{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K4IXOY6GYH7WSZ4KIMNFC5NXY6","short_pith_number":"pith:K4IXOY6G","schema_version":"1.0","canonical_sha256":"57117763c6c1ff69678a431a5175b7c78bbfa0db549106303a233544472c4755","source":{"kind":"arxiv","id":"2303.17594","version":2},"attestation_state":"computed","paper":{"title":"MobileInst: Video Instance Segmentation on the Mobile","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dashan Gao, Haoyi Jiang, Jiancheng Lyu, Renhong Zhang, Shuai Zhang, Shusheng Yang, Tianheng Cheng, Wenyu Liu, Xiaowen Ying, Xinggang Wang, Xin Li","submitted_at":"2023-03-30T17:59:02Z","abstract_excerpt":"Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame pixel-level instance perception and (2) complicated heuristics for tracking objects. To address those issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices. Firstly, MobileInst adopts a mobile vision transformer to extract multi-level semantic features and presents an efficient query-based dual-transformer instance decoder for mask kernels and a "},"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":"2303.17594","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"ee8e72738e23703fca7449f5b723b3a5934a37f5a4afd5ec6a6471593f123bf7","abstract_canon_sha256":"ef98b6333730e8329ef179471bab7dac15422e0f489baaa8c7018d878e1a16a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:49.181577Z","signature_b64":"39KINjTSm1a53Ue6x3HA0mFwKa5nsu0mc6tFNNDNcrkmi/KS63dB8RyC0k3s06AOH2EDLXW3mdYne80jok6HBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57117763c6c1ff69678a431a5175b7c78bbfa0db549106303a233544472c4755","last_reissued_at":"2026-07-05T07:24:49.181139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:49.181139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileInst: Video Instance Segmentation on the Mobile","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dashan Gao, Haoyi Jiang, Jiancheng Lyu, Renhong Zhang, Shuai Zhang, Shusheng Yang, Tianheng Cheng, Wenyu Liu, Xiaowen Ying, Xinggang Wang, Xin Li","submitted_at":"2023-03-30T17:59:02Z","abstract_excerpt":"Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame pixel-level instance perception and (2) complicated heuristics for tracking objects. To address those issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices. Firstly, MobileInst adopts a mobile vision transformer to extract multi-level semantic features and presents an efficient query-based dual-transformer instance decoder for mask kernels and a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17594","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/2303.17594/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":"2303.17594","created_at":"2026-07-05T07:24:49.181196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17594v2","created_at":"2026-07-05T07:24:49.181196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17594","created_at":"2026-07-05T07:24:49.181196+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4IXOY6GYH7W","created_at":"2026-07-05T07:24:49.181196+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4IXOY6GYH7WSZ4K","created_at":"2026-07-05T07:24:49.181196+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4IXOY6G","created_at":"2026-07-05T07:24:49.181196+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/K4IXOY6GYH7WSZ4KIMNFC5NXY6","json":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6.json","graph_json":"https://pith.science/api/pith-number/K4IXOY6GYH7WSZ4KIMNFC5NXY6/graph.json","events_json":"https://pith.science/api/pith-number/K4IXOY6GYH7WSZ4KIMNFC5NXY6/events.json","paper":"https://pith.science/paper/K4IXOY6G"},"agent_actions":{"view_html":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6","download_json":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6.json","view_paper":"https://pith.science/paper/K4IXOY6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17594&json=true","fetch_graph":"https://pith.science/api/pith-number/K4IXOY6GYH7WSZ4KIMNFC5NXY6/graph.json","fetch_events":"https://pith.science/api/pith-number/K4IXOY6GYH7WSZ4KIMNFC5NXY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6/action/storage_attestation","attest_author":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6/action/author_attestation","sign_citation":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6/action/citation_signature","submit_replication":"https://pith.science/pith/K4IXOY6GYH7WSZ4KIMNFC5NXY6/action/replication_record"}},"created_at":"2026-07-05T07:24:49.181196+00:00","updated_at":"2026-07-05T07:24:49.181196+00:00"}