{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4AOIK4UJJXPWA3O2ASRXZ3YJ2K","short_pith_number":"pith:4AOIK4UJ","schema_version":"1.0","canonical_sha256":"e01c8572894ddf606dda04a37cef09d2a8c06f95a4dabc3ab94010c63f081afe","source":{"kind":"arxiv","id":"2109.02281","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Jie Jiang, Jing Liu, Weining Wang, Xingjian He, Zhiyong Xu","submitted_at":"2021-09-06T08:24:38Z","abstract_excerpt":"Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction. In this paper, we propose a Spatial-Temporal Semantic Consistency method to capture class-exclusive context information. Specifically, we design a spatial-temporal consistency loss to constrain the semantic consistency in spatial and temporal dimensions. In addition, we adopt an pseudo-labeling strategy to enrich the training dataset. We obtain the scores of 59.84% and 58.85% mIoU on development (test part 1) and testing set of VSPW, "},"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":"2109.02281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-06T08:24:38Z","cross_cats_sorted":[],"title_canon_sha256":"b52a56513b5ae71a12d75d27cfec2a0f90392975836f1114a42055b50416b3ff","abstract_canon_sha256":"7066cec20306165116b2f59ed73b51f3561336ffa86a5ae717e3132b23c687a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:40.664244Z","signature_b64":"q2YhrBhT7+oK8B9NpC3KD/UQTnwBY9sgR99ZNKM97SIu1Aj4O9e9aD8nQB1zNRwOI+rTbMsj+qY8ZLlzdCWjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01c8572894ddf606dda04a37cef09d2a8c06f95a4dabc3ab94010c63f081afe","last_reissued_at":"2026-07-05T03:11:40.663714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:40.663714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Jie Jiang, Jing Liu, Weining Wang, Xingjian He, Zhiyong Xu","submitted_at":"2021-09-06T08:24:38Z","abstract_excerpt":"Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction. In this paper, we propose a Spatial-Temporal Semantic Consistency method to capture class-exclusive context information. Specifically, we design a spatial-temporal consistency loss to constrain the semantic consistency in spatial and temporal dimensions. In addition, we adopt an pseudo-labeling strategy to enrich the training dataset. We obtain the scores of 59.84% and 58.85% mIoU on development (test part 1) and testing set of VSPW, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02281","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/2109.02281/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":"2109.02281","created_at":"2026-07-05T03:11:40.663770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02281v1","created_at":"2026-07-05T03:11:40.663770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02281","created_at":"2026-07-05T03:11:40.663770+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AOIK4UJJXPW","created_at":"2026-07-05T03:11:40.663770+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AOIK4UJJXPWA3O2","created_at":"2026-07-05T03:11:40.663770+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AOIK4UJ","created_at":"2026-07-05T03:11:40.663770+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/4AOIK4UJJXPWA3O2ASRXZ3YJ2K","json":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K.json","graph_json":"https://pith.science/api/pith-number/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/graph.json","events_json":"https://pith.science/api/pith-number/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/events.json","paper":"https://pith.science/paper/4AOIK4UJ"},"agent_actions":{"view_html":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K","download_json":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K.json","view_paper":"https://pith.science/paper/4AOIK4UJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02281&json=true","fetch_graph":"https://pith.science/api/pith-number/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/graph.json","fetch_events":"https://pith.science/api/pith-number/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/action/storage_attestation","attest_author":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/action/author_attestation","sign_citation":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/action/citation_signature","submit_replication":"https://pith.science/pith/4AOIK4UJJXPWA3O2ASRXZ3YJ2K/action/replication_record"}},"created_at":"2026-07-05T03:11:40.663770+00:00","updated_at":"2026-07-05T03:11:40.663770+00:00"}