{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6EPAZWHKBNORNTROYD6AQATGMT","short_pith_number":"pith:6EPAZWHK","schema_version":"1.0","canonical_sha256":"f11e0cd8ea0b5d16ce2ec0fc08026664ff455a67c4069875c2357c3d98dbe61a","source":{"kind":"arxiv","id":"1712.00960","version":4},"attestation_state":"computed","paper":{"title":"FSSD: Feature Fusion Single Shot Multibox Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuqiang Zhou, Lu Yang, Zuoxin Li","submitted_at":"2017-12-04T09:05:55Z","abstract_excerpt":"SSD (Single Shot Multibox Detector) is one of the best object detection algorithms with both high accuracy and fast speed. However, SSD's feature pyramid detection method makes it hard to fuse the features from different scales. In this paper, we proposed FSSD (Feature Fusion Single Shot Multibox Detector), an enhanced SSD with a novel and lightweight feature fusion module which can improve the performance significantly over SSD with just a little speed drop. In the feature fusion module, features from different layers with different scales are concatenated together, followed by some down-samp"},"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":"1712.00960","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T09:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"a8e2aa5913c2a16a47d02e64abfc03405797ba1b0c0bffbf9ec086268490bf4d","abstract_canon_sha256":"b96487a1db545a3d2b676d43e2542b0a2335694abaee0e8762374ee249424f4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:25.990256Z","signature_b64":"pM0v34tyx4u+Oiuw0rr7gclobsndBpMd+t5uO0qGvd0PXmqP6TM2laiMwpoUQqOMKCHq7HBtPK3nNipplhjNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f11e0cd8ea0b5d16ce2ec0fc08026664ff455a67c4069875c2357c3d98dbe61a","last_reissued_at":"2026-07-05T07:48:25.989807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:25.989807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FSSD: Feature Fusion Single Shot Multibox Detector","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuqiang Zhou, Lu Yang, Zuoxin Li","submitted_at":"2017-12-04T09:05:55Z","abstract_excerpt":"SSD (Single Shot Multibox Detector) is one of the best object detection algorithms with both high accuracy and fast speed. However, SSD's feature pyramid detection method makes it hard to fuse the features from different scales. In this paper, we proposed FSSD (Feature Fusion Single Shot Multibox Detector), an enhanced SSD with a novel and lightweight feature fusion module which can improve the performance significantly over SSD with just a little speed drop. In the feature fusion module, features from different layers with different scales are concatenated together, followed by some down-samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00960","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/1712.00960/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":"1712.00960","created_at":"2026-07-05T07:48:25.989863+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00960v4","created_at":"2026-07-05T07:48:25.989863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00960","created_at":"2026-07-05T07:48:25.989863+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EPAZWHKBNOR","created_at":"2026-07-05T07:48:25.989863+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EPAZWHKBNORNTRO","created_at":"2026-07-05T07:48:25.989863+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EPAZWHK","created_at":"2026-07-05T07:48:25.989863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25312","citing_title":"LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"1907.10310","citing_title":"Towards Adversarially Robust Object Detection","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22169","citing_title":"Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14689","citing_title":"Are Candidate Models Really Needed for Active Learning?","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT","json":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT.json","graph_json":"https://pith.science/api/pith-number/6EPAZWHKBNORNTROYD6AQATGMT/graph.json","events_json":"https://pith.science/api/pith-number/6EPAZWHKBNORNTROYD6AQATGMT/events.json","paper":"https://pith.science/paper/6EPAZWHK"},"agent_actions":{"view_html":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT","download_json":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT.json","view_paper":"https://pith.science/paper/6EPAZWHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00960&json=true","fetch_graph":"https://pith.science/api/pith-number/6EPAZWHKBNORNTROYD6AQATGMT/graph.json","fetch_events":"https://pith.science/api/pith-number/6EPAZWHKBNORNTROYD6AQATGMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT/action/storage_attestation","attest_author":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT/action/author_attestation","sign_citation":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT/action/citation_signature","submit_replication":"https://pith.science/pith/6EPAZWHKBNORNTROYD6AQATGMT/action/replication_record"}},"created_at":"2026-07-05T07:48:25.989863+00:00","updated_at":"2026-07-05T07:48:25.989863+00:00"}