{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A5F2HWCMESEYLPJUYLUXG4PORN","short_pith_number":"pith:A5F2HWCM","schema_version":"1.0","canonical_sha256":"074ba3d84c248985bd34c2e97371ee8b748ff77b0bacc3597b5b30c360e574eb","source":{"kind":"arxiv","id":"2404.01990","version":1},"attestation_state":"computed","paper":{"title":"What is Point Supervision Worth in Video Instance Segmentation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Anima Anandkumar, De-An Huang, Jose M. Alvarez, Shiyi Lan, Shuaiyi Huang, Subhashree Radhakrishnan, Zhiding Yu","submitted_at":"2024-04-01T17:38:25Z","abstract_excerpt":"Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during training, and obtain high-quality mask predictions close to fully supervised models. Our proposed training method consists of a class-agnostic proposal generation module to provide rich negative samples and a spatio-temporal point-based matcher to match the object queries with the provided point annota"},"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":"2404.01990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"53c6b3c06145b21d9f1e1e51a038cc30f888e82b3296947dc39099ae2a2f1089","abstract_canon_sha256":"f66581a8f3bd6a1fc33fbdc7c98172619231a9cb5256762c0e861ce1757d6d32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:34.497639Z","signature_b64":"cZXRxHjj4noV8+SdWaUyv2fKuvKB28BBszh3KQ3FzjGZjEL1zkOWTReuSo7aQuUzFbzXPo2dH+PKDWHn5UUoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"074ba3d84c248985bd34c2e97371ee8b748ff77b0bacc3597b5b30c360e574eb","last_reissued_at":"2026-07-05T08:03:34.497232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:34.497232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is Point Supervision Worth in Video Instance Segmentation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Anima Anandkumar, De-An Huang, Jose M. Alvarez, Shiyi Lan, Shuaiyi Huang, Subhashree Radhakrishnan, Zhiding Yu","submitted_at":"2024-04-01T17:38:25Z","abstract_excerpt":"Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during training, and obtain high-quality mask predictions close to fully supervised models. Our proposed training method consists of a class-agnostic proposal generation module to provide rich negative samples and a spatio-temporal point-based matcher to match the object queries with the provided point annota"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01990","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/2404.01990/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":"2404.01990","created_at":"2026-07-05T08:03:34.497286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01990v1","created_at":"2026-07-05T08:03:34.497286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01990","created_at":"2026-07-05T08:03:34.497286+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5F2HWCMESEY","created_at":"2026-07-05T08:03:34.497286+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5F2HWCMESEYLPJU","created_at":"2026-07-05T08:03:34.497286+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5F2HWCM","created_at":"2026-07-05T08:03:34.497286+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/A5F2HWCMESEYLPJUYLUXG4PORN","json":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN.json","graph_json":"https://pith.science/api/pith-number/A5F2HWCMESEYLPJUYLUXG4PORN/graph.json","events_json":"https://pith.science/api/pith-number/A5F2HWCMESEYLPJUYLUXG4PORN/events.json","paper":"https://pith.science/paper/A5F2HWCM"},"agent_actions":{"view_html":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN","download_json":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN.json","view_paper":"https://pith.science/paper/A5F2HWCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01990&json=true","fetch_graph":"https://pith.science/api/pith-number/A5F2HWCMESEYLPJUYLUXG4PORN/graph.json","fetch_events":"https://pith.science/api/pith-number/A5F2HWCMESEYLPJUYLUXG4PORN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN/action/storage_attestation","attest_author":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN/action/author_attestation","sign_citation":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN/action/citation_signature","submit_replication":"https://pith.science/pith/A5F2HWCMESEYLPJUYLUXG4PORN/action/replication_record"}},"created_at":"2026-07-05T08:03:34.497286+00:00","updated_at":"2026-07-05T08:03:34.497286+00:00"}