{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GE7CENXIAPYSNCMCQBBKFZFQWQ","short_pith_number":"pith:GE7CENXI","schema_version":"1.0","canonical_sha256":"313e2236e803f12689828042a2e4b0b4016207c90bf29302074cc7e3835c22f9","source":{"kind":"arxiv","id":"1703.02716","version":1},"attestation_state":"computed","paper":{"title":"A Pursuit of Temporal Accuracy in General Activity Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Limin Wang, Xiaoou Tang, Yuanjun Xiong, Yue Zhao","submitted_at":"2017-03-08T05:52:52Z","abstract_excerpt":"Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In this paper, we propose a generic framework that can accurately detect a wide variety of activities from untrimmed videos. Our first contribution is a novel proposal scheme that can efficiently generate candidates with accurate temporal boundaries. The other contribution is a cascaded classification pipeline that explicitly distinguishes between relevance and co"},"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":"1703.02716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-08T05:52:52Z","cross_cats_sorted":[],"title_canon_sha256":"74dcd1ee863fc36d086acc91b6246ea3c51c1c579f2f8515433a14e76fac2df7","abstract_canon_sha256":"15dc86604ac5ccc4d42b4f10a3283058da567838fd830329a400acc4079c6237"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:05.801243Z","signature_b64":"s5UcuEFh++lj0/715KkXQ8KDtritOIDPyZXOtXKpCcq2UBIg4bDXYnlJsDFiL8RKgNy1XQu/LV/Yb/3vTBA2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"313e2236e803f12689828042a2e4b0b4016207c90bf29302074cc7e3835c22f9","last_reissued_at":"2026-05-18T00:49:05.800829Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:05.800829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Pursuit of Temporal Accuracy in General Activity Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Limin Wang, Xiaoou Tang, Yuanjun Xiong, Yue Zhao","submitted_at":"2017-03-08T05:52:52Z","abstract_excerpt":"Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In this paper, we propose a generic framework that can accurately detect a wide variety of activities from untrimmed videos. Our first contribution is a novel proposal scheme that can efficiently generate candidates with accurate temporal boundaries. The other contribution is a cascaded classification pipeline that explicitly distinguishes between relevance and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02716","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":""},"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":"1703.02716","created_at":"2026-05-18T00:49:05.800884+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02716v1","created_at":"2026-05-18T00:49:05.800884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02716","created_at":"2026-05-18T00:49:05.800884+00:00"},{"alias_kind":"pith_short_12","alias_value":"GE7CENXIAPYS","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"GE7CENXIAPYSNCMC","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"GE7CENXI","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09702","citing_title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ","json":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ.json","graph_json":"https://pith.science/api/pith-number/GE7CENXIAPYSNCMCQBBKFZFQWQ/graph.json","events_json":"https://pith.science/api/pith-number/GE7CENXIAPYSNCMCQBBKFZFQWQ/events.json","paper":"https://pith.science/paper/GE7CENXI"},"agent_actions":{"view_html":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ","download_json":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ.json","view_paper":"https://pith.science/paper/GE7CENXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02716&json=true","fetch_graph":"https://pith.science/api/pith-number/GE7CENXIAPYSNCMCQBBKFZFQWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GE7CENXIAPYSNCMCQBBKFZFQWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ/action/storage_attestation","attest_author":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ/action/author_attestation","sign_citation":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ/action/citation_signature","submit_replication":"https://pith.science/pith/GE7CENXIAPYSNCMCQBBKFZFQWQ/action/replication_record"}},"created_at":"2026-05-18T00:49:05.800884+00:00","updated_at":"2026-05-18T00:49:05.800884+00:00"}