKTXCFSJCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH/action/storage_attestation","attest_author":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH/action/author_attestation","sign_citation":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH/action/citation_signature","submit_replication":"https://pith.science/pith/SF7J6EAXEESYJAQJQKTXCFSJCH/action/replication_record"}},"created_at":"2026-07-05T09:48:55.873805+00:00","updated_at":"2026-07-05T09:48:55.873805+00:00"}