{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z5FDTCHMS6B76YRWW6DQSONFNU","short_pith_number":"pith:Z5FDTCHM","schema_version":"1.0","canonical_sha256":"cf4a3988ec9783ff6236b7870939a56d36402f823172595e49835cfba247bb69","source":{"kind":"arxiv","id":"2006.09220","version":2},"attestation_state":"computed","paper":{"title":"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juergen Gall, Ming-Ming Cheng, Shijie Li, Yazan Abu Farha, Yun Liu","submitted_at":"2020-06-16T14:50:47Z","abstract_excerpt":"With the success of deep learning in classifying short trimmed videos, more attention has been focused on temporally segmenting and classifying activities in long untrimmed videos. State-of-the-art approaches for action segmentation utilize several layers of temporal convolution and temporal pooling. Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors. In this paper, we propose a multi-stage architecture for the temporal action segmentation task that overcomes the limitations of the previous approaches. The fir"},"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":"2006.09220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-16T14:50:47Z","cross_cats_sorted":[],"title_canon_sha256":"eab96159432b0fd39bafd192449629d577c7afe44b3c2495e2b6e0febdb0a23a","abstract_canon_sha256":"ac35385249933f5b6f6a47ae7b0624f4dcc4d6c28bd2554514f142c953658e8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:32:45.320121Z","signature_b64":"r0SNDjL1dh6SBvSp06UeEsIZMCcPej9FDIb1F4HmiScPqcJwfqiJJaW6Xc6fiLh/V7H+4wfj/LzpbFJ4dKx+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf4a3988ec9783ff6236b7870939a56d36402f823172595e49835cfba247bb69","last_reissued_at":"2026-07-05T01:32:45.319718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:32:45.319718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juergen Gall, Ming-Ming Cheng, Shijie Li, Yazan Abu Farha, Yun Liu","submitted_at":"2020-06-16T14:50:47Z","abstract_excerpt":"With the success of deep learning in classifying short trimmed videos, more attention has been focused on temporally segmenting and classifying activities in long untrimmed videos. State-of-the-art approaches for action segmentation utilize several layers of temporal convolution and temporal pooling. Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors. In this paper, we propose a multi-stage architecture for the temporal action segmentation task that overcomes the limitations of the previous approaches. The fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09220","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/2006.09220/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":"2006.09220","created_at":"2026-07-05T01:32:45.319780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09220v2","created_at":"2026-07-05T01:32:45.319780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09220","created_at":"2026-07-05T01:32:45.319780+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5FDTCHMS6B7","created_at":"2026-07-05T01:32:45.319780+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5FDTCHMS6B76YRW","created_at":"2026-07-05T01:32:45.319780+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5FDTCHM","created_at":"2026-07-05T01:32:45.319780+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/Z5FDTCHMS6B76YRWW6DQSONFNU","json":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU.json","graph_json":"https://pith.science/api/pith-number/Z5FDTCHMS6B76YRWW6DQSONFNU/graph.json","events_json":"https://pith.science/api/pith-number/Z5FDTCHMS6B76YRWW6DQSONFNU/events.json","paper":"https://pith.science/paper/Z5FDTCHM"},"agent_actions":{"view_html":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU","download_json":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU.json","view_paper":"https://pith.science/paper/Z5FDTCHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09220&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5FDTCHMS6B76YRWW6DQSONFNU/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5FDTCHMS6B76YRWW6DQSONFNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU/action/storage_attestation","attest_author":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU/action/author_attestation","sign_citation":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU/action/citation_signature","submit_replication":"https://pith.science/pith/Z5FDTCHMS6B76YRWW6DQSONFNU/action/replication_record"}},"created_at":"2026-07-05T01:32:45.319780+00:00","updated_at":"2026-07-05T01:32:45.319780+00:00"}