{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XE2S4YMZOAHNUP7TV2VDLXOWMY","short_pith_number":"pith:XE2S4YMZ","schema_version":"1.0","canonical_sha256":"b9352e6199700eda3ff3aeaa35ddd666326395e2f1180ceb92da9db0c25d49d8","source":{"kind":"arxiv","id":"2607.08075","version":1},"attestation_state":"computed","paper":{"title":"UAV-OVVIS: Unmanned Aerial Vehicles Also Need Open-Vocabulary Video Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming Hu, Mingyu Dou, Shi Qiu, Yifan Chen, Zhe Sun","submitted_at":"2026-07-09T03:08:33Z","abstract_excerpt":"Unmanned Aerial Vehicle (UAV) videos are widely used in traffic monitoring, urban management, and emergency rescue. However, existing UAV video perception mainly relies on box-level localization and trajectory association under predefined categories, making it difficult to simultaneously support flexible queries and fine-grained instance-level dynamic understanding in open scenarios. To this end, we introduce a new task, UAV Open-Vocabulary Video Instance Segmentation (UAV-OVVIS), which discovers targets in UAV videos according to open-vocabulary queries and outputs instance-level segmentation"},"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":"2607.08075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T03:08:33Z","cross_cats_sorted":[],"title_canon_sha256":"ba077baf2ee8cdd20dfd15c0b5c94377fbf3be73933bb9d4419135c89a19ad39","abstract_canon_sha256":"18b1cdb3f70a6c5e96421bbd6b9db650bb5a257869695b5193ff95fcff16e03d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T00:19:09.696711Z","signature_b64":"da/LSDqZafJzgHNsbmVZuaG3a39xDpPJQzRO+krlGwfTTcU6B3+eRzgwX4dmITsEdOuOwDXthDVPZTnBjAV7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9352e6199700eda3ff3aeaa35ddd666326395e2f1180ceb92da9db0c25d49d8","last_reissued_at":"2026-07-10T00:19:09.696233Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T00:19:09.696233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UAV-OVVIS: Unmanned Aerial Vehicles Also Need Open-Vocabulary Video Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming Hu, Mingyu Dou, Shi Qiu, Yifan Chen, Zhe Sun","submitted_at":"2026-07-09T03:08:33Z","abstract_excerpt":"Unmanned Aerial Vehicle (UAV) videos are widely used in traffic monitoring, urban management, and emergency rescue. However, existing UAV video perception mainly relies on box-level localization and trajectory association under predefined categories, making it difficult to simultaneously support flexible queries and fine-grained instance-level dynamic understanding in open scenarios. To this end, we introduce a new task, UAV Open-Vocabulary Video Instance Segmentation (UAV-OVVIS), which discovers targets in UAV videos according to open-vocabulary queries and outputs instance-level segmentation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08075","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/2607.08075/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":"2607.08075","created_at":"2026-07-10T00:19:09.696366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08075v1","created_at":"2026-07-10T00:19:09.696366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08075","created_at":"2026-07-10T00:19:09.696366+00:00"},{"alias_kind":"pith_short_12","alias_value":"XE2S4YMZOAHN","created_at":"2026-07-10T00:19:09.696366+00:00"},{"alias_kind":"pith_short_16","alias_value":"XE2S4YMZOAHNUP7T","created_at":"2026-07-10T00:19:09.696366+00:00"},{"alias_kind":"pith_short_8","alias_value":"XE2S4YMZ","created_at":"2026-07-10T00:19:09.696366+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/XE2S4YMZOAHNUP7TV2VDLXOWMY","json":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY.json","graph_json":"https://pith.science/api/pith-number/XE2S4YMZOAHNUP7TV2VDLXOWMY/graph.json","events_json":"https://pith.science/api/pith-number/XE2S4YMZOAHNUP7TV2VDLXOWMY/events.json","paper":"https://pith.science/paper/XE2S4YMZ"},"agent_actions":{"view_html":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY","download_json":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY.json","view_paper":"https://pith.science/paper/XE2S4YMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08075&json=true","fetch_graph":"https://pith.science/api/pith-number/XE2S4YMZOAHNUP7TV2VDLXOWMY/graph.json","fetch_events":"https://pith.science/api/pith-number/XE2S4YMZOAHNUP7TV2VDLXOWMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY/action/storage_attestation","attest_author":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY/action/author_attestation","sign_citation":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY/action/citation_signature","submit_replication":"https://pith.science/pith/XE2S4YMZOAHNUP7TV2VDLXOWMY/action/replication_record"}},"created_at":"2026-07-10T00:19:09.696366+00:00","updated_at":"2026-07-10T00:19:09.696366+00:00"}