{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:535ZF3U2Z6K3QVM5RE4NWF2ICT","short_pith_number":"pith:535ZF3U2","schema_version":"1.0","canonical_sha256":"eefb92ee9acf95b8559d8938db174814f31a226c16c66d358667325e1623142c","source":{"kind":"arxiv","id":"2402.18115","version":2},"attestation_state":"computed","paper":{"title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Minghan Li, Shuai Li, Xindong Zhang","submitted_at":"2024-02-28T07:05:27Z","abstract_excerpt":"Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts throughout the entire video, making it hard to handle the different tasks with the same architecture. We make an attempt to address these issues and present a novel unified VS architecture, namely UniVS, by using prompts as queries. UniVS averages "},"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":"2402.18115","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T07:05:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fd29f7525afd5855345273e5cc7e5ddcce856e12c78900750e9c5c6dcc2c280c","abstract_canon_sha256":"b1d3367a38d8511e46faf4581bc2487d3c9da6595cf25d6e882ac00021dff541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:23.312406Z","signature_b64":"CuJpVxPzl1lvA07ETw9yOycYVLSNvlgv9+BuPBqAFrxRayK9NeHgqTnTYiT3R6/C9NyGFPg6vcxGuc+dpg8RCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eefb92ee9acf95b8559d8938db174814f31a226c16c66d358667325e1623142c","last_reissued_at":"2026-07-05T08:29:23.311923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:23.311923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Minghan Li, Shuai Li, Xindong Zhang","submitted_at":"2024-02-28T07:05:27Z","abstract_excerpt":"Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts throughout the entire video, making it hard to handle the different tasks with the same architecture. We make an attempt to address these issues and present a novel unified VS architecture, namely UniVS, by using prompts as queries. UniVS averages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18115","kind":"arxiv","version":2},"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/2402.18115/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":"2402.18115","created_at":"2026-07-05T08:29:23.311984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18115v2","created_at":"2026-07-05T08:29:23.311984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18115","created_at":"2026-07-05T08:29:23.311984+00:00"},{"alias_kind":"pith_short_12","alias_value":"535ZF3U2Z6K3","created_at":"2026-07-05T08:29:23.311984+00:00"},{"alias_kind":"pith_short_16","alias_value":"535ZF3U2Z6K3QVM5","created_at":"2026-07-05T08:29:23.311984+00:00"},{"alias_kind":"pith_short_8","alias_value":"535ZF3U2","created_at":"2026-07-05T08:29:23.311984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14096","citing_title":"Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT","json":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT.json","graph_json":"https://pith.science/api/pith-number/535ZF3U2Z6K3QVM5RE4NWF2ICT/graph.json","events_json":"https://pith.science/api/pith-number/535ZF3U2Z6K3QVM5RE4NWF2ICT/events.json","paper":"https://pith.science/paper/535ZF3U2"},"agent_actions":{"view_html":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT","download_json":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT.json","view_paper":"https://pith.science/paper/535ZF3U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18115&json=true","fetch_graph":"https://pith.science/api/pith-number/535ZF3U2Z6K3QVM5RE4NWF2ICT/graph.json","fetch_events":"https://pith.science/api/pith-number/535ZF3U2Z6K3QVM5RE4NWF2ICT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT/action/storage_attestation","attest_author":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT/action/author_attestation","sign_citation":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT/action/citation_signature","submit_replication":"https://pith.science/pith/535ZF3U2Z6K3QVM5RE4NWF2ICT/action/replication_record"}},"created_at":"2026-07-05T08:29:23.311984+00:00","updated_at":"2026-07-05T08:29:23.311984+00:00"}