{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YD7BGVIW6NF6WPXQV3KPQQMOFF","short_pith_number":"pith:YD7BGVIW","schema_version":"1.0","canonical_sha256":"c0fe135516f34beb3ef0aed4f8418e297593af22c128b403bc1e215e656e7952","source":{"kind":"arxiv","id":"2209.05653","version":5},"attestation_state":"computed","paper":{"title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Junbin Zhang, Meng-Hsun Tsai, Pei-Hsuan Tsai","submitted_at":"2022-09-13T00:01:23Z","abstract_excerpt":"Video action segmentation have been widely applied in many fields. Most previous studies employed video-based vision models for this purpose. However, they often rely on a large receptive field, LSTM or Transformer methods to capture long-term dependencies within videos, leading to significant computational resource requirements. To address this challenge, graph-based model was proposed. However, previous graph-based models are less accurate. Hence, this study introduces a graph-structured approach named Semantic2Graph, to model long-term dependencies in videos, thereby reducing computational "},"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":"2209.05653","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-13T00:01:23Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"3880ab5f6c28c3a77f473670eb8d8d8b6c8f330d6374bda291bcfc575b2b952a","abstract_canon_sha256":"181f36f0c4dfe38e69ff31699e9a77044d8a6dd749b2a0efd163e047aca7b869"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:37.166930Z","signature_b64":"aJlVUf3QaejaiVkxOOA7xjThUtmXK3UV7R5/mW+gT6+gk9M2s/5wxhCWQpECDEiNYCFmINW4mFrZFIxoxWxFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0fe135516f34beb3ef0aed4f8418e297593af22c128b403bc1e215e656e7952","last_reissued_at":"2026-07-05T07:41:37.166437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:37.166437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Junbin Zhang, Meng-Hsun Tsai, Pei-Hsuan Tsai","submitted_at":"2022-09-13T00:01:23Z","abstract_excerpt":"Video action segmentation have been widely applied in many fields. Most previous studies employed video-based vision models for this purpose. However, they often rely on a large receptive field, LSTM or Transformer methods to capture long-term dependencies within videos, leading to significant computational resource requirements. To address this challenge, graph-based model was proposed. However, previous graph-based models are less accurate. Hence, this study introduces a graph-structured approach named Semantic2Graph, to model long-term dependencies in videos, thereby reducing computational "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05653","kind":"arxiv","version":5},"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/2209.05653/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":"2209.05653","created_at":"2026-07-05T07:41:37.166488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.05653v5","created_at":"2026-07-05T07:41:37.166488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05653","created_at":"2026-07-05T07:41:37.166488+00:00"},{"alias_kind":"pith_short_12","alias_value":"YD7BGVIW6NF6","created_at":"2026-07-05T07:41:37.166488+00:00"},{"alias_kind":"pith_short_16","alias_value":"YD7BGVIW6NF6WPXQ","created_at":"2026-07-05T07:41:37.166488+00:00"},{"alias_kind":"pith_short_8","alias_value":"YD7BGVIW","created_at":"2026-07-05T07:41:37.166488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15173","citing_title":"Boundary-Centric Active Learning for Temporal Action Segmentation","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF","json":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF.json","graph_json":"https://pith.science/api/pith-number/YD7BGVIW6NF6WPXQV3KPQQMOFF/graph.json","events_json":"https://pith.science/api/pith-number/YD7BGVIW6NF6WPXQV3KPQQMOFF/events.json","paper":"https://pith.science/paper/YD7BGVIW"},"agent_actions":{"view_html":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF","download_json":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF.json","view_paper":"https://pith.science/paper/YD7BGVIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.05653&json=true","fetch_graph":"https://pith.science/api/pith-number/YD7BGVIW6NF6WPXQV3KPQQMOFF/graph.json","fetch_events":"https://pith.science/api/pith-number/YD7BGVIW6NF6WPXQV3KPQQMOFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF/action/storage_attestation","attest_author":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF/action/author_attestation","sign_citation":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF/action/citation_signature","submit_replication":"https://pith.science/pith/YD7BGVIW6NF6WPXQV3KPQQMOFF/action/replication_record"}},"created_at":"2026-07-05T07:41:37.166488+00:00","updated_at":"2026-07-05T07:41:37.166488+00:00"}