{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SI5VJWH2EZYBU4QXK2O44KEFW3","short_pith_number":"pith:SI5VJWH2","schema_version":"1.0","canonical_sha256":"923b54d8fa26701a7217569dce2885b6c080c5d8b3acc629da245d23b4703af4","source":{"kind":"arxiv","id":"1901.01892","version":2},"attestation_state":"computed","paper":{"title":"Scale-Aware Trident Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Naiyan Wang, Yanghao Li, Yuntao Chen, Zhaoxiang Zhang","submitted_at":"2019-01-07T16:08:37Z","abstract_excerpt":"Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to spec"},"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":"1901.01892","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-07T16:08:37Z","cross_cats_sorted":[],"title_canon_sha256":"545fc6c79a65db7fcf03cfaf71d5c296e40938d15376be7764f810fa21c76796","abstract_canon_sha256":"78e3a03493bfb952383816e8026e9efb39defb608a73e9bc4e01b009a86571a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:24.842549Z","signature_b64":"shuvbQpzmgeIwHFe04Uhfd6bJNiBfUPBHeNi1+y590hG/bHC7c53FUIJ6Xnm2lpPI4AbXlvO+HRNeXoDnSAnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"923b54d8fa26701a7217569dce2885b6c080c5d8b3acc629da245d23b4703af4","last_reissued_at":"2026-07-04T23:58:24.842050Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:24.842050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale-Aware Trident Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Naiyan Wang, Yanghao Li, Yuntao Chen, Zhaoxiang Zhang","submitted_at":"2019-01-07T16:08:37Z","abstract_excerpt":"Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01892","kind":"arxiv","version":2},"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/1901.01892/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":"1901.01892","created_at":"2026-07-04T23:58:24.842115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.01892v2","created_at":"2026-07-04T23:58:24.842115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01892","created_at":"2026-07-04T23:58:24.842115+00:00"},{"alias_kind":"pith_short_12","alias_value":"SI5VJWH2EZYB","created_at":"2026-07-04T23:58:24.842115+00:00"},{"alias_kind":"pith_short_16","alias_value":"SI5VJWH2EZYBU4QX","created_at":"2026-07-04T23:58:24.842115+00:00"},{"alias_kind":"pith_short_8","alias_value":"SI5VJWH2","created_at":"2026-07-04T23:58:24.842115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.06881","citing_title":"Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3","json":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3.json","graph_json":"https://pith.science/api/pith-number/SI5VJWH2EZYBU4QXK2O44KEFW3/graph.json","events_json":"https://pith.science/api/pith-number/SI5VJWH2EZYBU4QXK2O44KEFW3/events.json","paper":"https://pith.science/paper/SI5VJWH2"},"agent_actions":{"view_html":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3","download_json":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3.json","view_paper":"https://pith.science/paper/SI5VJWH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.01892&json=true","fetch_graph":"https://pith.science/api/pith-number/SI5VJWH2EZYBU4QXK2O44KEFW3/graph.json","fetch_events":"https://pith.science/api/pith-number/SI5VJWH2EZYBU4QXK2O44KEFW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3/action/storage_attestation","attest_author":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3/action/author_attestation","sign_citation":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3/action/citation_signature","submit_replication":"https://pith.science/pith/SI5VJWH2EZYBU4QXK2O44KEFW3/action/replication_record"}},"created_at":"2026-07-04T23:58:24.842115+00:00","updated_at":"2026-07-04T23:58:24.842115+00:00"}