{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WWQMEVNX5FZXWCYWKZA35GF5XE","short_pith_number":"pith:WWQMEVNX","schema_version":"1.0","canonical_sha256":"b5a0c255b7e9737b0b165641be98bdb9061d7023d9ffdb4956a0d67d9e48749b","source":{"kind":"arxiv","id":"2405.15995","version":1},"attestation_state":"computed","paper":{"title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erik Blasch, Haibin Ling, Jie Wei, Peiyao Wang, Yuewei Lin","submitted_at":"2024-05-25T00:44:13Z","abstract_excerpt":"Although the performance of Temporal Action Segmentation (TAS) has improved in recent years, achieving promising results often comes with a high computational cost due to dense inputs, complex model structures, and resource-intensive post-processing requirements. To improve the efficiency while keeping the performance, we present a novel perspective centered on per-segment classification. By harnessing the capabilities of Transformers, we tokenize each video segment as an instance token, endowed with intrinsic instance segmentation. To realize efficient action segmentation, we introduce BaForm"},"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":"2405.15995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T00:44:13Z","cross_cats_sorted":[],"title_canon_sha256":"0a7995036ba706739de3686f3776324e05b0d4a4597b463f474ef012e6179d86","abstract_canon_sha256":"ca9fc439abe81185461575f8ae84efd800e1e71c8cda7b38d3167b9ccc66dbc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:59.984183Z","signature_b64":"PWU+G+WR0VIjueaQNZ6T4IeCWUUEYGDxbGtUbVGj8HQ6vta4ikfsGKy0i0xqlGK68Whqt1IbI8bQJnW8D1UYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5a0c255b7e9737b0b165641be98bdb9061d7023d9ffdb4956a0d67d9e48749b","last_reissued_at":"2026-07-05T08:22:59.983734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:59.983734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Erik Blasch, Haibin Ling, Jie Wei, Peiyao Wang, Yuewei Lin","submitted_at":"2024-05-25T00:44:13Z","abstract_excerpt":"Although the performance of Temporal Action Segmentation (TAS) has improved in recent years, achieving promising results often comes with a high computational cost due to dense inputs, complex model structures, and resource-intensive post-processing requirements. To improve the efficiency while keeping the performance, we present a novel perspective centered on per-segment classification. By harnessing the capabilities of Transformers, we tokenize each video segment as an instance token, endowed with intrinsic instance segmentation. To realize efficient action segmentation, we introduce BaForm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15995","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/2405.15995/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":"2405.15995","created_at":"2026-07-05T08:22:59.983791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15995v1","created_at":"2026-07-05T08:22:59.983791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15995","created_at":"2026-07-05T08:22:59.983791+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWQMEVNX5FZX","created_at":"2026-07-05T08:22:59.983791+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWQMEVNX5FZXWCYW","created_at":"2026-07-05T08:22:59.983791+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWQMEVNX","created_at":"2026-07-05T08:22:59.983791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02472","citing_title":"HRTR: A Single-stage Transformer for Fine-grained Sub-second Action Segmentation in Stroke Rehabilitation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE","json":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE.json","graph_json":"https://pith.science/api/pith-number/WWQMEVNX5FZXWCYWKZA35GF5XE/graph.json","events_json":"https://pith.science/api/pith-number/WWQMEVNX5FZXWCYWKZA35GF5XE/events.json","paper":"https://pith.science/paper/WWQMEVNX"},"agent_actions":{"view_html":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE","download_json":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE.json","view_paper":"https://pith.science/paper/WWQMEVNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15995&json=true","fetch_graph":"https://pith.science/api/pith-number/WWQMEVNX5FZXWCYWKZA35GF5XE/graph.json","fetch_events":"https://pith.science/api/pith-number/WWQMEVNX5FZXWCYWKZA35GF5XE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE/action/storage_attestation","attest_author":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE/action/author_attestation","sign_citation":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE/action/citation_signature","submit_replication":"https://pith.science/pith/WWQMEVNX5FZXWCYWKZA35GF5XE/action/replication_record"}},"created_at":"2026-07-05T08:22:59.983791+00:00","updated_at":"2026-07-05T08:22:59.983791+00:00"}