{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4OHPPR3SNVSMWHLL66WFYX26DI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7ffa8072d1ede19517e201028845afa509d0ca93ecc1bf6820b7fd766cc00d72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-03T08:01:55Z","title_canon_sha256":"ebadba5916437835f5a68997350f66490fb782d5ba9df5c5980f584cb193ffe4"},"schema_version":"1.0","source":{"id":"2208.01897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.01897","created_at":"2026-07-05T04:45:51Z"},{"alias_kind":"arxiv_version","alias_value":"2208.01897v1","created_at":"2026-07-05T04:45:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01897","created_at":"2026-07-05T04:45:51Z"},{"alias_kind":"pith_short_12","alias_value":"4OHPPR3SNVSM","created_at":"2026-07-05T04:45:51Z"},{"alias_kind":"pith_short_16","alias_value":"4OHPPR3SNVSMWHLL","created_at":"2026-07-05T04:45:51Z"},{"alias_kind":"pith_short_8","alias_value":"4OHPPR3S","created_at":"2026-07-05T04:45:51Z"}],"graph_snapshots":[{"event_id":"sha256:c16a07b3901d2d143294ec87f9db0626e88cfecedab0dddc72a0c5f2da9a476c","target":"graph","created_at":"2026-07-05T04:45:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.01897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained action recognition is a challenging task in computer vision. As fine-grained datasets have small inter-class variations in spatial and temporal space, fine-grained action recognition model requires good temporal reasoning and discrimination of attribute action semantics. Leveraging on CNN's ability in capturing high level spatial-temporal feature representations and Transformer's modeling efficiency in capturing latent semantics and global dependencies, we investigate two frameworks that combine CNN vision backbone and Transformer Encoder to enhance fine-grained action recognition","authors_text":"Haosong Zhang, Hui Li Tan, Joo Hwee Lim, Liyuan Li, Mei Chee Leong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-03T08:01:55Z","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01897","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f4f259b7a22d39d2bd6073d6752b366cd183a3601eccfb7d02ff8443cf4824e5","target":"record","created_at":"2026-07-05T04:45:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7ffa8072d1ede19517e201028845afa509d0ca93ecc1bf6820b7fd766cc00d72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-03T08:01:55Z","title_canon_sha256":"ebadba5916437835f5a68997350f66490fb782d5ba9df5c5980f584cb193ffe4"},"schema_version":"1.0","source":{"id":"2208.01897","kind":"arxiv","version":1}},"canonical_sha256":"e38ef7c7726d64cb1d6bf7ac5c5f5e1a2df6311c79f3dce5944c7b4560d2dd5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e38ef7c7726d64cb1d6bf7ac5c5f5e1a2df6311c79f3dce5944c7b4560d2dd5f","first_computed_at":"2026-07-05T04:45:51.064171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:45:51.064171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fqUAjyj/SCgheS7tRpDfFsh+qy6N5DdmpeVb4W15wYTM4IA7xAu9mMhbbG8RUdrfLYu0VFb8ApCMUOfkMgSBAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:45:51.064649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.01897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4f259b7a22d39d2bd6073d6752b366cd183a3601eccfb7d02ff8443cf4824e5","sha256:c16a07b3901d2d143294ec87f9db0626e88cfecedab0dddc72a0c5f2da9a476c"],"state_sha256":"3ffb7ce9a020b184a20bc9a7388287f90063db6ae058fc0565240967976cc47b"}