{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:65CZH6ILK54UMZEFEKYUONJXJA","short_pith_number":"pith:65CZH6IL","schema_version":"1.0","canonical_sha256":"f74593f90b577946648522b1473537483022eb9876c7555b0831e164b3c9bd37","source":{"kind":"arxiv","id":"2110.12369","version":1},"attestation_state":"computed","paper":{"title":"AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hong Cai, Shubhankar Borse, Yizhe Zhang","submitted_at":"2021-10-24T07:07:41Z","abstract_excerpt":"In video segmentation, generating temporally consistent results across frames is as important as achieving frame-wise accuracy. Existing methods rely either on optical flow regularization or fine-tuning with test data to attain temporal consistency. However, optical flow is not always avail-able and reliable. Besides, it is expensive to compute. Fine-tuning the original model in test time is cost sensitive.\n  This paper presents an efficient, intuitive, and unsupervised online adaptation method, AuxAdapt, for improving the temporal consistency of most neural network models. It does not require"},"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":"2110.12369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-24T07:07:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"a2ce62628e58d71770515b7e7fdbf51cb9cd9c6add1a3ea1c39337244b8c4646","abstract_canon_sha256":"413349f2769146deebfa603da1d33464c5eadf8560a42725a9245830b6a3c4cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:19.367694Z","signature_b64":"Lc08lbPpqUIS5CMzwkTtl5GWGQeJrjUJi6WB14wwu5Va2Aafp/8GhXNli/LraLo+ugTG2OBvZEOjig2l8SjFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74593f90b577946648522b1473537483022eb9876c7555b0831e164b3c9bd37","last_reissued_at":"2026-07-05T03:25:19.367241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:19.367241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hong Cai, Shubhankar Borse, Yizhe Zhang","submitted_at":"2021-10-24T07:07:41Z","abstract_excerpt":"In video segmentation, generating temporally consistent results across frames is as important as achieving frame-wise accuracy. Existing methods rely either on optical flow regularization or fine-tuning with test data to attain temporal consistency. However, optical flow is not always avail-able and reliable. Besides, it is expensive to compute. Fine-tuning the original model in test time is cost sensitive.\n  This paper presents an efficient, intuitive, and unsupervised online adaptation method, AuxAdapt, for improving the temporal consistency of most neural network models. It does not require"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12369","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/2110.12369/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":"2110.12369","created_at":"2026-07-05T03:25:19.367302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12369v1","created_at":"2026-07-05T03:25:19.367302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12369","created_at":"2026-07-05T03:25:19.367302+00:00"},{"alias_kind":"pith_short_12","alias_value":"65CZH6ILK54U","created_at":"2026-07-05T03:25:19.367302+00:00"},{"alias_kind":"pith_short_16","alias_value":"65CZH6ILK54UMZEF","created_at":"2026-07-05T03:25:19.367302+00:00"},{"alias_kind":"pith_short_8","alias_value":"65CZH6IL","created_at":"2026-07-05T03:25:19.367302+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/65CZH6ILK54UMZEFEKYUONJXJA","json":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA.json","graph_json":"https://pith.science/api/pith-number/65CZH6ILK54UMZEFEKYUONJXJA/graph.json","events_json":"https://pith.science/api/pith-number/65CZH6ILK54UMZEFEKYUONJXJA/events.json","paper":"https://pith.science/paper/65CZH6IL"},"agent_actions":{"view_html":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA","download_json":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA.json","view_paper":"https://pith.science/paper/65CZH6IL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12369&json=true","fetch_graph":"https://pith.science/api/pith-number/65CZH6ILK54UMZEFEKYUONJXJA/graph.json","fetch_events":"https://pith.science/api/pith-number/65CZH6ILK54UMZEFEKYUONJXJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA/action/storage_attestation","attest_author":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA/action/author_attestation","sign_citation":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA/action/citation_signature","submit_replication":"https://pith.science/pith/65CZH6ILK54UMZEFEKYUONJXJA/action/replication_record"}},"created_at":"2026-07-05T03:25:19.367302+00:00","updated_at":"2026-07-05T03:25:19.367302+00:00"}