{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FK4FG2PL32CBQJIIU6KVLIMER7","short_pith_number":"pith:FK4FG2PL","schema_version":"1.0","canonical_sha256":"2ab85369ebde84182508a79555a1848fecd36fdb088955157ee0d2e51dc20afe","source":{"kind":"arxiv","id":"1908.03448","version":1},"attestation_state":"computed","paper":{"title":"Relation-Aware Pyramid Network (RapNet) for temporal action proposal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jialin Gao, Jiani Li, Jiwei Li, Xi Zhou, Yufeng Yuan, Zhixiang Shi","submitted_at":"2019-08-09T13:20:32Z","abstract_excerpt":"In this technical report, we describe our solution to temporal action proposal (task 1) in ActivityNet Challenge 2019. First, we fine-tune a ResNet-50-C3D CNN on ActivityNet v1.3 based on Kinetics pretrained model to extract snippet-level video representations and then we design a Relation-Aware Pyramid Network (RapNet) to generate temporal multiscale proposals with confidence score. After that, we employ a two-stage snippet-level boundary adjustment scheme to re-rank the order of generated proposals. Ensemble methods are also been used to improve the performance of our solution, which helps u"},"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":"1908.03448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-09T13:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"c2b02c681df29c84b62bbfb1abab95f888fb9f64ba9eb9eac79c57fc4f705ffb","abstract_canon_sha256":"128195512502213c09b423268fd9a616f195fa8c0139aaecb2574e8a80edee6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:40.051070Z","signature_b64":"2OX68vvERCGHXcKef6ZvL4WP3ZSe7mZIKjiEGUyayvZn6I/IYgBYVbK2BQutxazEGVz067LiStBRpAkmIc+0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ab85369ebde84182508a79555a1848fecd36fdb088955157ee0d2e51dc20afe","last_reissued_at":"2026-07-04T23:52:40.050728Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:40.050728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relation-Aware Pyramid Network (RapNet) for temporal action proposal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jialin Gao, Jiani Li, Jiwei Li, Xi Zhou, Yufeng Yuan, Zhixiang Shi","submitted_at":"2019-08-09T13:20:32Z","abstract_excerpt":"In this technical report, we describe our solution to temporal action proposal (task 1) in ActivityNet Challenge 2019. First, we fine-tune a ResNet-50-C3D CNN on ActivityNet v1.3 based on Kinetics pretrained model to extract snippet-level video representations and then we design a Relation-Aware Pyramid Network (RapNet) to generate temporal multiscale proposals with confidence score. After that, we employ a two-stage snippet-level boundary adjustment scheme to re-rank the order of generated proposals. Ensemble methods are also been used to improve the performance of our solution, which helps u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03448","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/1908.03448/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":"1908.03448","created_at":"2026-07-04T23:52:40.050786+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03448v1","created_at":"2026-07-04T23:52:40.050786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03448","created_at":"2026-07-04T23:52:40.050786+00:00"},{"alias_kind":"pith_short_12","alias_value":"FK4FG2PL32CB","created_at":"2026-07-04T23:52:40.050786+00:00"},{"alias_kind":"pith_short_16","alias_value":"FK4FG2PL32CBQJII","created_at":"2026-07-04T23:52:40.050786+00:00"},{"alias_kind":"pith_short_8","alias_value":"FK4FG2PL","created_at":"2026-07-04T23:52:40.050786+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/FK4FG2PL32CBQJIIU6KVLIMER7","json":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7.json","graph_json":"https://pith.science/api/pith-number/FK4FG2PL32CBQJIIU6KVLIMER7/graph.json","events_json":"https://pith.science/api/pith-number/FK4FG2PL32CBQJIIU6KVLIMER7/events.json","paper":"https://pith.science/paper/FK4FG2PL"},"agent_actions":{"view_html":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7","download_json":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7.json","view_paper":"https://pith.science/paper/FK4FG2PL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03448&json=true","fetch_graph":"https://pith.science/api/pith-number/FK4FG2PL32CBQJIIU6KVLIMER7/graph.json","fetch_events":"https://pith.science/api/pith-number/FK4FG2PL32CBQJIIU6KVLIMER7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7/action/storage_attestation","attest_author":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7/action/author_attestation","sign_citation":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7/action/citation_signature","submit_replication":"https://pith.science/pith/FK4FG2PL32CBQJIIU6KVLIMER7/action/replication_record"}},"created_at":"2026-07-04T23:52:40.050786+00:00","updated_at":"2026-07-04T23:52:40.050786+00:00"}