{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PFSCYCDRVWZXMSHBBEFOGJUHLI","short_pith_number":"pith:PFSCYCDR","schema_version":"1.0","canonical_sha256":"79642c0871adb37648e1090ae326875a18bdca1501d37760c5a68fd4818279fc","source":{"kind":"arxiv","id":"2104.07719","version":4},"attestation_state":"computed","paper":{"title":"Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Guangxing Han, Jiawei Ma, Shih-Fu Chang, Shiyuan Huang, Yicheng He","submitted_at":"2021-04-15T19:01:27Z","abstract_excerpt":"Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object proposal is a key ingredient in modern object detectors. However, the quality of proposals generated for few-shot classes using existing methods is far worse than that of many-shot classes, e.g., missing boxes for few-shot classes due to misclassification or inaccurate spatial locations with respect to true objects. To address the noisy proposal problem, we propose a novel meta-learning based FSOD model by jointly o"},"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":"2104.07719","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-15T19:01:27Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"d2bae63cf863d47b3c7719029d23e04193b38d20e28f6ae7d8799516ecb866ec","abstract_canon_sha256":"900208551599afe325aa22fb5c23fb40d3c7ebaf3131ac79de15d1024fcd0158"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:26.242286Z","signature_b64":"H74aFlpnnMe8Ie4szXe/3f4O1iFz5ff349v/SkD1kapn7a+xJkhb5RD6vGgzVxCZ3dxL3JjdfjXBIWwV+VYnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79642c0871adb37648e1090ae326875a18bdca1501d37760c5a68fd4818279fc","last_reissued_at":"2026-07-05T04:28:26.241878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:26.241878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Guangxing Han, Jiawei Ma, Shih-Fu Chang, Shiyuan Huang, Yicheng He","submitted_at":"2021-04-15T19:01:27Z","abstract_excerpt":"Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object proposal is a key ingredient in modern object detectors. However, the quality of proposals generated for few-shot classes using existing methods is far worse than that of many-shot classes, e.g., missing boxes for few-shot classes due to misclassification or inaccurate spatial locations with respect to true objects. To address the noisy proposal problem, we propose a novel meta-learning based FSOD model by jointly o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07719","kind":"arxiv","version":4},"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/2104.07719/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":"2104.07719","created_at":"2026-07-05T04:28:26.241930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.07719v4","created_at":"2026-07-05T04:28:26.241930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07719","created_at":"2026-07-05T04:28:26.241930+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFSCYCDRVWZX","created_at":"2026-07-05T04:28:26.241930+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFSCYCDRVWZXMSHB","created_at":"2026-07-05T04:28:26.241930+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFSCYCDR","created_at":"2026-07-05T04:28:26.241930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15308","citing_title":"Few-Shot Object Detection via Spatial-Channel State Space Model","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI","json":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI.json","graph_json":"https://pith.science/api/pith-number/PFSCYCDRVWZXMSHBBEFOGJUHLI/graph.json","events_json":"https://pith.science/api/pith-number/PFSCYCDRVWZXMSHBBEFOGJUHLI/events.json","paper":"https://pith.science/paper/PFSCYCDR"},"agent_actions":{"view_html":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI","download_json":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI.json","view_paper":"https://pith.science/paper/PFSCYCDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.07719&json=true","fetch_graph":"https://pith.science/api/pith-number/PFSCYCDRVWZXMSHBBEFOGJUHLI/graph.json","fetch_events":"https://pith.science/api/pith-number/PFSCYCDRVWZXMSHBBEFOGJUHLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI/action/storage_attestation","attest_author":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI/action/author_attestation","sign_citation":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI/action/citation_signature","submit_replication":"https://pith.science/pith/PFSCYCDRVWZXMSHBBEFOGJUHLI/action/replication_record"}},"created_at":"2026-07-05T04:28:26.241930+00:00","updated_at":"2026-07-05T04:28:26.241930+00:00"}