{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MU3HKHFYORG6JAIVIKGHGLFVRL","short_pith_number":"pith:MU3HKHFY","schema_version":"1.0","canonical_sha256":"6536751cb8744de48115428c732cb58accd600b111cd54dbd1dc187e28ec8d2f","source":{"kind":"arxiv","id":"2005.12872","version":3},"attestation_state":"computed","paper":{"title":"End-to-End Object Detection with Transformers","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Kirillov, Francisco Massa, Gabriel Synnaeve, Nicolas Carion, Nicolas Usunier, Sergey Zagoruyko","submitted_at":"2020-05-26T17:06:38Z","abstract_excerpt":"We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge about the task. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons ab"},"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":"2005.12872","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-26T17:06:38Z","cross_cats_sorted":[],"title_canon_sha256":"07cbd34cb635a8011a196adef48e7601350966746c4b8acaa20f48d8a893395f","abstract_canon_sha256":"3ce9a1669789a510a82035c85c46a8547311495293494d6966cfce2b730e8cc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:22.552628Z","signature_b64":"YJkmTnX377luNO9iRsLZ2h44BatUy0aOzdsShb7K6bkciWnV/l6JZbkrwCsArbqcN+VpKc++akSiR1mWG7haCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6536751cb8744de48115428c732cb58accd600b111cd54dbd1dc187e28ec8d2f","last_reissued_at":"2026-07-05T01:06:22.552191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:22.552191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Object Detection with Transformers","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Kirillov, Francisco Massa, Gabriel Synnaeve, Nicolas Carion, Nicolas Usunier, Sergey Zagoruyko","submitted_at":"2020-05-26T17:06:38Z","abstract_excerpt":"We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge about the task. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons ab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.12872","kind":"arxiv","version":3},"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/2005.12872/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":"2005.12872","created_at":"2026-07-05T01:06:22.552246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.12872v3","created_at":"2026-07-05T01:06:22.552246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.12872","created_at":"2026-07-05T01:06:22.552246+00:00"},{"alias_kind":"pith_short_12","alias_value":"MU3HKHFYORG6","created_at":"2026-07-05T01:06:22.552246+00:00"},{"alias_kind":"pith_short_16","alias_value":"MU3HKHFYORG6JAIV","created_at":"2026-07-05T01:06:22.552246+00:00"},{"alias_kind":"pith_short_8","alias_value":"MU3HKHFY","created_at":"2026-07-05T01:06:22.552246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23825","citing_title":"From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20272","citing_title":"Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18824","citing_title":"Where Will They Go? Modelling Multimodal Pedestrian Manoeuvres from Ego-centric Videos","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17631","citing_title":"Better Queries, Cheaper Attention: Adapting Transformers for Efficient Sparse Reconstruction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12988","citing_title":"A Machine Learning Framework for Real-Time Personalized Ergonomic Pose Analysis","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03266","citing_title":"ReforMe: Re-Shaping Documents with Contextual Prompting and Layout-Aware Propagation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29059","citing_title":"Flow Matching in Feature Space for Stochastic World Modeling","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29161","citing_title":"GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29667","citing_title":"Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29391","citing_title":"Phast: Simultaneous reconstruction of photoelectron count and time profiles from PMT waveforms via machine learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2212.12130","citing_title":"Learning to Detect and Segment for Open Vocabulary Object Detection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2502.07553","citing_title":"Transformers Provably Learn Sparse XOR with Polylogarithmic Parameters","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20649","citing_title":"AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04086","citing_title":"LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04127","citing_title":"SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26633","citing_title":"SynSur: An end-to-end generative pipeline for synthetic industrial surface defect generation and detection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00244","citing_title":"Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20000","citing_title":"RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11081","citing_title":"MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09996","citing_title":"A Comparative Study of Modern Object Detectors for Robust Apple Detection in Orchard Imagery","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2304.13705","citing_title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL","json":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL.json","graph_json":"https://pith.science/api/pith-number/MU3HKHFYORG6JAIVIKGHGLFVRL/graph.json","events_json":"https://pith.science/api/pith-number/MU3HKHFYORG6JAIVIKGHGLFVRL/events.json","paper":"https://pith.science/paper/MU3HKHFY"},"agent_actions":{"view_html":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL","download_json":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL.json","view_paper":"https://pith.science/paper/MU3HKHFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.12872&json=true","fetch_graph":"https://pith.science/api/pith-number/MU3HKHFYORG6JAIVIKGHGLFVRL/graph.json","fetch_events":"https://pith.science/api/pith-number/MU3HKHFYORG6JAIVIKGHGLFVRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL/action/storage_attestation","attest_author":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL/action/author_attestation","sign_citation":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL/action/citation_signature","submit_replication":"https://pith.science/pith/MU3HKHFYORG6JAIVIKGHGLFVRL/action/replication_record"}},"created_at":"2026-07-05T01:06:22.552246+00:00","updated_at":"2026-07-05T01:06:22.552246+00:00"}