{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZDQLG4UWGMKN366B4WYOVDMTOC","short_pith_number":"pith:ZDQLG4UW","schema_version":"1.0","canonical_sha256":"c8e0b372963314ddfbc1e5b0ea8d9370a9718cc251f0f6347e695e60da2ddcbb","source":{"kind":"arxiv","id":"2406.08814","version":1},"attestation_state":"computed","paper":{"title":"Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Feng, Errui Ding, Hao Zhou, Jingdong Wang, Kun Yao, Wenyu Liu, Xiaohu Huang, Xinggang Wang, Zhengqi Zhao","submitted_at":"2024-06-13T05:15:52Z","abstract_excerpt":"The key to action counting is accurately locating each video's repetitive actions. Instead of estimating the probability of each frame belonging to an action directly, we propose a dual-branch network, i.e., SkimFocusNet, working in a two-step manner. The model draws inspiration from empirical observations indicating that humans typically engage in coarse skimming of entire sequences to grasp the general action pattern initially, followed by a finer, frame-by-frame focus to determine if it aligns with the target action. Specifically, SkimFocusNet incorporates a skim branch and a focus branch. "},"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":"2406.08814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T05:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"a5e5bbfcc41f36d31dfe5767148a17f0f8a40f81db84dda4d1932c2fc315bb61","abstract_canon_sha256":"4818fd468f01c7ef581b2f83b91487ef1d8a7a87550fc459180460d717bbe52f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:23.814888Z","signature_b64":"4rYTdHstktec3J+u90TcWv7bwj32FI/7JPuEBNq/twDl+BUXzb+3jQTlo8CsezRNQk66Scw0S45rMX5hzX5AAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e0b372963314ddfbc1e5b0ea8d9370a9718cc251f0f6347e695e60da2ddcbb","last_reissued_at":"2026-07-05T08:31:23.814456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:23.814456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Feng, Errui Ding, Hao Zhou, Jingdong Wang, Kun Yao, Wenyu Liu, Xiaohu Huang, Xinggang Wang, Zhengqi Zhao","submitted_at":"2024-06-13T05:15:52Z","abstract_excerpt":"The key to action counting is accurately locating each video's repetitive actions. Instead of estimating the probability of each frame belonging to an action directly, we propose a dual-branch network, i.e., SkimFocusNet, working in a two-step manner. The model draws inspiration from empirical observations indicating that humans typically engage in coarse skimming of entire sequences to grasp the general action pattern initially, followed by a finer, frame-by-frame focus to determine if it aligns with the target action. Specifically, SkimFocusNet incorporates a skim branch and a focus branch. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08814","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/2406.08814/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":"2406.08814","created_at":"2026-07-05T08:31:23.814519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08814v1","created_at":"2026-07-05T08:31:23.814519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08814","created_at":"2026-07-05T08:31:23.814519+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDQLG4UWGMKN","created_at":"2026-07-05T08:31:23.814519+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDQLG4UWGMKN366B","created_at":"2026-07-05T08:31:23.814519+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDQLG4UW","created_at":"2026-07-05T08:31:23.814519+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/ZDQLG4UWGMKN366B4WYOVDMTOC","json":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC.json","graph_json":"https://pith.science/api/pith-number/ZDQLG4UWGMKN366B4WYOVDMTOC/graph.json","events_json":"https://pith.science/api/pith-number/ZDQLG4UWGMKN366B4WYOVDMTOC/events.json","paper":"https://pith.science/paper/ZDQLG4UW"},"agent_actions":{"view_html":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC","download_json":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC.json","view_paper":"https://pith.science/paper/ZDQLG4UW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08814&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDQLG4UWGMKN366B4WYOVDMTOC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDQLG4UWGMKN366B4WYOVDMTOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC/action/storage_attestation","attest_author":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC/action/author_attestation","sign_citation":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC/action/citation_signature","submit_replication":"https://pith.science/pith/ZDQLG4UWGMKN366B4WYOVDMTOC/action/replication_record"}},"created_at":"2026-07-05T08:31:23.814519+00:00","updated_at":"2026-07-05T08:31:23.814519+00:00"}