{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:24P2RHEKV4MCV2DACHNWXWYITT","short_pith_number":"pith:24P2RHEK","schema_version":"1.0","canonical_sha256":"d71fa89c8aaf182ae86011db6bdb089cc72d0649fd5d95f8ddf3762d8f3ebe5d","source":{"kind":"arxiv","id":"2203.15312","version":4},"attestation_state":"computed","paper":{"title":"In-N-Out Generative Learning for Dense Unsupervised Video Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Zhou, Hongxia Yang, Huiling Zhou, Jingren Zhou, Peike Li, Xiao Pan, Yi Yang, Zongxin Yang","submitted_at":"2022-03-29T07:56:21Z","abstract_excerpt":"In this paper, we focus on unsupervised learning for Video Object Segmentation (VOS) which learns visual correspondence (i.e., the similarity between pixel-level features) from unlabeled videos. Previous methods are mainly based on the contrastive learning paradigm, which optimize either in image level or pixel level. Image-level optimization (e.g., the spatially pooled feature of ResNet) learns robust high-level semantics but is sub-optimal since the pixel-level features are optimized implicitly. By contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual qu"},"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":"2203.15312","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T07:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"df3f72cffb98dda31fdce5416826884b0c21eced1832430289a13487dcc97531","abstract_canon_sha256":"83103df2c66bbc648753d197aa79e581cce0a6a2edd6522cbdfb1969f0e7e8e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:16.682724Z","signature_b64":"X/SkwVL3TYV+QLDaBYHDDVlTvc5HrougfpYZ24Mkc4lm+VgOeCJww4+p7xEVYvKA6OU9HTCWC1CbfK87OdVECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d71fa89c8aaf182ae86011db6bdb089cc72d0649fd5d95f8ddf3762d8f3ebe5d","last_reissued_at":"2026-07-05T05:09:16.682290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:16.682290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-N-Out Generative Learning for Dense Unsupervised Video Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Zhou, Hongxia Yang, Huiling Zhou, Jingren Zhou, Peike Li, Xiao Pan, Yi Yang, Zongxin Yang","submitted_at":"2022-03-29T07:56:21Z","abstract_excerpt":"In this paper, we focus on unsupervised learning for Video Object Segmentation (VOS) which learns visual correspondence (i.e., the similarity between pixel-level features) from unlabeled videos. Previous methods are mainly based on the contrastive learning paradigm, which optimize either in image level or pixel level. Image-level optimization (e.g., the spatially pooled feature of ResNet) learns robust high-level semantics but is sub-optimal since the pixel-level features are optimized implicitly. By contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15312","kind":"arxiv","version":4},"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/2203.15312/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":"2203.15312","created_at":"2026-07-05T05:09:16.682363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15312v4","created_at":"2026-07-05T05:09:16.682363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15312","created_at":"2026-07-05T05:09:16.682363+00:00"},{"alias_kind":"pith_short_12","alias_value":"24P2RHEKV4MC","created_at":"2026-07-05T05:09:16.682363+00:00"},{"alias_kind":"pith_short_16","alias_value":"24P2RHEKV4MCV2DA","created_at":"2026-07-05T05:09:16.682363+00:00"},{"alias_kind":"pith_short_8","alias_value":"24P2RHEK","created_at":"2026-07-05T05:09:16.682363+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/24P2RHEKV4MCV2DACHNWXWYITT","json":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT.json","graph_json":"https://pith.science/api/pith-number/24P2RHEKV4MCV2DACHNWXWYITT/graph.json","events_json":"https://pith.science/api/pith-number/24P2RHEKV4MCV2DACHNWXWYITT/events.json","paper":"https://pith.science/paper/24P2RHEK"},"agent_actions":{"view_html":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT","download_json":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT.json","view_paper":"https://pith.science/paper/24P2RHEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15312&json=true","fetch_graph":"https://pith.science/api/pith-number/24P2RHEKV4MCV2DACHNWXWYITT/graph.json","fetch_events":"https://pith.science/api/pith-number/24P2RHEKV4MCV2DACHNWXWYITT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT/action/storage_attestation","attest_author":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT/action/author_attestation","sign_citation":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT/action/citation_signature","submit_replication":"https://pith.science/pith/24P2RHEKV4MCV2DACHNWXWYITT/action/replication_record"}},"created_at":"2026-07-05T05:09:16.682363+00:00","updated_at":"2026-07-05T05:09:16.682363+00:00"}