{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GTWMLFWM5K22MMSBPSQO2KVB6V","short_pith_number":"pith:GTWMLFWM","schema_version":"1.0","canonical_sha256":"34ecc596cceab5a632417ca0ed2aa1f55205e00edd72055d3ebcb91680fb2286","source":{"kind":"arxiv","id":"2405.03318","version":1},"attestation_state":"computed","paper":{"title":"Enhancing DETRs Variants through Improved Content Query and Similar Query Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chuangji Shi, Jiangwei Lao, Jian Wang, Jiaotuan Wang, Jingdong Chen, Xin Guo, Yingying Zhang","submitted_at":"2024-05-06T09:50:04Z","abstract_excerpt":"The design of the query is crucial for the performance of DETR and its variants. Each query consists of two components: a content part and a positional one. Traditionally, the content query is initialized with a zero or learnable embedding, lacking essential content information and resulting in sub-optimal performance. In this paper, we introduce a novel plug-and-play module, Self-Adaptive Content Query (SACQ), to address this limitation. The SACQ module utilizes features from the transformer encoder to generate content queries via self-attention pooling. This allows candidate queries to adapt"},"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":"2405.03318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T09:50:04Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"26ac3a71358b241dc857a2e2531715b566d4629c8640db5327ad2a1245d63af2","abstract_canon_sha256":"72a662c6b52e6565cfa6037d87544cddab4ed08b285bc6aa650a3d0e3290ae7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:01.494603Z","signature_b64":"OkPN0z3CWY4DnUmt5gz7AEwd3o5PZSUslYv7sRqmjWtu75u0OFAbaTT1svAwI52Hjc8fdffsehX76YqwBh3/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34ecc596cceab5a632417ca0ed2aa1f55205e00edd72055d3ebcb91680fb2286","last_reissued_at":"2026-07-05T08:16:01.494163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:01.494163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing DETRs Variants through Improved Content Query and Similar Query Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chuangji Shi, Jiangwei Lao, Jian Wang, Jiaotuan Wang, Jingdong Chen, Xin Guo, Yingying Zhang","submitted_at":"2024-05-06T09:50:04Z","abstract_excerpt":"The design of the query is crucial for the performance of DETR and its variants. Each query consists of two components: a content part and a positional one. Traditionally, the content query is initialized with a zero or learnable embedding, lacking essential content information and resulting in sub-optimal performance. In this paper, we introduce a novel plug-and-play module, Self-Adaptive Content Query (SACQ), to address this limitation. The SACQ module utilizes features from the transformer encoder to generate content queries via self-attention pooling. This allows candidate queries to adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03318","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/2405.03318/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":"2405.03318","created_at":"2026-07-05T08:16:01.494218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03318v1","created_at":"2026-07-05T08:16:01.494218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03318","created_at":"2026-07-05T08:16:01.494218+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTWMLFWM5K22","created_at":"2026-07-05T08:16:01.494218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTWMLFWM5K22MMSB","created_at":"2026-07-05T08:16:01.494218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTWMLFWM","created_at":"2026-07-05T08:16:01.494218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00374","citing_title":"LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Image","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V","json":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V.json","graph_json":"https://pith.science/api/pith-number/GTWMLFWM5K22MMSBPSQO2KVB6V/graph.json","events_json":"https://pith.science/api/pith-number/GTWMLFWM5K22MMSBPSQO2KVB6V/events.json","paper":"https://pith.science/paper/GTWMLFWM"},"agent_actions":{"view_html":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V","download_json":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V.json","view_paper":"https://pith.science/paper/GTWMLFWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03318&json=true","fetch_graph":"https://pith.science/api/pith-number/GTWMLFWM5K22MMSBPSQO2KVB6V/graph.json","fetch_events":"https://pith.science/api/pith-number/GTWMLFWM5K22MMSBPSQO2KVB6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V/action/storage_attestation","attest_author":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V/action/author_attestation","sign_citation":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V/action/citation_signature","submit_replication":"https://pith.science/pith/GTWMLFWM5K22MMSBPSQO2KVB6V/action/replication_record"}},"created_at":"2026-07-05T08:16:01.494218+00:00","updated_at":"2026-07-05T08:16:01.494218+00:00"}